made everything compile and even run somehow

apps/traincascade/CMakeLists.txt

@@ -1,4 +1,4 @@
-set(OPENCV_TRAINCASCADE_DEPS opencv_core opencv_ml opencv_imgproc opencv_photo opencv_objdetect opencv_imgcodecs opencv_videoio opencv_highgui opencv_calib3d opencv_video opencv_features2d)
+set(OPENCV_TRAINCASCADE_DEPS opencv_core opencv_imgproc opencv_objdetect opencv_imgcodecs opencv_highgui opencv_calib3d opencv_features2d)
 ocv_check_dependencies(${OPENCV_TRAINCASCADE_DEPS})
 
 if(NOT OCV_DEPENDENCIES_FOUND)
@@ -10,13 +10,10 @@ project(traincascade)
 ocv_include_directories("${CMAKE_CURRENT_SOURCE_DIR}" "${OpenCV_SOURCE_DIR}/include/opencv")
 ocv_include_modules(${OPENCV_TRAINCASCADE_DEPS})
 
-set(traincascade_files traincascade.cpp
-  cascadeclassifier.cpp cascadeclassifier.h
-  boost.cpp boost.h features.cpp traincascade_features.h
-  haarfeatures.cpp haarfeatures.h
-  lbpfeatures.cpp lbpfeatures.h
-  HOGfeatures.cpp HOGfeatures.h
-  imagestorage.cpp imagestorage.h)
+file(GLOB SRCS *.cpp)
+file(GLOB HDRS *.h*)
+
+set(traincascade_files ${SRCS} ${HDRS})
 
 set(the_target opencv_traincascade)
 add_executable(${the_target} ${traincascade_files})

apps/traincascade/boost.h

@@ -2,7 +2,7 @@
 #define _OPENCV_BOOST_H_
 
 #include "traincascade_features.h"
-#include "ml.h"
+#include "old_ml.hpp"
 
 struct CvCascadeBoostParams : CvBoostParams
 {

apps/traincascade/cascadeclassifier.h

@@ -7,8 +7,6 @@
 #include "lbpfeatures.h"
 #include "HOGfeatures.h" //new
 #include "boost.h"
-#include "cv.h"
-#include "cxcore.h"
 
 #define CC_CASCADE_FILENAME "cascade.xml"
 #define CC_PARAMS_FILENAME "params.xml"

apps/traincascade/old_ml_data.cpp

@@ -0,0 +1,792 @@
+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                        Intel License Agreement
+//
+// Copyright (C) 2000, Intel Corporation, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of Intel Corporation may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Intel Corporation or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#include "old_ml_precomp.hpp"
+#include <ctype.h>
+
+#define MISS_VAL    FLT_MAX
+#define CV_VAR_MISS    0
+
+CvTrainTestSplit::CvTrainTestSplit()
+{
+    train_sample_part_mode = CV_COUNT;
+    train_sample_part.count = -1;
+    mix = false;
+}
+
+CvTrainTestSplit::CvTrainTestSplit( int _train_sample_count, bool _mix )
+{
+    train_sample_part_mode = CV_COUNT;
+    train_sample_part.count = _train_sample_count;
+    mix = _mix;
+}
+
+CvTrainTestSplit::CvTrainTestSplit( float _train_sample_portion, bool _mix )
+{
+    train_sample_part_mode = CV_PORTION;
+    train_sample_part.portion = _train_sample_portion;
+    mix = _mix;
+}
+
+////////////////
+
+CvMLData::CvMLData()
+{
+    values = missing = var_types = var_idx_mask = response_out = var_idx_out = var_types_out = 0;
+    train_sample_idx = test_sample_idx = 0;
+    header_lines_number = 0;
+    sample_idx = 0;
+    response_idx = -1;
+
+    train_sample_count = -1;
+
+    delimiter = ',';
+    miss_ch = '?';
+    //flt_separator = '.';
+
+    rng = &cv::theRNG();
+}
+
+CvMLData::~CvMLData()
+{
+    clear();
+}
+
+void CvMLData::free_train_test_idx()
+{
+    cvReleaseMat( &train_sample_idx );
+    cvReleaseMat( &test_sample_idx );
+    sample_idx = 0;
+}
+
+void CvMLData::clear()
+{
+    class_map.clear();
+
+    cvReleaseMat( &values );
+    cvReleaseMat( &missing );
+    cvReleaseMat( &var_types );
+    cvReleaseMat( &var_idx_mask );
+
+    cvReleaseMat( &response_out );
+    cvReleaseMat( &var_idx_out );
+    cvReleaseMat( &var_types_out );
+
+    free_train_test_idx();
+
+    total_class_count = 0;
+
+    response_idx = -1;
+
+    train_sample_count = -1;
+}
+
+
+void CvMLData::set_header_lines_number( int idx )
+{
+    header_lines_number = std::max(0, idx);
+}
+
+int CvMLData::get_header_lines_number() const
+{
+    return header_lines_number;
+}
+
+static char *fgets_chomp(char *str, int n, FILE *stream)
+{
+    char *head = fgets(str, n, stream);
+    if( head )
+    {
+        for(char *tail = head + strlen(head) - 1; tail >= head; --tail)
+        {
+            if( *tail != '\r'  && *tail != '\n' )
+                break;
+            *tail = '\0';
+        }
+    }
+    return head;
+}
+
+
+int CvMLData::read_csv(const char* filename)
+{
+    const int M = 1000000;
+    const char str_delimiter[3] = { ' ', delimiter, '\0' };
+    FILE* file = 0;
+    CvMemStorage* storage;
+    CvSeq* seq;
+    char *ptr;
+    float* el_ptr;
+    CvSeqReader reader;
+    int cols_count = 0;
+    uchar *var_types_ptr = 0;
+
+    clear();
+
+    file = fopen( filename, "rt" );
+
+    if( !file )
+        return -1;
+
+    std::vector<char> _buf(M);
+    char* buf = &_buf[0];
+
+    // skip header lines
+    for( int i = 0; i < header_lines_number; i++ )
+    {
+        if( fgets( buf, M, file ) == 0 )
+        {
+            fclose(file);
+            return -1;
+        }
+    }
+
+    // read the first data line and determine the number of variables
+    if( !fgets_chomp( buf, M, file ))
+    {
+        fclose(file);
+        return -1;
+    }
+
+    ptr = buf;
+    while( *ptr == ' ' )
+        ptr++;
+    for( ; *ptr != '\0'; )
+    {
+        if(*ptr == delimiter || *ptr == ' ')
+        {
+            cols_count++;
+            ptr++;
+            while( *ptr == ' ' ) ptr++;
+        }
+        else
+            ptr++;
+    }
+
+    cols_count++;
+
+    if ( cols_count == 0)
+    {
+        fclose(file);
+        return -1;
+    }
+
+    // create temporary memory storage to store the whole database
+    el_ptr = new float[cols_count];
+    storage = cvCreateMemStorage();
+    seq = cvCreateSeq( 0, sizeof(*seq), cols_count*sizeof(float), storage );
+
+    var_types = cvCreateMat( 1, cols_count, CV_8U );
+    cvZero( var_types );
+    var_types_ptr = var_types->data.ptr;
+
+    for(;;)
+    {
+        char *token = NULL;
+        int type;
+        token = strtok(buf, str_delimiter);
+        if (!token)
+            break;
+        for (int i = 0; i < cols_count-1; i++)
+        {
+            str_to_flt_elem( token, el_ptr[i], type);
+            var_types_ptr[i] |= type;
+            token = strtok(NULL, str_delimiter);
+            if (!token)
+            {
+                fclose(file);
+                delete [] el_ptr;
+                return -1;
+            }
+        }
+        str_to_flt_elem( token, el_ptr[cols_count-1], type);
+        var_types_ptr[cols_count-1] |= type;
+        cvSeqPush( seq, el_ptr );
+        if( !fgets_chomp( buf, M, file ) )
+            break;
+    }
+    fclose(file);
+
+    values = cvCreateMat( seq->total, cols_count, CV_32FC1 );
+    missing = cvCreateMat( seq->total, cols_count, CV_8U );
+    var_idx_mask = cvCreateMat( 1, values->cols, CV_8UC1 );
+    cvSet( var_idx_mask, cvRealScalar(1) );
+    train_sample_count = seq->total;
+
+    cvStartReadSeq( seq, &reader );
+    for(int i = 0; i < seq->total; i++ )
+    {
+        const float* sdata = (float*)reader.ptr;
+        float* ddata = values->data.fl + cols_count*i;
+        uchar* dm = missing->data.ptr + cols_count*i;
+
+        for( int j = 0; j < cols_count; j++ )
+        {
+            ddata[j] = sdata[j];
+            dm[j] = ( fabs( MISS_VAL - sdata[j] ) <= FLT_EPSILON );
+        }
+        CV_NEXT_SEQ_ELEM( seq->elem_size, reader );
+    }
+
+    if ( cvNorm( missing, 0, CV_L1 ) <= FLT_EPSILON )
+        cvReleaseMat( &missing );
+
+    cvReleaseMemStorage( &storage );
+    delete []el_ptr;
+    return 0;
+}
+
+const CvMat* CvMLData::get_values() const
+{
+    return values;
+}
+
+const CvMat* CvMLData::get_missing() const
+{
+    CV_FUNCNAME( "CvMLData::get_missing" );
+    __BEGIN__;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+
+    __END__;
+
+    return missing;
+}
+
+const std::map<cv::String, int>& CvMLData::get_class_labels_map() const
+{
+    return class_map;
+}
+
+void CvMLData::str_to_flt_elem( const char* token, float& flt_elem, int& type)
+{
+
+    char* stopstring = NULL;
+    flt_elem = (float)strtod( token, &stopstring );
+    assert( stopstring );
+    type = CV_VAR_ORDERED;
+    if ( *stopstring == miss_ch && strlen(stopstring) == 1 ) // missed value
+    {
+        flt_elem = MISS_VAL;
+        type = CV_VAR_MISS;
+    }
+    else
+    {
+        if ( (*stopstring != 0) && (*stopstring != '\n') && (strcmp(stopstring, "\r\n") != 0) ) // class label
+        {
+            int idx = class_map[token];
+            if ( idx == 0)
+            {
+                total_class_count++;
+                idx = total_class_count;
+                class_map[token] = idx;
+            }
+            flt_elem = (float)idx;
+            type = CV_VAR_CATEGORICAL;
+        }
+    }
+}
+
+void CvMLData::set_delimiter(char ch)
+{
+    CV_FUNCNAME( "CvMLData::set_delimited" );
+    __BEGIN__;
+
+    if (ch == miss_ch /*|| ch == flt_separator*/)
+        CV_ERROR(CV_StsBadArg, "delimited, miss_character and flt_separator must be different");
+
+    delimiter = ch;
+
+    __END__;
+}
+
+char CvMLData::get_delimiter() const
+{
+    return delimiter;
+}
+
+void CvMLData::set_miss_ch(char ch)
+{
+    CV_FUNCNAME( "CvMLData::set_miss_ch" );
+    __BEGIN__;
+
+    if (ch == delimiter/* || ch == flt_separator*/)
+        CV_ERROR(CV_StsBadArg, "delimited, miss_character and flt_separator must be different");
+
+    miss_ch = ch;
+
+    __END__;
+}
+
+char CvMLData::get_miss_ch() const
+{
+    return miss_ch;
+}
+
+void CvMLData::set_response_idx( int idx )
+{
+    CV_FUNCNAME( "CvMLData::set_response_idx" );
+    __BEGIN__;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+
+    if ( idx >= values->cols)
+        CV_ERROR( CV_StsBadArg, "idx value is not correct" );
+
+    if ( response_idx >= 0 )
+        chahge_var_idx( response_idx, true );
+    if ( idx >= 0 )
+        chahge_var_idx( idx, false );
+    response_idx = idx;
+
+    __END__;
+}
+
+int CvMLData::get_response_idx() const
+{
+    CV_FUNCNAME( "CvMLData::get_response_idx" );
+    __BEGIN__;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+     __END__;
+    return response_idx;
+}
+
+void CvMLData::change_var_type( int var_idx, int type )
+{
+    CV_FUNCNAME( "CvMLData::change_var_type" );
+    __BEGIN__;
+
+    int var_count = 0;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+
+     var_count = values->cols;
+
+    if ( var_idx < 0 || var_idx >= var_count)
+        CV_ERROR( CV_StsBadArg, "var_idx is not correct" );
+
+    if ( type != CV_VAR_ORDERED && type != CV_VAR_CATEGORICAL)
+         CV_ERROR( CV_StsBadArg, "type is not correct" );
+
+    assert( var_types );
+    if ( var_types->data.ptr[var_idx] == CV_VAR_CATEGORICAL && type == CV_VAR_ORDERED)
+        CV_ERROR( CV_StsBadArg, "it`s impossible to assign CV_VAR_ORDERED type to categorical variable" );
+    var_types->data.ptr[var_idx] = (uchar)type;
+
+    __END__;
+
+    return;
+}
+
+void CvMLData::set_var_types( const char* str )
+{
+    CV_FUNCNAME( "CvMLData::set_var_types" );
+    __BEGIN__;
+
+    const char* ord = 0, *cat = 0;
+    int var_count = 0, set_var_type_count = 0;
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+
+    var_count = values->cols;
+
+    assert( var_types );
+
+    ord = strstr( str, "ord" );
+    cat = strstr( str, "cat" );
+    if ( !ord && !cat )
+        CV_ERROR( CV_StsBadArg, "types string is not correct" );
+
+    if ( !ord && strlen(cat) == 3 ) // str == "cat"
+    {
+        cvSet( var_types, cvScalarAll(CV_VAR_CATEGORICAL) );
+        return;
+    }
+
+    if ( !cat && strlen(ord) == 3 ) // str == "ord"
+    {
+        cvSet( var_types, cvScalarAll(CV_VAR_ORDERED) );
+        return;
+    }
+
+    if ( ord ) // parse ord str
+    {
+        char* stopstring = NULL;
+        if ( ord[3] != '[')
+            CV_ERROR( CV_StsBadArg, "types string is not correct" );
+
+        ord += 4; // pass "ord["
+        do
+        {
+            int b1 = (int)strtod( ord, &stopstring );
+            if ( *stopstring == 0 || (*stopstring != ',' && *stopstring != ']' && *stopstring != '-') )
+                CV_ERROR( CV_StsBadArg, "types string is not correct" );
+            ord = stopstring + 1;
+            if ( (stopstring[0] == ',') || (stopstring[0] == ']'))
+            {
+                if ( var_types->data.ptr[b1] == CV_VAR_CATEGORICAL)
+                    CV_ERROR( CV_StsBadArg, "it`s impossible to assign CV_VAR_ORDERED type to categorical variable" );
+                var_types->data.ptr[b1] = CV_VAR_ORDERED;
+                set_var_type_count++;
+            }
+            else
+            {
+                if ( stopstring[0] == '-')
+                {
+                    int b2 = (int)strtod( ord, &stopstring);
+                    if ( (*stopstring == 0) || (*stopstring != ',' && *stopstring != ']') )
+                        CV_ERROR( CV_StsBadArg, "types string is not correct" );
+                    ord = stopstring + 1;
+                    for (int i = b1; i <= b2; i++)
+                    {
+                        if ( var_types->data.ptr[i] == CV_VAR_CATEGORICAL)
+                            CV_ERROR( CV_StsBadArg, "it`s impossible to assign CV_VAR_ORDERED type to categorical variable" );
+                        var_types->data.ptr[i] = CV_VAR_ORDERED;
+                    }
+                    set_var_type_count += b2 - b1 + 1;
+                }
+                else
+                    CV_ERROR( CV_StsBadArg, "types string is not correct" );
+
+            }
+        }
+        while (*stopstring != ']');
+
+        if ( stopstring[1] != '\0' && stopstring[1] != ',')
+            CV_ERROR( CV_StsBadArg, "types string is not correct" );
+    }
+
+    if ( cat ) // parse cat str
+    {
+        char* stopstring = NULL;
+        if ( cat[3] != '[')
+            CV_ERROR( CV_StsBadArg, "types string is not correct" );
+
+        cat += 4; // pass "cat["
+        do
+        {
+            int b1 = (int)strtod( cat, &stopstring );
+            if ( *stopstring == 0 || (*stopstring != ',' && *stopstring != ']' && *stopstring != '-') )
+                CV_ERROR( CV_StsBadArg, "types string is not correct" );
+            cat = stopstring + 1;
+            if ( (stopstring[0] == ',') || (stopstring[0] == ']'))
+            {
+                var_types->data.ptr[b1] = CV_VAR_CATEGORICAL;
+                set_var_type_count++;
+            }
+            else
+            {
+                if ( stopstring[0] == '-')
+                {
+                    int b2 = (int)strtod( cat, &stopstring);
+                    if ( (*stopstring == 0) || (*stopstring != ',' && *stopstring != ']') )
+                        CV_ERROR( CV_StsBadArg, "types string is not correct" );
+                    cat = stopstring + 1;
+                    for (int i = b1; i <= b2; i++)
+                        var_types->data.ptr[i] = CV_VAR_CATEGORICAL;
+                    set_var_type_count += b2 - b1 + 1;
+                }
+                else
+                    CV_ERROR( CV_StsBadArg, "types string is not correct" );
+
+            }
+        }
+        while (*stopstring != ']');
+
+        if ( stopstring[1] != '\0' && stopstring[1] != ',')
+            CV_ERROR( CV_StsBadArg, "types string is not correct" );
+    }
+
+    if (set_var_type_count != var_count)
+        CV_ERROR( CV_StsBadArg, "types string is not correct" );
+
+     __END__;
+}
+
+const CvMat* CvMLData::get_var_types()
+{
+    CV_FUNCNAME( "CvMLData::get_var_types" );
+    __BEGIN__;
+
+    uchar *var_types_out_ptr = 0;
+    int avcount, vt_size;
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+
+    assert( var_idx_mask );
+
+    avcount = cvFloor( cvNorm( var_idx_mask, 0, CV_L1 ) );
+    vt_size = avcount + (response_idx >= 0);
+
+    if ( avcount == values->cols || (avcount == values->cols-1 && response_idx == values->cols-1) )
+        return var_types;
+
+    if ( !var_types_out || ( var_types_out && var_types_out->cols != vt_size ) )
+    {
+        cvReleaseMat( &var_types_out );
+        var_types_out = cvCreateMat( 1, vt_size, CV_8UC1 );
+    }
+
+    var_types_out_ptr = var_types_out->data.ptr;
+    for( int i = 0; i < var_types->cols; i++)
+    {
+        if (i == response_idx || !var_idx_mask->data.ptr[i]) continue;
+        *var_types_out_ptr = var_types->data.ptr[i];
+        var_types_out_ptr++;
+    }
+    if ( response_idx >= 0 )
+        *var_types_out_ptr = var_types->data.ptr[response_idx];
+
+    __END__;
+
+    return var_types_out;
+}
+
+int CvMLData::get_var_type( int var_idx ) const
+{
+    return var_types->data.ptr[var_idx];
+}
+
+const CvMat* CvMLData::get_responses()
+{
+    CV_FUNCNAME( "CvMLData::get_responses_ptr" );
+    __BEGIN__;
+
+    int var_count = 0;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+    var_count = values->cols;
+
+    if ( response_idx < 0 || response_idx >= var_count )
+       return 0;
+    if ( !response_out )
+        response_out = cvCreateMatHeader( values->rows, 1, CV_32FC1 );
+    else
+        cvInitMatHeader( response_out, values->rows, 1, CV_32FC1);
+    cvGetCol( values, response_out, response_idx );
+
+    __END__;
+
+    return response_out;
+}
+
+void CvMLData::set_train_test_split( const CvTrainTestSplit * spl)
+{
+    CV_FUNCNAME( "CvMLData::set_division" );
+    __BEGIN__;
+
+    int sample_count = 0;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+
+    sample_count = values->rows;
+
+    float train_sample_portion;
+
+    if (spl->train_sample_part_mode == CV_COUNT)
+    {
+        train_sample_count = spl->train_sample_part.count;
+        if (train_sample_count > sample_count)
+            CV_ERROR( CV_StsBadArg, "train samples count is not correct" );
+        train_sample_count = train_sample_count<=0 ? sample_count : train_sample_count;
+    }
+    else // dtype.train_sample_part_mode == CV_PORTION
+    {
+        train_sample_portion = spl->train_sample_part.portion;
+        if ( train_sample_portion > 1)
+            CV_ERROR( CV_StsBadArg, "train samples count is not correct" );
+        train_sample_portion = train_sample_portion <= FLT_EPSILON ||
+            1 - train_sample_portion <= FLT_EPSILON ? 1 : train_sample_portion;
+        train_sample_count = std::max(1, cvFloor( train_sample_portion * sample_count ));
+    }
+
+    if ( train_sample_count == sample_count )
+    {
+        free_train_test_idx();
+        return;
+    }
+
+    if ( train_sample_idx && train_sample_idx->cols != train_sample_count )
+        free_train_test_idx();
+
+    if ( !sample_idx)
+    {
+        int test_sample_count = sample_count- train_sample_count;
+        sample_idx = (int*)cvAlloc( sample_count * sizeof(sample_idx[0]) );
+        for (int i = 0; i < sample_count; i++ )
+            sample_idx[i] = i;
+        train_sample_idx = cvCreateMatHeader( 1, train_sample_count, CV_32SC1 );
+        *train_sample_idx = cvMat( 1, train_sample_count, CV_32SC1, &sample_idx[0] );
+
+        CV_Assert(test_sample_count > 0);
+        test_sample_idx = cvCreateMatHeader( 1, test_sample_count, CV_32SC1 );
+        *test_sample_idx = cvMat( 1, test_sample_count, CV_32SC1, &sample_idx[train_sample_count] );
+    }
+
+    mix = spl->mix;
+    if ( mix )
+        mix_train_and_test_idx();
+
+    __END__;
+}
+
+const CvMat* CvMLData::get_train_sample_idx() const
+{
+    CV_FUNCNAME( "CvMLData::get_train_sample_idx" );
+    __BEGIN__;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+    __END__;
+
+    return train_sample_idx;
+}
+
+const CvMat* CvMLData::get_test_sample_idx() const
+{
+    CV_FUNCNAME( "CvMLData::get_test_sample_idx" );
+    __BEGIN__;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+    __END__;
+
+    return test_sample_idx;
+}
+
+void CvMLData::mix_train_and_test_idx()
+{
+    CV_FUNCNAME( "CvMLData::mix_train_and_test_idx" );
+    __BEGIN__;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+    __END__;
+
+    if ( !sample_idx)
+        return;
+
+    if ( train_sample_count > 0 && train_sample_count < values->rows )
+    {
+        int n = values->rows;
+        for (int i = 0; i < n; i++)
+        {
+            int a = (*rng)(n);
+            int b = (*rng)(n);
+            int t;
+            CV_SWAP( sample_idx[a], sample_idx[b], t );
+        }
+    }
+}
+
+const CvMat* CvMLData::get_var_idx()
+{
+     CV_FUNCNAME( "CvMLData::get_var_idx" );
+    __BEGIN__;
+
+    int avcount = 0;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+
+    assert( var_idx_mask );
+
+    avcount = cvFloor( cvNorm( var_idx_mask, 0, CV_L1 ) );
+    int* vidx;
+
+    if ( avcount == values->cols )
+        return 0;
+
+    if ( !var_idx_out || ( var_idx_out && var_idx_out->cols != avcount ) )
+    {
+        cvReleaseMat( &var_idx_out );
+        var_idx_out = cvCreateMat( 1, avcount, CV_32SC1);
+        if ( response_idx >=0 )
+            var_idx_mask->data.ptr[response_idx] = 0;
+    }
+
+    vidx = var_idx_out->data.i;
+
+    for(int i = 0; i < var_idx_mask->cols; i++)
+        if ( var_idx_mask->data.ptr[i] )
+        {
+            *vidx = i;
+            vidx++;
+        }
+
+    __END__;
+
+    return var_idx_out;
+}
+
+void CvMLData::chahge_var_idx( int vi, bool state )
+{
+    change_var_idx( vi, state );
+}
+
+void CvMLData::change_var_idx( int vi, bool state )
+{
+     CV_FUNCNAME( "CvMLData::change_var_idx" );
+    __BEGIN__;
+
+    int var_count = 0;
+
+    if ( !values )
+        CV_ERROR( CV_StsInternal, "data is empty" );
+
+    var_count = values->cols;
+
+    if ( vi < 0 || vi >= var_count)
+        CV_ERROR( CV_StsBadArg, "variable index is not correct" );
+
+    assert( var_idx_mask );
+    var_idx_mask->data.ptr[vi] = state;
+
+    __END__;
+}
+
+/* End of file. */

apps/traincascade/old_ml_precomp.hpp

@@ -0,0 +1,376 @@
+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                        Intel License Agreement
+//
+// Copyright (C) 2000, Intel Corporation, all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of Intel Corporation may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Intel Corporation or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#ifndef __OPENCV_PRECOMP_H__
+#define __OPENCV_PRECOMP_H__
+
+#include "opencv2/core.hpp"
+#include "old_ml.hpp"
+#include "opencv2/core/core_c.h"
+#include "opencv2/core/utility.hpp"
+
+#include "opencv2/core/private.hpp"
+
+#include <assert.h>
+#include <float.h>
+#include <limits.h>
+#include <math.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <time.h>
+
+#define ML_IMPL CV_IMPL
+#define __BEGIN__ __CV_BEGIN__
+#define __END__ __CV_END__
+#define EXIT __CV_EXIT__
+
+#define CV_MAT_ELEM_FLAG( mat, type, comp, vect, tflag )    \
+    (( tflag == CV_ROW_SAMPLE )                             \
+    ? (CV_MAT_ELEM( mat, type, comp, vect ))                \
+    : (CV_MAT_ELEM( mat, type, vect, comp )))
+
+/* Convert matrix to vector */
+#define ICV_MAT2VEC( mat, vdata, vstep, num )      \
+    if( MIN( (mat).rows, (mat).cols ) != 1 )       \
+        CV_ERROR( CV_StsBadArg, "" );              \
+    (vdata) = ((mat).data.ptr);                    \
+    if( (mat).rows == 1 )                          \
+    {                                              \
+        (vstep) = CV_ELEM_SIZE( (mat).type );      \
+        (num) = (mat).cols;                        \
+    }                                              \
+    else                                           \
+    {                                              \
+        (vstep) = (mat).step;                      \
+        (num) = (mat).rows;                        \
+    }
+
+/* get raw data */
+#define ICV_RAWDATA( mat, flags, rdata, sstep, cstep, m, n )         \
+    (rdata) = (mat).data.ptr;                                        \
+    if( CV_IS_ROW_SAMPLE( flags ) )                                  \
+    {                                                                \
+        (sstep) = (mat).step;                                        \
+        (cstep) = CV_ELEM_SIZE( (mat).type );                        \
+        (m) = (mat).rows;                                            \
+        (n) = (mat).cols;                                            \
+    }                                                                \
+    else                                                             \
+    {                                                                \
+        (cstep) = (mat).step;                                        \
+        (sstep) = CV_ELEM_SIZE( (mat).type );                        \
+        (n) = (mat).rows;                                            \
+        (m) = (mat).cols;                                            \
+    }
+
+#define ICV_IS_MAT_OF_TYPE( mat, mat_type) \
+    (CV_IS_MAT( mat ) && CV_MAT_TYPE( mat->type ) == (mat_type) &&   \
+    (mat)->cols > 0 && (mat)->rows > 0)
+
+/*
+    uchar* data; int sstep, cstep;      - trainData->data
+    uchar* classes; int clstep; int ncl;- trainClasses
+    uchar* tmask; int tmstep; int ntm;  - typeMask
+    uchar* missed;int msstep, mcstep;   -missedMeasurements...
+    int mm, mn;                         == m,n == size,dim
+    uchar* sidx;int sistep;             - sampleIdx
+    uchar* cidx;int cistep;             - compIdx
+    int k, l;                           == n,m == dim,size (length of cidx, sidx)
+    int m, n;                           == size,dim
+*/
+#define ICV_DECLARE_TRAIN_ARGS()                                                    \
+    uchar* data;                                                                    \
+    int sstep, cstep;                                                               \
+    uchar* classes;                                                                 \
+    int clstep;                                                                     \
+    int ncl;                                                                        \
+    uchar* tmask;                                                                   \
+    int tmstep;                                                                     \
+    int ntm;                                                                        \
+    uchar* missed;                                                                  \
+    int msstep, mcstep;                                                             \
+    int mm, mn;                                                                     \
+    uchar* sidx;                                                                    \
+    int sistep;                                                                     \
+    uchar* cidx;                                                                    \
+    int cistep;                                                                     \
+    int k, l;                                                                       \
+    int m, n;                                                                       \
+                                                                                    \
+    data = classes = tmask = missed = sidx = cidx = NULL;                           \
+    sstep = cstep = clstep = ncl = tmstep = ntm = msstep = mcstep = mm = mn = 0;    \
+    sistep = cistep = k = l = m = n = 0;
+
+#define ICV_TRAIN_DATA_REQUIRED( param, flags )                                     \
+    if( !ICV_IS_MAT_OF_TYPE( (param), CV_32FC1 ) )                                  \
+    {                                                                               \
+        CV_ERROR( CV_StsBadArg, "Invalid " #param " parameter" );                   \
+    }                                                                               \
+    else                                                                            \
+    {                                                                               \
+        ICV_RAWDATA( *(param), (flags), data, sstep, cstep, m, n );                 \
+        k = n;                                                                      \
+        l = m;                                                                      \
+    }
+
+#define ICV_TRAIN_CLASSES_REQUIRED( param )                                         \
+    if( !ICV_IS_MAT_OF_TYPE( (param), CV_32FC1 ) )                                  \
+    {                                                                               \
+        CV_ERROR( CV_StsBadArg, "Invalid " #param " parameter" );                   \
+    }                                                                               \
+    else                                                                            \
+    {                                                                               \
+        ICV_MAT2VEC( *(param), classes, clstep, ncl );                              \
+        if( m != ncl )                                                              \
+        {                                                                           \
+            CV_ERROR( CV_StsBadArg, "Unmatched sizes" );                            \
+        }                                                                           \
+    }
+
+#define ICV_ARG_NULL( param )                                                       \
+    if( (param) != NULL )                                                           \
+    {                                                                               \
+        CV_ERROR( CV_StsBadArg, #param " parameter must be NULL" );                 \
+    }
+
+#define ICV_MISSED_MEASUREMENTS_OPTIONAL( param, flags )                            \
+    if( param )                                                                     \
+    {                                                                               \
+        if( !ICV_IS_MAT_OF_TYPE( param, CV_8UC1 ) )                                 \
+        {                                                                           \
+            CV_ERROR( CV_StsBadArg, "Invalid " #param " parameter" );               \
+        }                                                                           \
+        else                                                                        \
+        {                                                                           \
+            ICV_RAWDATA( *(param), (flags), missed, msstep, mcstep, mm, mn );       \
+            if( mm != m || mn != n )                                                \
+            {                                                                       \
+                CV_ERROR( CV_StsBadArg, "Unmatched sizes" );                        \
+            }                                                                       \
+        }                                                                           \
+    }
+
+#define ICV_COMP_IDX_OPTIONAL( param )                                              \
+    if( param )                                                                     \
+    {                                                                               \
+        if( !ICV_IS_MAT_OF_TYPE( param, CV_32SC1 ) )                                \
+        {                                                                           \
+            CV_ERROR( CV_StsBadArg, "Invalid " #param " parameter" );               \
+        }                                                                           \
+        else                                                                        \
+        {                                                                           \
+            ICV_MAT2VEC( *(param), cidx, cistep, k );                               \
+            if( k > n )                                                             \
+                CV_ERROR( CV_StsBadArg, "Invalid " #param " parameter" );           \
+        }                                                                           \
+    }
+
+#define ICV_SAMPLE_IDX_OPTIONAL( param )                                            \
+    if( param )                                                                     \
+    {                                                                               \
+        if( !ICV_IS_MAT_OF_TYPE( param, CV_32SC1 ) )                                \
+        {                                                                           \
+            CV_ERROR( CV_StsBadArg, "Invalid " #param " parameter" );               \
+        }                                                                           \
+        else                                                                        \
+        {                                                                           \
+            ICV_MAT2VEC( *sampleIdx, sidx, sistep, l );                             \
+            if( l > m )                                                             \
+                CV_ERROR( CV_StsBadArg, "Invalid " #param " parameter" );           \
+        }                                                                           \
+    }
+
+/****************************************************************************************/
+#define ICV_CONVERT_FLOAT_ARRAY_TO_MATRICE( array, matrice )        \
+{                                                                   \
+    CvMat a, b;                                                     \
+    int dims = (matrice)->cols;                                     \
+    int nsamples = (matrice)->rows;                                 \
+    int type = CV_MAT_TYPE((matrice)->type);                        \
+    int i, offset = dims;                                           \
+                                                                    \
+    CV_ASSERT( type == CV_32FC1 || type == CV_64FC1 );              \
+    offset *= ((type == CV_32FC1) ? sizeof(float) : sizeof(double));\
+                                                                    \
+    b = cvMat( 1, dims, CV_32FC1 );                                 \
+    cvGetRow( matrice, &a, 0 );                                     \
+    for( i = 0; i < nsamples; i++, a.data.ptr += offset )           \
+    {                                                               \
+        b.data.fl = (float*)array[i];                               \
+        CV_CALL( cvConvert( &b, &a ) );                             \
+    }                                                               \
+}
+
+/****************************************************************************************\
+*                       Auxiliary functions declarations                                 *
+\****************************************************************************************/
+
+/* Generates a set of classes centers in quantity <num_of_clusters> that are generated as
+   uniform random vectors in parallelepiped, where <data> is concentrated. Vectors in
+   <data> should have horizontal orientation. If <centers> != NULL, the function doesn't
+   allocate any memory and stores generated centers in <centers>, returns <centers>.
+   If <centers> == NULL, the function allocates memory and creates the matrice. Centers
+   are supposed to be oriented horizontally. */
+CvMat* icvGenerateRandomClusterCenters( int seed,
+                                        const CvMat* data,
+                                        int num_of_clusters,
+                                        CvMat* centers CV_DEFAULT(0));
+
+/* Fills the <labels> using <probs> by choosing the maximal probability. Outliers are
+   fixed by <oulier_tresh> and have cluster label (-1). Function also controls that there
+   weren't "empty" clusters by filling empty clusters with the maximal probability vector.
+   If probs_sums != NULL, filles it with the sums of probabilities for each sample (it is
+   useful for normalizing probabilities' matrice of FCM) */
+void icvFindClusterLabels( const CvMat* probs, float outlier_thresh, float r,
+                           const CvMat* labels );
+
+typedef struct CvSparseVecElem32f
+{
+    int idx;
+    float val;
+}
+CvSparseVecElem32f;
+
+/* Prepare training data and related parameters */
+#define CV_TRAIN_STATMODEL_DEFRAGMENT_TRAIN_DATA    1
+#define CV_TRAIN_STATMODEL_SAMPLES_AS_ROWS          2
+#define CV_TRAIN_STATMODEL_SAMPLES_AS_COLUMNS       4
+#define CV_TRAIN_STATMODEL_CATEGORICAL_RESPONSE     8
+#define CV_TRAIN_STATMODEL_ORDERED_RESPONSE         16
+#define CV_TRAIN_STATMODEL_RESPONSES_ON_OUTPUT      32
+#define CV_TRAIN_STATMODEL_ALWAYS_COPY_TRAIN_DATA   64
+#define CV_TRAIN_STATMODEL_SPARSE_AS_SPARSE         128
+
+int
+cvPrepareTrainData( const char* /*funcname*/,
+                    const CvMat* train_data, int tflag,
+                    const CvMat* responses, int response_type,
+                    const CvMat* var_idx,
+                    const CvMat* sample_idx,
+                    bool always_copy_data,
+                    const float*** out_train_samples,
+                    int* _sample_count,
+                    int* _var_count,
+                    int* _var_all,
+                    CvMat** out_responses,
+                    CvMat** out_response_map,
+                    CvMat** out_var_idx,
+                    CvMat** out_sample_idx=0 );
+
+void
+cvSortSamplesByClasses( const float** samples, const CvMat* classes,
+                        int* class_ranges, const uchar** mask CV_DEFAULT(0) );
+
+void
+cvCombineResponseMaps (CvMat*  _responses,
+                 const CvMat*  old_response_map,
+                       CvMat*  new_response_map,
+                       CvMat** out_response_map);
+
+void
+cvPreparePredictData( const CvArr* sample, int dims_all, const CvMat* comp_idx,
+                      int class_count, const CvMat* prob, float** row_sample,
+                      int as_sparse CV_DEFAULT(0) );
+
+/* copies clustering [or batch "predict"] results
+   (labels and/or centers and/or probs) back to the output arrays */
+void
+cvWritebackLabels( const CvMat* labels, CvMat* dst_labels,
+                   const CvMat* centers, CvMat* dst_centers,
+                   const CvMat* probs, CvMat* dst_probs,
+                   const CvMat* sample_idx, int samples_all,
+                   const CvMat* comp_idx, int dims_all );
+#define cvWritebackResponses cvWritebackLabels
+
+#define XML_FIELD_NAME "_name"
+CvFileNode* icvFileNodeGetChild(CvFileNode* father, const char* name);
+CvFileNode* icvFileNodeGetChildArrayElem(CvFileNode* father, const char* name,int index);
+CvFileNode* icvFileNodeGetNext(CvFileNode* n, const char* name);
+
+
+void cvCheckTrainData( const CvMat* train_data, int tflag,
+                       const CvMat* missing_mask,
+                       int* var_all, int* sample_all );
+
+CvMat* cvPreprocessIndexArray( const CvMat* idx_arr, int data_arr_size, bool check_for_duplicates=false );
+
+CvMat* cvPreprocessVarType( const CvMat* type_mask, const CvMat* var_idx,
+                            int var_all, int* response_type );
+
+CvMat* cvPreprocessOrderedResponses( const CvMat* responses,
+                const CvMat* sample_idx, int sample_all );
+
+CvMat* cvPreprocessCategoricalResponses( const CvMat* responses,
+                const CvMat* sample_idx, int sample_all,
+                CvMat** out_response_map, CvMat** class_counts=0 );
+
+const float** cvGetTrainSamples( const CvMat* train_data, int tflag,
+                   const CvMat* var_idx, const CvMat* sample_idx,
+                   int* _var_count, int* _sample_count,
+                   bool always_copy_data=false );
+
+namespace cv
+{
+    struct DTreeBestSplitFinder
+    {
+        DTreeBestSplitFinder(){ splitSize = 0, tree = 0; node = 0; }
+        DTreeBestSplitFinder( CvDTree* _tree, CvDTreeNode* _node);
+        DTreeBestSplitFinder( const DTreeBestSplitFinder& finder, Split );
+        virtual ~DTreeBestSplitFinder() {}
+        virtual void operator()(const BlockedRange& range);
+        void join( DTreeBestSplitFinder& rhs );
+        Ptr<CvDTreeSplit> bestSplit;
+        Ptr<CvDTreeSplit> split;
+        int splitSize;
+        CvDTree* tree;
+        CvDTreeNode* node;
+    };
+
+    struct ForestTreeBestSplitFinder : DTreeBestSplitFinder
+    {
+        ForestTreeBestSplitFinder() : DTreeBestSplitFinder() {}
+        ForestTreeBestSplitFinder( CvForestTree* _tree, CvDTreeNode* _node );
+        ForestTreeBestSplitFinder( const ForestTreeBestSplitFinder& finder, Split );
+        virtual void operator()(const BlockedRange& range);
+    };
+}
+
+#endif /* __ML_H__ */

apps/traincascade/traincascade.cpp

@@ -1,6 +1,4 @@
 #include "opencv2/core.hpp"
-
-#include "cv.h"
 #include "cascadeclassifier.h"
 
 using namespace std;

apps/traincascade/traincascade_features.h

@@ -2,9 +2,6 @@
 #define _OPENCV_FEATURES_H_
 
 #include "imagestorage.h"
-#include "cxcore.h"
-#include "cv.h"
-#include "ml.h"
 #include <stdio.h>
 
 #define FEATURES "features"

modules/ml/include/opencv2/ml.hpp

@@ -135,7 +135,7 @@ public:
     virtual Mat getCatMap() const = 0;
     
     virtual void setTrainTestSplit(int count, bool shuffle=true) = 0;
-    virtual void setTrainTestSplitRatio(float ratio, bool shuffle=true) = 0;
+    virtual void setTrainTestSplitRatio(double ratio, bool shuffle=true) = 0;
     virtual void shuffleTrainTest() = 0;
 
     static Mat getSubVector(const Mat& vec, const Mat& idx);
@@ -156,7 +156,6 @@ class CV_EXPORTS_W StatModel : public Algorithm
 {
 public:
     enum { UPDATE_MODEL = 1, RAW_OUTPUT=1, COMPRESSED_INPUT=2, PREPROCESSED_INPUT=4 };
-    virtual ~StatModel();
     virtual void clear();
 
     virtual int getVarCount() const = 0;
@@ -164,16 +163,30 @@ public:
     virtual bool isTrained() const = 0;
     virtual bool isClassifier() const = 0;
 
-    virtual bool train( const Ptr<TrainData>& trainData, int flags=0 ) = 0;
+    virtual bool train( const Ptr<TrainData>& trainData, int flags=0 );
+    virtual bool train( InputArray samples, int layout, InputArray responses );
     virtual float calcError( const Ptr<TrainData>& data, bool test, OutputArray resp ) const;
     virtual float predict( InputArray samples, OutputArray results=noArray(), int flags=0 ) const = 0;
 
     template<typename _Tp> static Ptr<_Tp> load(const String& filename)
     {
         FileStorage fs(filename, FileStorage::READ);
-        Ptr<_Tp> p = _Tp::create();
-        p->read(fs.getFirstTopLevelNode());
-        return p->isTrained() ? p : Ptr<_Tp>();
+        Ptr<_Tp> model = _Tp::create();
+        model->read(fs.getFirstTopLevelNode());
+        return model->isTrained() ? model : Ptr<_Tp>();
+    }
+
+    template<typename _Tp> static Ptr<_Tp> train(const Ptr<TrainData>& data, const typename _Tp::Params& p, int flags=0)
+    {
+        Ptr<_Tp> model = _Tp::create(p);
+        return !model.empty() && model->train(data, flags) ? model : Ptr<_Tp>();
+    }
+
+    template<typename _Tp> static Ptr<_Tp> train(InputArray samples, int layout, InputArray responses,
+                                                 const typename _Tp::Params& p, int flags=0)
+    {
+        Ptr<_Tp> model = _Tp::create(p);
+        return !model.empty() && model->train(TrainData::create(samples, layout, responses), flags) ? model : Ptr<_Tp>();
     }
 
     virtual void save(const String& filename) const;
@@ -192,11 +205,17 @@ public:
 class CV_EXPORTS_W NormalBayesClassifier : public StatModel
 {
 public:
-    virtual ~NormalBayesClassifier();
+    class CV_EXPORTS_W_MAP Params
+    {
+    public:
+        Params();
+    };
     virtual float predictProb( InputArray inputs, OutputArray outputs,
                                OutputArray outputProbs, int flags=0 ) const = 0;
+    virtual void setParams(const Params& params) = 0;
+    virtual Params getParams() const = 0;
 
-    static Ptr<NormalBayesClassifier> create();
+    static Ptr<NormalBayesClassifier> create(const Params& params=Params());
 };
 
 /****************************************************************************************\
@@ -207,13 +226,21 @@ public:
 class CV_EXPORTS_W KNearest : public StatModel
 {
 public:
-    virtual void setDefaultK(int k) = 0;
-    virtual int getDefaultK() const = 0;
+    class CV_EXPORTS_W_MAP Params
+    {
+    public:
+        Params(int defaultK=10, bool isclassifier=true);
+
+        int defaultK;
+        bool isclassifier;
+    };
+    virtual void setParams(const Params& p) = 0;
+    virtual Params getParams() const = 0;
     virtual float findNearest( InputArray samples, int k,
                                OutputArray results,
                                OutputArray neighborResponses=noArray(),
                                OutputArray dist=noArray() ) const = 0;
-    static Ptr<KNearest> create(bool isclassifier=true);
+    static Ptr<KNearest> create(const Params& params=Params());
 };
 
 /****************************************************************************************\
@@ -247,7 +274,6 @@ public:
     class CV_EXPORTS Kernel : public Algorithm
     {
     public:
-        virtual ~Kernel();
         virtual int getType() const = 0;
         virtual void calc( int vcount, int n, const float* vecs, const float* another, float* results ) = 0;
     };
@@ -261,8 +287,6 @@ public:
     // SVM params type
     enum { C=0, GAMMA=1, P=2, NU=3, COEF=4, DEGREE=5 };
 
-    virtual ~SVM();
-
     virtual bool trainAuto( const Ptr<TrainData>& data, int kFold = 10,
                     ParamGrid Cgrid = SVM::getDefaultGrid(SVM::C),
                     ParamGrid gammaGrid  = SVM::getDefaultGrid(SVM::GAMMA),
@@ -399,8 +423,6 @@ public:
         int subsetOfs;
     };
 
-    virtual ~DTrees();
-
     virtual void setDParams(const Params& p);
     virtual Params getDParams() const;
 
@@ -464,7 +486,6 @@ public:
     // Boosting type
     enum { DISCRETE=0, REAL=1, LOGIT=2, GENTLE=3 };
 
-    virtual ~Boost();
     virtual Params getBParams() const = 0;
     virtual void setBParams(const Params& p) = 0;
 
@@ -491,7 +512,6 @@ public:
     };
 
     enum {SQUARED_LOSS=0, ABSOLUTE_LOSS, HUBER_LOSS=3, DEVIANCE_LOSS};
-    virtual ~GBTrees();
 
     virtual void setK(int k) = 0;
 
@@ -513,10 +533,16 @@ public:
     struct CV_EXPORTS_W_MAP Params
     {
         Params();
-        Params( TermCriteria termCrit, int trainMethod, double param1, double param2=0 );
+        Params( const Mat& layerSizes, int activateFunc, double fparam1, double fparam2,
+                TermCriteria termCrit, int trainMethod, double param1, double param2=0 );
 
         enum { BACKPROP=0, RPROP=1 };
 
+        CV_PROP_RW Mat layerSizes;
+        CV_PROP_RW int activateFunc;
+        CV_PROP_RW double fparam1;
+        CV_PROP_RW double fparam2;
+
         CV_PROP_RW TermCriteria termCrit;
         CV_PROP_RW int trainMethod;
 
@@ -527,23 +553,17 @@ public:
         CV_PROP_RW double rpDW0, rpDWPlus, rpDWMinus, rpDWMin, rpDWMax;
     };
 
-    virtual ~ANN_MLP();
-
     // possible activation functions
     enum { IDENTITY = 0, SIGMOID_SYM = 1, GAUSSIAN = 2 };
 
     // available training flags
     enum { UPDATE_WEIGHTS = 1, NO_INPUT_SCALE = 2, NO_OUTPUT_SCALE = 4 };
 
-    virtual Mat getLayerSizes() const = 0;
     virtual Mat getWeights(int layerIdx) const = 0;
     virtual void setParams(const Params& p) = 0;
     virtual Params getParams() const = 0;
 
-    static Ptr<ANN_MLP> create(InputArray layerSizes=noArray(),
-                               const Params& params=Params(),
-                               int activateFunc=ANN_MLP::SIGMOID_SYM,
-                               double fparam1=0, double fparam2=0);
+    static Ptr<ANN_MLP> create(const Params& params=Params());
 };
 
 /****************************************************************************************\

modules/ml/src/ann_mlp.cpp

@@ -42,10 +42,11 @@
 
 namespace cv { namespace ml {
 
-ANN_MLP::~ANN_MLP() {}
-
 ANN_MLP::Params::Params()
 {
+    layerSizes = Mat();
+    activateFunc = SIGMOID_SYM;
+    fparam1 = fparam2 = 0;
     termCrit = TermCriteria( TermCriteria::COUNT + TermCriteria::EPS, 1000, 0.01 );
     trainMethod = RPROP;
     bpDWScale = bpMomentScale = 0.1;
@@ -54,8 +55,13 @@ ANN_MLP::Params::Params()
 }
 
 
-ANN_MLP::Params::Params( TermCriteria _termCrit, int _trainMethod, double _param1, double _param2 )
+ANN_MLP::Params::Params( const Mat& _layerSizes, int _activateFunc, double _fparam1, double _fparam2,
+                         TermCriteria _termCrit, int _trainMethod, double _param1, double _param2 )
 {
+    layerSizes = _layerSizes;
+    activateFunc = _activateFunc;
+    fparam1 = _fparam1;
+    fparam2 = _fparam2;
     termCrit = _termCrit;
     trainMethod = _trainMethod;
     bpDWScale = bpMomentScale = 0.1;
@@ -95,15 +101,25 @@ public:
         clear();
     }
 
-    ANN_MLPImpl( const Mat& _layer_sizes, int _activ_func,
-                 double _f_param1, double _f_param2 )
+    ANN_MLPImpl( const Params& p )
     {
-        clear();
-        create( _layer_sizes, _activ_func, _f_param1, _f_param2 );
+        setParams(p);
     }
 
     virtual ~ANN_MLPImpl() {}
 
+    void setParams(const Params& p)
+    {
+        params = p;
+        create( params.layerSizes );
+        set_activ_func( params.activateFunc, params.fparam1, params.fparam2 );
+    }
+
+    Params getParams() const
+    {
+        return params;
+    }
+
     void clear()
     {
         min_val = max_val = min_val1 = max_val1 = 0.;
@@ -183,16 +199,13 @@ public:
         }
     }
 
-    void create( InputArray _layer_sizes, int _activ_func,
-                 double _f_param1, double _f_param2 )
+    void create( InputArray _layer_sizes )
     {
         clear();
 
         _layer_sizes.copyTo(layer_sizes);
         int l_count = layer_count();
 
-        set_activ_func( _activ_func, _f_param1, _f_param2 );
-
         weights.resize(l_count + 2);
         max_lsize = 0;
 
@@ -665,16 +678,6 @@ public:
         calc_output_scale( outputs, flags );
     }
 
-    void setParams( const Params& _params )
-    {
-        params = _params;
-    }
-
-    Params getParams() const
-    {
-        return params;
-    }
-
     bool train( const Ptr<TrainData>& trainData, int flags )
     {
         const int MAX_ITER = 1000;
@@ -1240,7 +1243,7 @@ public:
 
         vector<int> _layer_sizes;
         fn["layer_sizes"] >> _layer_sizes;
-        create( _layer_sizes, SIGMOID_SYM, 0, 0 );
+        create( _layer_sizes );
 
         int i, l_count = layer_count();
         read_params(fn);
@@ -1307,15 +1310,9 @@ public:
 };
 
 
-Ptr<ANN_MLP> ANN_MLP::create(InputArray _layerSizes,
-                             const ANN_MLP::Params& params,
-                             int activateFunc,
-                             double fparam1, double fparam2)
+Ptr<ANN_MLP> ANN_MLP::create(const ANN_MLP::Params& params)
 {
-    Mat layerSizes = _layerSizes.getMat();
-    Ptr<ANN_MLPImpl> ann = makePtr<ANN_MLPImpl>(layerSizes, activateFunc, fparam1, fparam2);
-    ann->setParams(params);
-
+    Ptr<ANN_MLPImpl> ann = makePtr<ANN_MLPImpl>(params);
     return ann;
 }
 

modules/ml/src/boost.cpp

@@ -54,8 +54,6 @@ log_ratio( double val )
 }
 
 
-Boost::~Boost() {}
-
 Boost::Params::Params()
 {
     boostType = Boost::REAL;
@@ -106,6 +104,7 @@ public:
     void startTraining( const Ptr<TrainData>& trainData, int flags )
     {
         DTreesImpl::startTraining(trainData, flags);
+        sumResult.assign(w->sidx.size(), 0.);
 
         if( bparams.boostType != Boost::DISCRETE )
         {
@@ -114,14 +113,10 @@ public:
             w->ord_responses.resize(n);
 
             double a = -1, b = 1;
-            if( bparams.boostType == Boost::REAL )
-                a = 0;
-            else if( bparams.boostType == Boost::LOGIT )
+            if( bparams.boostType == Boost::LOGIT )
             {
-                sumResult.assign(w->sidx.size(), 0.);
                 a = -2, b = 2;
             }
-
             for( i = 0; i < n; i++ )
                 w->ord_responses[i] = w->cat_responses[i] > 0 ? b : a;
         }
@@ -197,7 +192,7 @@ public:
         }
         else if( bparams.boostType == Boost::REAL )
         {
-            double p = node->value;
+            double p = (node->value+1)*0.5;
             node->value = 0.5*log_ratio(p);
         }
     }
@@ -227,7 +222,7 @@ public:
     {
         int i, n = (int)w->sidx.size();
         int nvars = (int)varIdx.size();
-        double sumw = 0.;
+        double sumw = 0., C = 1.;
         cv::AutoBuffer<double> buf(n*3 + nvars);
         double* result = buf;
         float* sbuf = (float*)(result + n*3);
@@ -261,7 +256,7 @@ public:
 
             if( sumw != 0 )
                 err /= sumw;
-            double C = -log_ratio( err );
+            C = -log_ratio( err );
             double scale = std::exp(C);
 
             sumw = 0;
@@ -289,6 +284,7 @@ public:
             for( i = 0; i < n; i++ )
             {
                 int si = w->sidx[i];
+                CV_Assert( std::abs(w->ord_responses[si]) == 1 );
                 double wval = w->sample_weights[si]*std::exp(-result[i]*w->ord_responses[si]);
                 sumw += wval;
                 w->sample_weights[si] = wval;
@@ -330,6 +326,20 @@ public:
         }
         else
             CV_Error(CV_StsNotImplemented, "Unknown boosting type");
+
+        /*if( bparams.boostType != Boost::LOGIT )
+        {
+            double err = 0;
+            for( i = 0; i < n; i++ )
+            {
+                sumResult[i] += result[i]*C;
+                if( bparams.boostType != Boost::DISCRETE )
+                    err += sumResult[i]*w->ord_responses[w->sidx[i]] < 0;
+                else
+                    err += sumResult[i]*w->cat_responses[w->sidx[i]] < 0;
+            }
+            printf("%d trees. C=%.2f, training error=%.1f%%, working set size=%d (out of %d)\n", (int)roots.size(), C, err*100./n, (int)sidx.size(), n);
+        }*/
         
         // renormalize weights
         if( sumw > FLT_EPSILON )

modules/ml/src/data.cpp

@@ -379,7 +379,7 @@ public:
                 tempCatOfs.push_back(ofs);
                 std::copy(labels.begin(), labels.end(), std::back_inserter(tempCatMap));
             }
-            else if( haveMissing )
+            else
             {
                 tempCatOfs.push_back(Vec2i(0, 0));
                 /*Mat missing_i = layout == ROW_SAMPLE ? missing.col(i) : missing.row(i);
@@ -741,9 +741,9 @@ public:
             CV_Error( CV_StsBadArg, "type of some variables is not specified" );
     }
 
-    void setTrainTestSplitRatio(float ratio, bool shuffle)
+    void setTrainTestSplitRatio(double ratio, bool shuffle)
     {
-        CV_Assert( 0 <= ratio && ratio <= 1 );
+        CV_Assert( 0. <= ratio && ratio <= 1. );
         setTrainTestSplit(cvRound(getNSamples()*ratio), shuffle);
     }
 

modules/ml/src/inner_functions.cpp

@@ -50,7 +50,6 @@ ParamGrid::ParamGrid(double _minVal, double _maxVal, double _logStep)
     logStep = std::max(_logStep, 1.);
 }
 
-StatModel::~StatModel() {}
 void StatModel::clear() {}
 
 int StatModel::getVarCount() const { return 0; }
@@ -61,6 +60,11 @@ bool StatModel::train( const Ptr<TrainData>&, int )
     return false;
 }
 
+bool StatModel::train( InputArray samples, int layout, InputArray responses )
+{
+    return train(TrainData::create(samples, layout, responses));
+}
+
 float StatModel::calcError( const Ptr<TrainData>& data, bool testerr, OutputArray _resp ) const
 {
     Mat samples = data->getSamples();

modules/ml/src/knearest.cpp

@@ -49,18 +49,27 @@
 namespace cv {
 namespace ml {
 
+KNearest::Params::Params(int k, bool isclassifier_)
+{
+    defaultK = k;
+    isclassifier = isclassifier_;
+}
+
+
 class KNearestImpl : public KNearest
 {
 public:
-    KNearestImpl(bool __isClassifier=true)
+    KNearestImpl(const Params& p)
     {
-        defaultK = 3;
-        _isClassifier = __isClassifier;
+        params = p;
     }
 
     virtual ~KNearestImpl() {}
 
-    bool isClassifier() const { return _isClassifier; }
+    Params getParams() const { return params; }
+    void setParams(const Params& p) { params = p; }
+
+    bool isClassifier() const { return params.isclassifier; }
     bool isTrained() const { return !samples.empty(); }
 
     String getDefaultModelName() const { return "opencv_ml_knn"; }
@@ -188,7 +197,7 @@ public:
 
             if( results || testidx+range.start == 0 )
             {
-                if( !_isClassifier || k == 1 )
+                if( !params.isclassifier || k == 1 )
                 {
                     float s = 0.f;
                     for( j = 0; j < k; j++ )
@@ -316,12 +325,13 @@ public:
 
     float predict(InputArray inputs, OutputArray outputs, int) const
     {
-        return findNearest( inputs, defaultK, outputs, noArray(), noArray() );
+        return findNearest( inputs, params.defaultK, outputs, noArray(), noArray() );
     }
 
     void write( FileStorage& fs ) const
     {
-        fs << "is_classifier" << (int)_isClassifier;
+        fs << "is_classifier" << (int)params.isclassifier;
+        fs << "default_k" << params.defaultK;
 
         fs << "samples" << samples;
         fs << "responses" << responses;
@@ -330,24 +340,21 @@ public:
     void read( const FileNode& fn )
     {
         clear();
-        _isClassifier = (int)fn["is_classifier"] != 0;
+        params.isclassifier = (int)fn["is_classifier"] != 0;
+        params.defaultK = (int)fn["default_k"];
 
         fn["samples"] >> samples;
         fn["responses"] >> responses;
     }
 
-    void setDefaultK(int _k) { defaultK = _k; }
-    int getDefaultK() const { return defaultK; }
-
     Mat samples;
     Mat responses;
-    bool _isClassifier;
-    int defaultK;
+    Params params;
 };
 
-Ptr<KNearest> KNearest::create(bool isClassifier)
+Ptr<KNearest> KNearest::create(const Params& p)
 {
-    return makePtr<KNearestImpl>(isClassifier);
+    return makePtr<KNearestImpl>(p);
 }
 
 }

modules/ml/src/nbayes.cpp

@@ -43,7 +43,7 @@
 namespace cv {
 namespace ml {
 
-NormalBayesClassifier::~NormalBayesClassifier() {}
+NormalBayesClassifier::Params::Params() {}
 
 class NormalBayesClassifierImpl : public NormalBayesClassifier
 {
@@ -53,6 +53,9 @@ public:
         nallvars = 0;
     }
 
+    void setParams(const Params&) {}
+    Params getParams() const { return Params(); }
+
     bool train( const Ptr<TrainData>& trainData, int flags )
     {
         const float min_variation = FLT_EPSILON;
@@ -452,7 +455,7 @@ public:
 };
 
 
-Ptr<NormalBayesClassifier> NormalBayesClassifier::create()
+Ptr<NormalBayesClassifier> NormalBayesClassifier::create(const Params&)
 {
     Ptr<NormalBayesClassifierImpl> p = makePtr<NormalBayesClassifierImpl>();
     return p;

modules/ml/src/svm.cpp

@@ -134,8 +134,6 @@ SVM::Params::Params( int _svmType, int _kernelType,
     termCrit = _termCrit;
 }
 
-SVM::Kernel::~Kernel() {}
-
 /////////////////////////////////////// SVM kernel ///////////////////////////////////////
 class SVMKernelImpl : public SVM::Kernel
 {
@@ -358,7 +356,51 @@ static void sortSamplesByClasses( const Mat& _samples, const Mat& _responses,
     
 //////////////////////// SVM implementation //////////////////////////////
 
-SVM::~SVM() {}
+ParamGrid SVM::getDefaultGrid( int param_id )
+{
+    ParamGrid grid;
+    if( param_id == SVM::C )
+    {
+        grid.minVal = 0.1;
+        grid.maxVal = 500;
+        grid.logStep = 5; // total iterations = 5
+    }
+    else if( param_id == SVM::GAMMA )
+    {
+        grid.minVal = 1e-5;
+        grid.maxVal = 0.6;
+        grid.logStep = 15; // total iterations = 4
+    }
+    else if( param_id == SVM::P )
+    {
+        grid.minVal = 0.01;
+        grid.maxVal = 100;
+        grid.logStep = 7; // total iterations = 4
+    }
+    else if( param_id == SVM::NU )
+    {
+        grid.minVal = 0.01;
+        grid.maxVal = 0.2;
+        grid.logStep = 3; // total iterations = 3
+    }
+    else if( param_id == SVM::COEF )
+    {
+        grid.minVal = 0.1;
+        grid.maxVal = 300;
+        grid.logStep = 14; // total iterations = 3
+    }
+    else if( param_id == SVM::DEGREE )
+    {
+        grid.minVal = 0.01;
+        grid.maxVal = 4;
+        grid.logStep = 7; // total iterations = 3
+    }
+    else
+        cvError( CV_StsBadArg, "SVM::getDefaultGrid", "Invalid type of parameter "
+                "(use one of SVM::C, SVM::GAMMA et al.)", __FILE__, __LINE__ );
+    return grid;
+}
+
 
 class SVMImpl : public SVM
 {
@@ -371,52 +413,6 @@ public:
         int ofs;
     };
 
-    virtual ParamGrid getDefaultGrid( int param_id ) const
-    {
-        ParamGrid grid;
-        if( param_id == SVM::C )
-        {
-            grid.minVal = 0.1;
-            grid.maxVal = 500;
-            grid.logStep = 5; // total iterations = 5
-        }
-        else if( param_id == SVM::GAMMA )
-        {
-            grid.minVal = 1e-5;
-            grid.maxVal = 0.6;
-            grid.logStep = 15; // total iterations = 4
-        }
-        else if( param_id == SVM::P )
-        {
-            grid.minVal = 0.01;
-            grid.maxVal = 100;
-            grid.logStep = 7; // total iterations = 4
-        }
-        else if( param_id == SVM::NU )
-        {
-            grid.minVal = 0.01;
-            grid.maxVal = 0.2;
-            grid.logStep = 3; // total iterations = 3
-        }
-        else if( param_id == SVM::COEF )
-        {
-            grid.minVal = 0.1;
-            grid.maxVal = 300;
-            grid.logStep = 14; // total iterations = 3
-        }
-        else if( param_id == SVM::DEGREE )
-        {
-            grid.minVal = 0.01;
-            grid.maxVal = 4;
-            grid.logStep = 7; // total iterations = 3
-        }
-        else
-            cvError( CV_StsBadArg, "SVM::getDefaultGrid", "Invalid type of parameter "
-                     "(use one of SVM::C, SVM::GAMMA et al.)", __FILE__, __LINE__ );
-        return grid;
-    }
-
-
     // Generalized SMO+SVMlight algorithm
     // Solves:
     //
@@ -1568,6 +1564,9 @@ public:
         if( svmType == C_SVC || svmType == NU_SVC )
         {
             responses = data->getTrainNormCatResponses();
+            if( responses.empty() )
+                CV_Error(CV_StsBadArg, "in the case of classification problem the responses must be categorical; "
+                                       "either specify varType when creating TrainData, or pass integer responses");
             class_labels = data->getClassLabels();
         }
         else
@@ -1793,7 +1792,7 @@ public:
         {
             int svmType = svm->params.svmType;
             int sv_total = svm->sv.rows;
-            int class_count = !svm->class_labels.empty() ? svm->class_labels.cols : svmType == ONE_CLASS ? 1 : 0;
+            int class_count = !svm->class_labels.empty() ? (int)svm->class_labels.total() : svmType == ONE_CLASS ? 1 : 0;
 
             AutoBuffer<float> _buffer(sv_total + (class_count+1)*2);
             float* buffer = _buffer;

modules/ml/src/tree.cpp

@@ -48,8 +48,6 @@ namespace ml {
 
 using std::vector;
 
-DTrees::~DTrees() {}
-
 void DTrees::setDParams(const DTrees::Params&)
 {
     CV_Error(CV_StsNotImplemented, "");

modules/ml/test/test_emknearestkmeans.cpp

@@ -313,7 +313,7 @@ void CV_KNearestTest::run( int /*start_from*/ )
 
     int code = cvtest::TS::OK;
     Ptr<KNearest> knearest = KNearest::create(true);
-    knearest->train(TrainData::create(trainData, cv::ml::ROW_SAMPLE, trainLabels), 0);;
+    knearest->train(trainData, cv::ml::ROW_SAMPLE, trainLabels);
     knearest->findNearest( testData, 4, bestLabels);
     float err;
     if( !calcErr( bestLabels, testLabels, sizes, err, true ) )

modules/ml/test/test_mltests2.cpp

@@ -371,8 +371,9 @@ int CV_MLBaseTest::train( int testCaseIdx )
                                  data->getVarIdx(), data->getTrainSampleIdx());
         int layer_sz[] = { data->getNAllVars(), 100, 100, (int)cls_map.size() };
         Mat layer_sizes( 1, (int)(sizeof(layer_sz)/sizeof(layer_sz[0])), CV_32S, layer_sz );
-        model = ANN_MLP::create(layer_sizes, ANN_MLP::Params(TermCriteria(TermCriteria::COUNT,300,0.01),
-                                                        str_to_ann_train_method(train_method_str), param1, param2));
+        model = ANN_MLP::create(ANN_MLP::Params(layer_sizes, ANN_MLP::SIGMOID_SYM, 0, 0,
+                                                TermCriteria(TermCriteria::COUNT,300,0.01),
+                                                str_to_ann_train_method(train_method_str), param1, param2));
     }
     else if( modelName == CV_DTREE )
     {

samples/cpp/bagofwords_classification.cpp

@@ -2326,14 +2326,14 @@ static void removeBowImageDescriptorsByCount( vector<ObdImage>& images, vector<M
     CV_Assert( bowImageDescriptors.size() == objectPresent.size() );
 }
 
-static void setSVMParams( const SVM::Params& svmParams, Mat& class_wts_cv, const Mat& responses, bool balanceClasses )
+static void setSVMParams( SVM::Params& svmParams, Mat& class_wts_cv, const Mat& responses, bool balanceClasses )
 {
     int pos_ex = countNonZero(responses == 1);
     int neg_ex = countNonZero(responses == -1);
     cout << pos_ex << " positive training samples; " << neg_ex << " negative training samples" << endl;
 
-    svmParams.svm_type = CvSVM::C_SVC;
-    svmParams.kernel_type = CvSVM::RBF;
+    svmParams.svmType = SVM::C_SVC;
+    svmParams.kernelType = SVM::RBF;
     if( balanceClasses )
     {
         Mat class_wts( 2, 1, CV_32FC1 );
@@ -2351,43 +2351,44 @@ static void setSVMParams( const SVM::Params& svmParams, Mat& class_wts_cv, const
             class_wts.at<float>(1) = static_cast<float>(pos_ex)/static_cast<float>(pos_ex+neg_ex);
         }
         class_wts_cv = class_wts;
-        svmParams.class_weights = &class_wts_cv;
+        svmParams.classWeights = class_wts_cv;
     }
 }
 
-static void setSVMTrainAutoParams( CvParamGrid& c_grid, CvParamGrid& gamma_grid,
-                            CvParamGrid& p_grid, CvParamGrid& nu_grid,
-                            CvParamGrid& coef_grid, CvParamGrid& degree_grid )
+static void setSVMTrainAutoParams( ParamGrid& c_grid, ParamGrid& gamma_grid,
+                            ParamGrid& p_grid, ParamGrid& nu_grid,
+                            ParamGrid& coef_grid, ParamGrid& degree_grid )
 {
-    c_grid = CvSVM::get_default_grid(CvSVM::C);
+    c_grid = SVM::getDefaultGrid(SVM::C);
 
-    gamma_grid = CvSVM::get_default_grid(CvSVM::GAMMA);
+    gamma_grid = SVM::getDefaultGrid(SVM::GAMMA);
 
-    p_grid = CvSVM::get_default_grid(CvSVM::P);
-    p_grid.step = 0;
+    p_grid = SVM::getDefaultGrid(SVM::P);
+    p_grid.logStep = 0;
 
-    nu_grid = CvSVM::get_default_grid(CvSVM::NU);
-    nu_grid.step = 0;
+    nu_grid = SVM::getDefaultGrid(SVM::NU);
+    nu_grid.logStep = 0;
 
-    coef_grid = CvSVM::get_default_grid(CvSVM::COEF);
-    coef_grid.step = 0;
+    coef_grid = SVM::getDefaultGrid(SVM::COEF);
+    coef_grid.logStep = 0;
 
-    degree_grid = CvSVM::get_default_grid(CvSVM::DEGREE);
-    degree_grid.step = 0;
+    degree_grid = SVM::getDefaultGrid(SVM::DEGREE);
+    degree_grid.logStep = 0;
 }
 
-static void trainSVMClassifier( CvSVM& svm, const SVMTrainParamsExt& svmParamsExt, const string& objClassName, VocData& vocData,
+static Ptr<SVM> trainSVMClassifier( const SVMTrainParamsExt& svmParamsExt, const string& objClassName, VocData& vocData,
                          Ptr<BOWImgDescriptorExtractor>& bowExtractor, const Ptr<FeatureDetector>& fdetector,
                          const string& resPath )
 {
     /* first check if a previously trained svm for the current class has been saved to file */
     string svmFilename = resPath + svmsDir + "/" + objClassName + ".xml.gz";
+    Ptr<SVM> svm;
 
     FileStorage fs( svmFilename, FileStorage::READ);
     if( fs.isOpened() )
     {
         cout << "*** LOADING SVM CLASSIFIER FOR CLASS " << objClassName << " ***" << endl;
-        svm.load( svmFilename.c_str() );
+        svm = StatModel::load<SVM>( svmFilename );
     }
     else
     {
@@ -2438,20 +2439,24 @@ static void trainSVMClassifier( CvSVM& svm, const SVMTrainParamsExt& svmParamsEx
         }
 
         cout << "TRAINING SVM FOR CLASS ..." << objClassName << "..." << endl;
-        CvSVMParams svmParams;
-        CvMat class_wts_cv;
+        SVM::Params svmParams;
+        Mat class_wts_cv;
         setSVMParams( svmParams, class_wts_cv, responses, svmParamsExt.balanceClasses );
-        CvParamGrid c_grid, gamma_grid, p_grid, nu_grid, coef_grid, degree_grid;
+        svm = SVM::create(svmParams);
+        ParamGrid c_grid, gamma_grid, p_grid, nu_grid, coef_grid, degree_grid;
         setSVMTrainAutoParams( c_grid, gamma_grid,  p_grid, nu_grid, coef_grid, degree_grid );
-        svm.train_auto( trainData, responses, Mat(), Mat(), svmParams, 10, c_grid, gamma_grid, p_grid, nu_grid, coef_grid, degree_grid );
+
+        svm->trainAuto(TrainData::create(trainData, ROW_SAMPLE, responses), 10,
+                       c_grid, gamma_grid, p_grid, nu_grid, coef_grid, degree_grid);
         cout << "SVM TRAINING FOR CLASS " << objClassName << " COMPLETED" << endl;
 
-        svm.save( svmFilename.c_str() );
+        svm->save( svmFilename );
         cout << "SAVED CLASSIFIER TO FILE" << endl;
     }
+    return svm;
 }
 
-static void computeConfidences( CvSVM& svm, const string& objClassName, VocData& vocData,
+static void computeConfidences( const Ptr<SVM>& svm, const string& objClassName, VocData& vocData,
                          Ptr<BOWImgDescriptorExtractor>& bowExtractor, const Ptr<FeatureDetector>& fdetector,
                          const string& resPath )
 {
@@ -2477,12 +2482,12 @@ static void computeConfidences( CvSVM& svm, const string& objClassName, VocData&
         if( imageIdx == 0 )
         {
             // In the first iteration, determine the sign of the positive class
-            float classVal = confidences[imageIdx] = svm.predict( bowImageDescriptors[imageIdx], false );
-            float scoreVal = confidences[imageIdx] = svm.predict( bowImageDescriptors[imageIdx], true );
+            float classVal = confidences[imageIdx] = svm->predict( bowImageDescriptors[imageIdx], noArray(), 0 );
+            float scoreVal = confidences[imageIdx] = svm->predict( bowImageDescriptors[imageIdx], noArray(), StatModel::RAW_OUTPUT );
             signMul = (classVal < 0) == (scoreVal < 0) ? 1.f : -1.f;
         }
         // svm output of decision function
-        confidences[imageIdx] = signMul * svm.predict( bowImageDescriptors[imageIdx], true );
+        confidences[imageIdx] = signMul * svm->predict( bowImageDescriptors[imageIdx], noArray(), StatModel::RAW_OUTPUT );
     }
 
     cout << "WRITING QUERY RESULTS TO VOC RESULTS FILE FOR CLASS " << objClassName << "..." << endl;
@@ -2592,9 +2597,8 @@ int main(int argc, char** argv)
     for( size_t classIdx = 0; classIdx < objClasses.size(); ++classIdx )
     {
         // Train a classifier on train dataset
-        CvSVM svm;
-        trainSVMClassifier( svm, svmTrainParamsExt, objClasses[classIdx], vocData,
-                            bowExtractor, featureDetector, resPath );
+        Ptr<SVM> svm = trainSVMClassifier( svmTrainParamsExt, objClasses[classIdx], vocData,
+                                           bowExtractor, featureDetector, resPath );
 
         // Now use the classifier over all images on the test dataset and rank according to score order
         // also calculating precision-recall etc.

samples/cpp/letter_recog.cpp

@@ -179,10 +179,7 @@ build_rtrees_classifier( const string& data_filename,
         // create classifier by using <data> and <responses>
         cout << "Training the classifier ...\n";
         Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples);
-
-        // 3. train classifier
-        model = RTrees::create(RTrees::Params(10,10,0,false,15,Mat(),true,4,TC(100,0.01f)));
-        model->train( tdata );
+        model = StatModel::train<RTrees>(tdata, RTrees::Params(10,10,0,false,15,Mat(),true,4,TC(100,0.01f)));
         cout << endl;
     }
 
@@ -267,10 +264,12 @@ build_boost_classifier( const string& data_filename,
 
         Ptr<TrainData> tdata = TrainData::create(new_data, ROW_SAMPLE, new_responses,
                                                  noArray(), noArray(), noArray(), var_type);
-        model = Boost::create(Boost::Params(Boost::REAL, 100, 0.95, 5, false, Mat() ));
+        vector<double> priors(2);
+        priors[0] = 1;
+        priors[1] = 26;
 
         cout << "Training the classifier (may take a few minutes)...\n";
-        model->train(tdata);
+        model = StatModel::train<Boost>(tdata, Boost::Params(Boost::GENTLE, 100, 0.95, 5, false, Mat(priors) ));
         cout << endl;
     }
 
@@ -333,7 +332,6 @@ build_mlp_classifier( const string& data_filename,
     if( !ok )
         return ok;
 
-    int i, j;
     Ptr<ANN_MLP> model;
 
     int nsamples_all = data.rows;
@@ -360,14 +358,14 @@ build_mlp_classifier( const string& data_filename,
         // !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
 
         Mat train_data = data.rowRange(0, ntrain_samples);
-        Mat new_responses = Mat::zeros( ntrain_samples, class_count, CV_32F );
+        Mat train_responses = Mat::zeros( ntrain_samples, class_count, CV_32F );
 
         // 1. unroll the responses
         cout << "Unrolling the responses...\n";
-        for( i = 0; i < ntrain_samples; i++ )
+        for( int i = 0; i < ntrain_samples; i++ )
         {
-            int cls_label = responses.at<int>(i) - 'A'
-            new_responses.at<float>(i, cls_label) = 1.f;
+            int cls_label = responses.at<int>(i) - 'A';
+            train_responses.at<float>(i, cls_label) = 1.f;
         }
 
         // 2. train classifier
@@ -385,180 +383,63 @@ build_mlp_classifier( const string& data_filename,
         int max_iter = 1000;
 #endif
 
-        mlp.train( &train_data, new_responses, 0, 0,
-                  ANN_MLP::Params(TC(max_iter,0), method, method_param));
+        Ptr<TrainData> tdata = TrainData::create(train_data, ROW_SAMPLE, train_responses);
 
-
-        model = ANN_MLP::create() mlp.create( &layer_sizes );
-        printf( "Training the classifier (may take a few minutes)...\n");
-
-        cvReleaseMat( &new_responses );
-        printf("\n");
+        cout << "Training the classifier (may take a few minutes)...\n";
+        model = StatModel::train<ANN_MLP>(tdata, ANN_MLP::Params(layer_sizes, ANN_MLP::SIGMOID_SYM, 0, 0, TC(max_iter,0), method, method_param));
+        cout << endl;
     }
 
-    Mat mlp_response;
-
-    // compute prediction error on train and test data
-    for( i = 0; i < nsamples_all; i++ )
-    {
-        int best_class;
-        CvMat sample;
-        cvGetRow( data, &sample, i );
-        CvPoint max_loc;
-        mlp.predict( &sample, mlp_response );
-        cvMinMaxLoc( mlp_response, 0, 0, 0, &max_loc, 0 );
-        best_class = max_loc.x + 'A';
-
-        int r = fabs((double)best_class - responses->data.fl[i]) < FLT_EPSILON ? 1 : 0;
-
-        if( i < ntrain_samples )
-            train_hr += r;
-        else
-            test_hr += r;
-    }
-
-    test_hr /= (double)(nsamples_all-ntrain_samples);
-    train_hr /= (double)ntrain_samples;
-    printf( "Recognition rate: train = %.1f%%, test = %.1f%%\n",
-            train_hr*100., test_hr*100. );
-
-    if( !filename_to_save.empty() )
-        model->save( filename_to_save );
-
+    test_and_save_classifier(model, data, responses, ntrain_samples, 'A', filename_to_save);
     return true;
 }
 
 static bool
 build_knearest_classifier( const string& data_filename, int K )
 {
-    const int var_count = 16;
     Mat data;
-    CvMat train_data;
     Mat responses;
-
     bool ok = read_num_class_data( data_filename, 16, &data, &responses );
     if( !ok )
         return ok;
 
-    int nsamples_all = 0, ntrain_samples = 0;
+    Ptr<KNearest> model;
 
-    nsamples_all = data->rows;
-    ntrain_samples = (int)(nsamples_all*0.8);
+    int nsamples_all = data.rows;
+    int ntrain_samples = (int)(nsamples_all*0.8);
 
-    // 1. unroll the responses
-    printf( "Unrolling the responses...\n");
-    cvGetRows( data, &train_data, 0, ntrain_samples );
+    // create classifier by using <data> and <responses>
+    cout << "Training the classifier ...\n";
+    Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples);
+    model = StatModel::train<KNearest>(tdata, KNearest::Params(K, true));
+    cout << endl;
 
-    // 2. train classifier
-    Mat train_resp = cvCreateMat( ntrain_samples, 1, CV_32FC1);
-    for (int i = 0; i < ntrain_samples; i++)
-        train_resp->data.fl[i] = responses->data.fl[i];
-    Ptr<KNearest> model = KNearest::create(true);
-    model->train(train_data, train_resp);
-
-    Mat nearests = cvCreateMat( (nsamples_all - ntrain_samples), K, CV_32FC1);
-    float* _sample = new float[var_count * (nsamples_all - ntrain_samples)];
-    CvMat sample = cvMat( nsamples_all - ntrain_samples, 16, CV_32FC1, _sample );
-    float* true_results = new float[nsamples_all - ntrain_samples];
-    for (int j = ntrain_samples; j < nsamples_all; j++)
-    {
-        float *s = data->data.fl + j * var_count;
-
-        for (int i = 0; i < var_count; i++)
-        {
-            sample.data.fl[(j - ntrain_samples) * var_count + i] = s[i];
-        }
-        true_results[j - ntrain_samples] = responses->data.fl[j];
-    }
-    CvMat *result = cvCreateMat(1, nsamples_all - ntrain_samples, CV_32FC1);
-    knearest.find_nearest(&sample, K, result, 0, nearests, 0);
-    int true_resp = 0;
-    int accuracy = 0;
-    for (int i = 0; i < nsamples_all - ntrain_samples; i++)
-    {
-        if (result->data.fl[i] == true_results[i])
-            true_resp++;
-        for(int k = 0; k < K; k++ )
-        {
-            if( nearests->data.fl[i * K + k] == true_results[i])
-            accuracy++;
-        }
-    }
-
-    printf("true_resp = %f%%\tavg accuracy = %f%%\n", (float)true_resp / (nsamples_all - ntrain_samples) * 100,
-                                                      (float)accuracy / (nsamples_all - ntrain_samples) / K * 100);
-
-    delete[] true_results;
-    delete[] _sample;
-    cvReleaseMat( &train_resp );
-    cvReleaseMat( &nearests );
-    cvReleaseMat( &result );
-    cvReleaseMat( &data );
-    cvReleaseMat( &responses );
-
-    return 0;
+    test_and_save_classifier(model, data, responses, ntrain_samples, 0, string());
+    return true;
 }
 
 static bool
 build_nbayes_classifier( const string& data_filename )
 {
-    const int var_count = 16;
     Mat data;
-    CvMat train_data;
     Mat responses;
-
     bool ok = read_num_class_data( data_filename, 16, &data, &responses );
     if( !ok )
         return ok;
 
-    int nsamples_all = 0, ntrain_samples = 0;
+    Ptr<NormalBayesClassifier> model;
 
-    nsamples_all = data->rows;
-    ntrain_samples = (int)(nsamples_all*0.5);
+    int nsamples_all = data.rows;
+    int ntrain_samples = (int)(nsamples_all*0.8);
 
-    // 1. unroll the responses
-    printf( "Unrolling the responses...\n");
-    cvGetRows( data, &train_data, 0, ntrain_samples );
+    // create classifier by using <data> and <responses>
+    cout << "Training the classifier ...\n";
+    Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples);
+    model = StatModel::train<NormalBayesClassifier>(tdata, NormalBayesClassifier::Params());
+    cout << endl;
 
-    // 2. train classifier
-    Mat train_resp = cvCreateMat( ntrain_samples, 1, CV_32FC1);
-    for (int i = 0; i < ntrain_samples; i++)
-        train_resp->data.fl[i] = responses->data.fl[i];
-    CvNormalBayesClassifier nbayes(&train_data, train_resp);
-
-    float* _sample = new float[var_count * (nsamples_all - ntrain_samples)];
-    CvMat sample = cvMat( nsamples_all - ntrain_samples, 16, CV_32FC1, _sample );
-    float* true_results = new float[nsamples_all - ntrain_samples];
-    for (int j = ntrain_samples; j < nsamples_all; j++)
-    {
-        float *s = data->data.fl + j * var_count;
-
-        for (int i = 0; i < var_count; i++)
-        {
-            sample.data.fl[(j - ntrain_samples) * var_count + i] = s[i];
-        }
-        true_results[j - ntrain_samples] = responses->data.fl[j];
-    }
-    CvMat *result = cvCreateMat(1, nsamples_all - ntrain_samples, CV_32FC1);
-    nbayes.predict(&sample, result);
-    int true_resp = 0;
-    //int accuracy = 0;
-    for (int i = 0; i < nsamples_all - ntrain_samples; i++)
-    {
-        if (result->data.fl[i] == true_results[i])
-            true_resp++;
-    }
-
-    printf("true_resp = %f%%\n", (float)true_resp / (nsamples_all - ntrain_samples) * 100);
-
-    delete[] true_results;
-    delete[] _sample;
-    cvReleaseMat( &train_resp );
-    cvReleaseMat( &result );
-    cvReleaseMat( &data );
-    cvReleaseMat( &responses );
-
-    return 0;
+    test_and_save_classifier(model, data, responses, ntrain_samples, 0, string());
+    return true;
 }
 
 static bool
@@ -568,95 +449,47 @@ build_svm_classifier( const string& data_filename,
 {
     Mat data;
     Mat responses;
-    Mat train_resp;
-    CvMat train_data;
-    int nsamples_all = 0, ntrain_samples = 0;
-    int var_count;
-    Ptr<SVM> model;
-
     bool ok = read_num_class_data( data_filename, 16, &data, &responses );
     if( !ok )
         return ok;
 
-    ////////// SVM parameters ///////////////////////////////
-    CvSVMParams param;
-    param.kernel_type=CvSVM::LINEAR;
-    param.svm_type=CvSVM::C_SVC;
-    param.C=1;
-    ///////////////////////////////////////////////////////////
+    Ptr<SVM> model;
 
-    printf( "The database %s is loaded.\n", data_filename );
-    nsamples_all = data->rows;
-    ntrain_samples = (int)(nsamples_all*0.1);
-    var_count = data->cols;
+    int nsamples_all = data.rows;
+    int ntrain_samples = (int)(nsamples_all*0.8);
 
     // Create or load Random Trees classifier
-    if( filename_to_load )
+    if( !filename_to_load.empty() )
     {
-        // load classifier from the specified file
-        svm.load( filename_to_load );
+        model = load_classifier<SVM>(filename_to_load);
+        if( model.empty() )
+            return false;
         ntrain_samples = 0;
-        if( svm.get_var_count() == 0 )
-        {
-            printf( "Could not read the classifier %s\n", filename_to_load );
-            return -1;
-        }
-        printf( "The classifier %s is loaded.\n", filename_to_load );
     }
     else
     {
-        // train classifier
-        printf( "Training the classifier (may take a few minutes)...\n");
-        cvGetRows( data, &train_data, 0, ntrain_samples );
-        train_resp = cvCreateMat( ntrain_samples, 1, CV_32FC1);
-        for (int i = 0; i < ntrain_samples; i++)
-            train_resp->data.fl[i] = responses->data.fl[i];
-        svm.train(&train_data, train_resp, 0, 0, param);
+        // create classifier by using <data> and <responses>
+        cout << "Training the classifier ...\n";
+        Ptr<TrainData> tdata = prepare_train_data(data, responses, ntrain_samples);
+
+        SVM::Params params;
+        params.svmType = SVM::C_SVC;
+        params.kernelType = SVM::LINEAR;
+        params.C = 1;
+
+        model = StatModel::train<SVM>(tdata, params);
+        cout << endl;
     }
 
-    // classification
-    std::vector<float> _sample(var_count * (nsamples_all - ntrain_samples));
-    CvMat sample = cvMat( nsamples_all - ntrain_samples, 16, CV_32FC1, &_sample[0] );
-    std::vector<float> true_results(nsamples_all - ntrain_samples);
-    for (int j = ntrain_samples; j < nsamples_all; j++)
-    {
-        float *s = data->data.fl + j * var_count;
-
-        for (int i = 0; i < var_count; i++)
-        {
-            sample.data.fl[(j - ntrain_samples) * var_count + i] = s[i];
-        }
-        true_results[j - ntrain_samples] = responses->data.fl[j];
-    }
-    CvMat *result = cvCreateMat(1, nsamples_all - ntrain_samples, CV_32FC1);
-
-    printf("Classification (may take a few minutes)...\n");
-    double t = (double)cvGetTickCount();
-    svm.predict(&sample, result);
-    t = (double)cvGetTickCount() - t;
-    printf("Prediction type: %gms\n", t/(cvGetTickFrequency()*1000.));
-
-    int true_resp = 0;
-    for (int i = 0; i < nsamples_all - ntrain_samples; i++)
-    {
-        if (result->data.fl[i] == true_results[i])
-            true_resp++;
-    }
-
-    printf("true_resp = %f%%\n", (float)true_resp / (nsamples_all - ntrain_samples) * 100);
-
-    if( !filename_to_save.empty() )
-        model->save( filename_to_save );
-
+    test_and_save_classifier(model, data, responses, ntrain_samples, 0, filename_to_save);
     return true;
 }
 
 int main( int argc, char *argv[] )
 {
-    char* filename_to_save = 0;
-    char* filename_to_load = 0;
-    char default_data_filename[] = "./letter-recognition.data";
-    char* data_filename = default_data_filename;
+    string filename_to_save = "";
+    string filename_to_load = "";
+    string data_filename = "./letter-recognition.data";
     int method = 0;
 
     int i;
@@ -685,15 +518,15 @@ int main( int argc, char *argv[] )
         {
             method = 2;
         }
-        else if ( strcmp(argv[i], "-knearest") == 0)
+        else if( strcmp(argv[i], "-knearest") == 0 || strcmp(argv[i], "-knn") == 0 )
         {
             method = 3;
         }
-        else if ( strcmp(argv[i], "-nbayes") == 0)
+        else if( strcmp(argv[i], "-nbayes") == 0)
         {
             method = 4;
         }
-        else if ( strcmp(argv[i], "-svm") == 0)
+        else if( strcmp(argv[i], "-svm") == 0)
         {
             method = 5;
         }

samples/cpp/mushroom.cpp

@@ -1,322 +0,0 @@
-#include "opencv2/core/core_c.h"
-#include "opencv2/ml/ml.hpp"
-#include <stdio.h>
-
-static void help()
-{
-    printf("\nThis program demonstrated the use of OpenCV's decision tree function for learning and predicting data\n"
-            "Usage :\n"
-            "./mushroom <path to agaricus-lepiota.data>\n"
-            "\n"
-            "The sample demonstrates how to build a decision tree for classifying mushrooms.\n"
-            "It uses the sample base agaricus-lepiota.data from UCI Repository, here is the link:\n"
-            "\n"
-            "Newman, D.J. & Hettich, S. & Blake, C.L. & Merz, C.J. (1998).\n"
-            "UCI Repository of machine learning databases\n"
-            "[http://www.ics.uci.edu/~mlearn/MLRepository.html].\n"
-            "Irvine, CA: University of California, Department of Information and Computer Science.\n"
-            "\n"
-            "// loads the mushroom database, which is a text file, containing\n"
-            "// one training sample per row, all the input variables and the output variable are categorical,\n"
-            "// the values are encoded by characters.\n\n");
-}
-
-static int mushroom_read_database( const char* filename, CvMat** data, CvMat** missing, CvMat** responses )
-{
-    const int M = 1024;
-    FILE* f = fopen( filename, "rt" );
-    CvMemStorage* storage;
-    CvSeq* seq;
-    char buf[M+2], *ptr;
-    float* el_ptr;
-    CvSeqReader reader;
-    int i, j, var_count = 0;
-
-    if( !f )
-        return 0;
-
-    // read the first line and determine the number of variables
-    if( !fgets( buf, M, f ))
-    {
-        fclose(f);
-        return 0;
-    }
-
-    for( ptr = buf; *ptr != '\0'; ptr++ )
-        var_count += *ptr == ',';
-    assert( ptr - buf == (var_count+1)*2 );
-
-    // create temporary memory storage to store the whole database
-    el_ptr = new float[var_count+1];
-    storage = cvCreateMemStorage();
-    seq = cvCreateSeq( 0, sizeof(*seq), (var_count+1)*sizeof(float), storage );
-
-    for(;;)
-    {
-        for( i = 0; i <= var_count; i++ )
-        {
-            int c = buf[i*2];
-            el_ptr[i] = c == '?' ? -1.f : (float)c;
-        }
-        if( i != var_count+1 )
-            break;
-        cvSeqPush( seq, el_ptr );
-        if( !fgets( buf, M, f ) || !strchr( buf, ',' ) )
-            break;
-    }
-    fclose(f);
-
-    // allocate the output matrices and copy the base there
-    *data = cvCreateMat( seq->total, var_count, CV_32F );
-    *missing = cvCreateMat( seq->total, var_count, CV_8U );
-    *responses = cvCreateMat( seq->total, 1, CV_32F );
-
-    cvStartReadSeq( seq, &reader );
-
-    for( i = 0; i < seq->total; i++ )
-    {
-        const float* sdata = (float*)reader.ptr + 1;
-        float* ddata = data[0]->data.fl + var_count*i;
-        float* dr = responses[0]->data.fl + i;
-        uchar* dm = missing[0]->data.ptr + var_count*i;
-
-        for( j = 0; j < var_count; j++ )
-        {
-            ddata[j] = sdata[j];
-            dm[j] = sdata[j] < 0;
-        }
-        *dr = sdata[-1];
-        CV_NEXT_SEQ_ELEM( seq->elem_size, reader );
-    }
-
-    cvReleaseMemStorage( &storage );
-    delete [] el_ptr;
-    return 1;
-}
-
-
-static CvDTree* mushroom_create_dtree( const CvMat* data, const CvMat* missing,
-                                const CvMat* responses, float p_weight )
-{
-    CvDTree* dtree;
-    CvMat* var_type;
-    int i, hr1 = 0, hr2 = 0, p_total = 0;
-    float priors[] = { 1, p_weight };
-
-    var_type = cvCreateMat( data->cols + 1, 1, CV_8U );
-    cvSet( var_type, cvScalarAll(CV_VAR_CATEGORICAL) ); // all the variables are categorical
-
-    dtree = new CvDTree;
-
-    dtree->train( data, CV_ROW_SAMPLE, responses, 0, 0, var_type, missing,
-                  CvDTreeParams( 8, // max depth
-                                 10, // min sample count
-                                 0, // regression accuracy: N/A here
-                                 true, // compute surrogate split, as we have missing data
-                                 15, // max number of categories (use sub-optimal algorithm for larger numbers)
-                                 10, // the number of cross-validation folds
-                                 true, // use 1SE rule => smaller tree
-                                 true, // throw away the pruned tree branches
-                                 priors // the array of priors, the bigger p_weight, the more attention
-                                        // to the poisonous mushrooms
-                                        // (a mushroom will be judjed to be poisonous with bigger chance)
-                                 ));
-
-    // compute hit-rate on the training database, demonstrates predict usage.
-    for( i = 0; i < data->rows; i++ )
-    {
-        CvMat sample, mask;
-        cvGetRow( data, &sample, i );
-        cvGetRow( missing, &mask, i );
-        double r = dtree->predict( &sample, &mask )->value;
-        int d = fabs(r - responses->data.fl[i]) >= FLT_EPSILON;
-        if( d )
-        {
-            if( r != 'p' )
-                hr1++;
-            else
-                hr2++;
-        }
-        p_total += responses->data.fl[i] == 'p';
-    }
-
-    printf( "Results on the training database:\n"
-            "\tPoisonous mushrooms mis-predicted: %d (%g%%)\n"
-            "\tFalse-alarms: %d (%g%%)\n", hr1, (double)hr1*100/p_total,
-            hr2, (double)hr2*100/(data->rows - p_total) );
-
-    cvReleaseMat( &var_type );
-
-    return dtree;
-}
-
-
-static const char* var_desc[] =
-{
-    "cap shape (bell=b,conical=c,convex=x,flat=f)",
-    "cap surface (fibrous=f,grooves=g,scaly=y,smooth=s)",
-    "cap color (brown=n,buff=b,cinnamon=c,gray=g,green=r,\n\tpink=p,purple=u,red=e,white=w,yellow=y)",
-    "bruises? (bruises=t,no=f)",
-    "odor (almond=a,anise=l,creosote=c,fishy=y,foul=f,\n\tmusty=m,none=n,pungent=p,spicy=s)",
-    "gill attachment (attached=a,descending=d,free=f,notched=n)",
-    "gill spacing (close=c,crowded=w,distant=d)",
-    "gill size (broad=b,narrow=n)",
-    "gill color (black=k,brown=n,buff=b,chocolate=h,gray=g,\n\tgreen=r,orange=o,pink=p,purple=u,red=e,white=w,yellow=y)",
-    "stalk shape (enlarging=e,tapering=t)",
-    "stalk root (bulbous=b,club=c,cup=u,equal=e,rhizomorphs=z,rooted=r)",
-    "stalk surface above ring (ibrous=f,scaly=y,silky=k,smooth=s)",
-    "stalk surface below ring (ibrous=f,scaly=y,silky=k,smooth=s)",
-    "stalk color above ring (brown=n,buff=b,cinnamon=c,gray=g,orange=o,\n\tpink=p,red=e,white=w,yellow=y)",
-    "stalk color below ring (brown=n,buff=b,cinnamon=c,gray=g,orange=o,\n\tpink=p,red=e,white=w,yellow=y)",
-    "veil type (partial=p,universal=u)",
-    "veil color (brown=n,orange=o,white=w,yellow=y)",
-    "ring number (none=n,one=o,two=t)",
-    "ring type (cobwebby=c,evanescent=e,flaring=f,large=l,\n\tnone=n,pendant=p,sheathing=s,zone=z)",
-    "spore print color (black=k,brown=n,buff=b,chocolate=h,green=r,\n\torange=o,purple=u,white=w,yellow=y)",
-    "population (abundant=a,clustered=c,numerous=n,\n\tscattered=s,several=v,solitary=y)",
-    "habitat (grasses=g,leaves=l,meadows=m,paths=p\n\turban=u,waste=w,woods=d)",
-    0
-};
-
-
-static void print_variable_importance( CvDTree* dtree )
-{
-    const CvMat* var_importance = dtree->get_var_importance();
-    int i;
-    char input[1000];
-
-    if( !var_importance )
-    {
-        printf( "Error: Variable importance can not be retrieved\n" );
-        return;
-    }
-
-    printf( "Print variable importance information? (y/n) " );
-    int values_read = scanf( "%1s", input );
-    CV_Assert(values_read == 1);
-
-    if( input[0] != 'y' && input[0] != 'Y' )
-        return;
-
-    for( i = 0; i < var_importance->cols*var_importance->rows; i++ )
-    {
-        double val = var_importance->data.db[i];
-        char buf[100];
-        int len = (int)(strchr( var_desc[i], '(' ) - var_desc[i] - 1);
-        strncpy( buf, var_desc[i], len );
-        buf[len] = '\0';
-        printf( "%s", buf );
-        printf( ": %g%%\n", val*100. );
-    }
-}
-
-static void interactive_classification( CvDTree* dtree )
-{
-    char input[1000];
-    const CvDTreeNode* root;
-    CvDTreeTrainData* data;
-
-    if( !dtree )
-        return;
-
-    root = dtree->get_root();
-    data = dtree->get_data();
-
-    for(;;)
-    {
-        const CvDTreeNode* node;
-
-        printf( "Start/Proceed with interactive mushroom classification (y/n): " );
-        int values_read = scanf( "%1s", input );
-        CV_Assert(values_read == 1);
-
-        if( input[0] != 'y' && input[0] != 'Y' )
-            break;
-        printf( "Enter 1-letter answers, '?' for missing/unknown value...\n" );
-
-        // custom version of predict
-        node = root;
-        for(;;)
-        {
-            CvDTreeSplit* split = node->split;
-            int dir = 0;
-
-            if( !node->left || node->Tn <= dtree->get_pruned_tree_idx() || !node->split )
-                break;
-
-            for( ; split != 0; )
-            {
-                int vi = split->var_idx, j;
-                int count = data->cat_count->data.i[vi];
-                const int* map = data->cat_map->data.i + data->cat_ofs->data.i[vi];
-
-                printf( "%s: ", var_desc[vi] );
-                values_read = scanf( "%1s", input );
-                CV_Assert(values_read == 1);
-
-                if( input[0] == '?' )
-                {
-                    split = split->next;
-                    continue;
-                }
-
-                // convert the input character to the normalized value of the variable
-                for( j = 0; j < count; j++ )
-                    if( map[j] == input[0] )
-                        break;
-                if( j < count )
-                {
-                    dir = (split->subset[j>>5] & (1 << (j&31))) ? -1 : 1;
-                    if( split->inversed )
-                        dir = -dir;
-                    break;
-                }
-                else
-                    printf( "Error: unrecognized value\n" );
-            }
-
-            if( !dir )
-            {
-                printf( "Impossible to classify the sample\n");
-                node = 0;
-                break;
-            }
-            node = dir < 0 ? node->left : node->right;
-        }
-
-        if( node )
-            printf( "Prediction result: the mushroom is %s\n",
-                    node->class_idx == 0 ? "EDIBLE" : "POISONOUS" );
-        printf( "\n-----------------------------\n" );
-    }
-}
-
-
-int main( int argc, char** argv )
-{
-    CvMat *data = 0, *missing = 0, *responses = 0;
-    CvDTree* dtree;
-    const char* base_path = argc >= 2 ? argv[1] : "agaricus-lepiota.data";
-
-    help();
-
-    if( !mushroom_read_database( base_path, &data, &missing, &responses ) )
-    {
-        printf( "\nUnable to load the training database\n\n");
-        help();
-        return -1;
-    }
-
-    dtree = mushroom_create_dtree( data, missing, responses,
-        10 // poisonous mushrooms will have 10x higher weight in the decision tree
-        );
-    cvReleaseMat( &data );
-    cvReleaseMat( &missing );
-    cvReleaseMat( &responses );
-
-    print_variable_importance( dtree );
-    interactive_classification( dtree );
-    delete dtree;
-
-    return 0;
-}

samples/cpp/points_classifier.cpp

@@ -102,8 +102,7 @@ static void predict_and_paint(const Ptr<StatModel>& model, Mat& dst)
 static void find_decision_boundary_NBC()
 {
     // learn classifier
-    Ptr<NormalBayesClassifier> normalBayesClassifier = NormalBayesClassifier::create();
-    normalBayesClassifier->train(prepare_train_data());
+    Ptr<NormalBayesClassifier> normalBayesClassifier = StatModel::train<NormalBayesClassifier>(prepare_train_data(), NormalBayesClassifier::Params());
 
     predict_and_paint(normalBayesClassifier, imgDst);
 }
@@ -113,10 +112,7 @@ static void find_decision_boundary_NBC()
 #if _KNN_
 static void find_decision_boundary_KNN( int K )
 {
-    Ptr<KNearest> knn = KNearest::create(true);
-    knn->setDefaultK(K);
-    knn->train(prepare_train_data());
-
+    Ptr<KNearest> knn = StatModel::train<KNearest>(prepare_train_data(), KNearest::Params(K, true));
     predict_and_paint(knn, imgDst);
 }
 #endif
@@ -124,9 +120,7 @@ static void find_decision_boundary_KNN( int K )
 #if _SVM_
 static void find_decision_boundary_SVM( SVM::Params params )
 {
-    Ptr<SVM> svm = SVM::create(params);
-    svm->train(prepare_train_data());
-
+    Ptr<SVM> svm = StatModel::train<SVM>(prepare_train_data(), params);
     predict_and_paint(svm, imgDst);
 
     Mat sv = svm->getSupportVectors();
@@ -149,8 +143,7 @@ static void find_decision_boundary_DT()
     params.use1SERule = false;
     params.truncatePrunedTree = false;
 
-    Ptr<DTrees> dtree = DTrees::create(params);
-    dtree->train(prepare_train_data());
+    Ptr<DTrees> dtree = StatModel::train<DTrees>(prepare_train_data(), params);
 
     predict_and_paint(dtree, imgDst);
 }
@@ -167,8 +160,7 @@ static void find_decision_boundary_BT()
                           Mat() // priors
                           );
 
-    Ptr<Boost> boost = Boost::create(params);
-    boost->train(prepare_train_data());
+    Ptr<Boost> boost = StatModel::train<Boost>(prepare_train_data(), params);
     predict_and_paint(boost, imgDst);
 }
 
@@ -185,8 +177,7 @@ static void find_decision_boundary_GBT()
                          false // use_surrogates )
                          );
 
-    Ptr<GBTrees> gbtrees = GBTrees::create(params);
-    gbtrees->train(prepare_train_data());
+    Ptr<GBTrees> gbtrees = StatModel::train<GBTrees>(prepare_train_data(), params);
     predict_and_paint(gbtrees, imgDst);
 }
 #endif
@@ -205,8 +196,7 @@ static void find_decision_boundary_RF()
                         TermCriteria(TermCriteria::MAX_ITER, 5, 0) // max_num_of_trees_in_the_forest,
                        );
 
-    Ptr<RTrees> rtrees = RTrees::create(params);
-    rtrees->train(prepare_train_data());
+    Ptr<RTrees> rtrees = StatModel::train<RTrees>(prepare_train_data(), params);
     predict_and_paint(rtrees, imgDst);
 }
 
@@ -215,9 +205,8 @@ static void find_decision_boundary_RF()
 #if _ANN_
 static void find_decision_boundary_ANN( const Mat&  layer_sizes )
 {
-    ANN_MLP::Params params(TermCriteria(TermCriteria::MAX_ITER+TermCriteria::EPS, 300, FLT_EPSILON),
+    ANN_MLP::Params params(layer_sizes, ANN_MLP::SIGMOID_SYM, 1, 1, TermCriteria(TermCriteria::MAX_ITER+TermCriteria::EPS, 300, FLT_EPSILON),
                            ANN_MLP::Params::BACKPROP, 0.001);
-    Ptr<ANN_MLP> ann = ANN_MLP::create(layer_sizes, params, ANN_MLP::SIGMOID_SYM, 1, 1 );
 
     Mat trainClasses = Mat::zeros( trainedPoints.size(), classColors.size(), CV_32FC1 );
     for( int i = 0; i < trainClasses.rows; i++ )
@@ -228,7 +217,7 @@ static void find_decision_boundary_ANN( const Mat&  layer_sizes )
     Mat samples = prepare_train_samples(trainedPoints);
     Ptr<TrainData> tdata = TrainData::create(samples, ROW_SAMPLE, trainClasses);
 
-    ann->train(tdata);
+    Ptr<ANN_MLP> ann = StatModel::train<ANN_MLP>(tdata, params);
     predict_and_paint(ann, imgDst);
 }
 #endif
@@ -340,18 +329,15 @@ int main()
             img.copyTo( imgDst );
 #if _NBC_
             find_decision_boundary_NBC();
-            namedWindow( "NormalBayesClassifier", WINDOW_AUTOSIZE );
             imshow( "NormalBayesClassifier", imgDst );
 #endif
 #if _KNN_
             int K = 3;
             find_decision_boundary_KNN( K );
-            namedWindow( "kNN", WINDOW_AUTOSIZE );
             imshow( "kNN", imgDst );
 
             K = 15;
             find_decision_boundary_KNN( K );
-            namedWindow( "kNN2", WINDOW_AUTOSIZE );
             imshow( "kNN2", imgDst );
 #endif
 
@@ -369,36 +355,30 @@ int main()
             params.termCrit = TermCriteria(TermCriteria::MAX_ITER+TermCriteria::EPS, 1000, 0.01);
 
             find_decision_boundary_SVM( params );
-            namedWindow( "classificationSVM1", WINDOW_AUTOSIZE );
             imshow( "classificationSVM1", imgDst );
 
             params.C = 10;
             find_decision_boundary_SVM( params );
-            namedWindow( "classificationSVM2", WINDOW_AUTOSIZE );
             imshow( "classificationSVM2", imgDst );
 #endif
 
 #if _DT_
             find_decision_boundary_DT();
-            namedWindow( "DT", WINDOW_AUTOSIZE );
             imshow( "DT", imgDst );
 #endif
 
 #if _BT_
             find_decision_boundary_BT();
-            namedWindow( "BT", WINDOW_AUTOSIZE );
             imshow( "BT", imgDst);
 #endif
 
 #if _GBT_
             find_decision_boundary_GBT();
-            namedWindow( "GBT", WINDOW_AUTOSIZE );
             imshow( "GBT", imgDst);
 #endif
 
 #if _RF_
             find_decision_boundary_RF();
-            namedWindow( "RF", WINDOW_AUTOSIZE );
             imshow( "RF", imgDst);
 #endif
 
@@ -408,13 +388,11 @@ int main()
             layer_sizes1.at<int>(1) = 5;
             layer_sizes1.at<int>(2) = classColors.size();
             find_decision_boundary_ANN( layer_sizes1 );
-            namedWindow( "ANN", WINDOW_AUTOSIZE );
             imshow( "ANN", imgDst );
 #endif
 
 #if _EM_
             find_decision_boundary_EM();
-            namedWindow( "EM", WINDOW_AUTOSIZE );
             imshow( "EM", imgDst );
 #endif
         }

samples/cpp/train_HOG.cpp

@@ -8,9 +8,10 @@
 #include <time.h>
 
 using namespace cv;
+using namespace cv::ml;
 using namespace std;
 
-void get_svm_detector(const SVM& svm, vector< float > & hog_detector );
+void get_svm_detector(const Ptr<SVM>& svm, vector< float > & hog_detector );
 void convert_to_ml(const std::vector< cv::Mat > & train_samples, cv::Mat& trainData );
 void load_images( const string & prefix, const string & filename, vector< Mat > & img_lst );
 void sample_neg( const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst, const Size & size );
@@ -20,49 +21,24 @@ void train_svm( const vector< Mat > & gradient_lst, const vector< int > & labels
 void draw_locations( Mat & img, const vector< Rect > & locations, const Scalar & color );
 void test_it( const Size & size );
 
-void get_svm_detector(const SVM& svm, vector< float > & hog_detector )
+void get_svm_detector(const Ptr<SVM>& svm, vector< float > & hog_detector )
 {
-    // get the number of variables
-    const int var_all = svm.get_var_count();
-    // get the number of support vectors
-    const int sv_total = svm.get_support_vector_count();
-    // get the decision function
-    const CvSVMDecisionFunc* decision_func = svm.get_decision_function();
     // get the support vectors
-    const float** sv = new const float*[ sv_total ];
-    for( int i = 0 ; i < sv_total ; ++i )
-        sv[ i ] = svm.get_support_vector(i);
+    Mat sv = svm->getSupportVectors();
+    const int sv_total = sv.rows;
+    // get the decision function
+    Mat alpha, svidx;
+    double rho = svm->getDecisionFunction(0, alpha, svidx);
 
-    CV_Assert( var_all > 0 &&
-        sv_total > 0 &&
-        decision_func != 0 &&
-        decision_func->alpha != 0 &&
-        decision_func->sv_count == sv_total );
+    CV_Assert( alpha.total() == 1 && svidx.total() == 1 && sv_total == 1 );
+    CV_Assert( (alpha.type() == CV_64F && alpha.at<double>(0) == 1.) ||
+               (alpha.type() == CV_32F && alpha.at<float>(0) == 1.f) );
+    CV_Assert( sv.type() == CV_32F );
+    hog_detector.clear();
 
-    float svi = 0.f;
-
-    hog_detector.clear(); //clear stuff in vector.
-    hog_detector.reserve( var_all + 1 ); //reserve place for memory efficiency.
-
-     /**
-    * hog_detector^i = \sum_j support_vector_j^i * \alpha_j
-    * hog_detector^dim = -\rho
-    */
-   for( int i = 0 ; i < var_all ; ++i )
-    {
-        svi = 0.f;
-        for( int j = 0 ; j < sv_total ; ++j )
-        {
-            if( decision_func->sv_index != NULL ) // sometime the sv_index isn't store on YML/XML.
-                svi += (float)( sv[decision_func->sv_index[j]][i] * decision_func->alpha[ j ] );
-            else
-                svi += (float)( sv[j][i] * decision_func->alpha[ j ] );
-        }
-        hog_detector.push_back( svi );
-    }
-    hog_detector.push_back( (float)-decision_func->rho );
-
-    delete[] sv;
+    hog_detector.resize(sv.cols + 1);
+    memcpy(&hog_detector[0], sv.data, sv.cols*sizeof(hog_detector[0]));
+    hog_detector[sv.cols] = (float)-rho;
 }
 
 
@@ -263,7 +239,7 @@ Mat get_hogdescriptor_visu(const Mat& color_origImg, vector<float>& descriptorVa
             int mx = drawX + cellSize/2;
             int my = drawY + cellSize/2;
 
-            rectangle(visu, Point((int)(drawX*zoomFac), (int)(drawY*zoomFac)), Point((int)((drawX+cellSize)*zoomFac), (int)((drawY+cellSize)*zoomFac)), CV_RGB(100,100,100), 1);
+            rectangle(visu, Point((int)(drawX*zoomFac), (int)(drawY*zoomFac)), Point((int)((drawX+cellSize)*zoomFac), (int)((drawY+cellSize)*zoomFac)), Scalar(100,100,100), 1);
 
             // draw in each cell all 9 gradient strengths
             for (int bin=0; bin<gradientBinSize; bin++)
@@ -288,7 +264,7 @@ Mat get_hogdescriptor_visu(const Mat& color_origImg, vector<float>& descriptorVa
                 float y2 = my + dirVecY * currentGradStrength * maxVecLen * scale;
 
                 // draw gradient visualization
-                line(visu, Point((int)(x1*zoomFac),(int)(y1*zoomFac)), Point((int)(x2*zoomFac),(int)(y2*zoomFac)), CV_RGB(0,255,0), 1);
+                line(visu, Point((int)(x1*zoomFac),(int)(y1*zoomFac)), Point((int)(x2*zoomFac),(int)(y2*zoomFac)), Scalar(0,255,0), 1);
 
             } // for (all bins)
 
@@ -337,28 +313,26 @@ void compute_hog( const vector< Mat > & img_lst, vector< Mat > & gradient_lst, c
 
 void train_svm( const vector< Mat > & gradient_lst, const vector< int > & labels )
 {
-    SVM svm;
-
     /* Default values to train SVM */
-    SVMParams params;
+    SVM::Params params;
     params.coef0 = 0.0;
     params.degree = 3;
-    params.term_crit.epsilon = 1e-3;
+    params.termCrit.epsilon = 1e-3;
     params.gamma = 0;
-    params.kernel_type = SVM::LINEAR;
+    params.kernelType = SVM::LINEAR;
     params.nu = 0.5;
     params.p = 0.1; // for EPSILON_SVR, epsilon in loss function?
     params.C = 0.01; // From paper, soft classifier
-    params.svm_type = SVM::EPS_SVR; // C_SVC; // EPSILON_SVR; // may be also NU_SVR; // do regression task
+    params.svmType = SVM::EPS_SVR; // C_SVC; // EPSILON_SVR; // may be also NU_SVR; // do regression task
 
     Mat train_data;
     convert_to_ml( gradient_lst, train_data );
 
     clog << "Start training...";
-    svm.train( train_data, Mat( labels ), Mat(), Mat(), params );
+    Ptr<SVM> svm = StatModel::train<SVM>(train_data, ROW_SAMPLE, Mat(labels), params);
     clog << "...[done]" << endl;
 
-    svm.save( "my_people_detector.yml" );
+    svm->save( "my_people_detector.yml" );
 }
 
 void draw_locations( Mat & img, const vector< Rect > & locations, const Scalar & color )
@@ -380,7 +354,7 @@ void test_it( const Size & size )
     Scalar reference( 0, 255, 0 );
     Scalar trained( 0, 0, 255 );
     Mat img, draw;
-    SVM svm;
+    Ptr<SVM> svm;
     HOGDescriptor hog;
     HOGDescriptor my_hog;
     my_hog.winSize = size;
@@ -388,7 +362,7 @@ void test_it( const Size & size )
     vector< Rect > locations;
 
     // Load the trained SVM.
-    svm.load( "my_people_detector.yml" );
+    svm = StatModel::load<SVM>( "my_people_detector.yml" );
     // Set the trained svm to my_hog
     vector< float > hog_detector;
     get_svm_detector( svm, hog_detector );

samples/cpp/tree_engine.cpp

@@ -1,63 +1,35 @@
 #include "opencv2/ml/ml.hpp"
-#include "opencv2/core/core_c.h"
+#include "opencv2/core/core.hpp"
 #include "opencv2/core/utility.hpp"
 #include <stdio.h>
+#include <string>
 #include <map>
 
+using namespace cv;
+using namespace cv::ml;
+
 static void help()
 {
     printf(
-        "\nThis sample demonstrates how to use different decision trees and forests including boosting and random trees:\n"
-        "CvDTree dtree;\n"
-        "CvBoost boost;\n"
-        "CvRTrees rtrees;\n"
-        "CvERTrees ertrees;\n"
-        "CvGBTrees gbtrees;\n"
-        "Call:\n\t./tree_engine [-r <response_column>] [-c] <csv filename>\n"
+        "\nThis sample demonstrates how to use different decision trees and forests including boosting and random trees.\n"
+        "Usage:\n\t./tree_engine [-r <response_column>] [-ts type_spec] <csv filename>\n"
         "where -r <response_column> specified the 0-based index of the response (0 by default)\n"
-        "-c specifies that the response is categorical (it's ordered by default) and\n"
+        "-ts specifies the var type spec in the form ord[n1,n2-n3,n4-n5,...]cat[m1-m2,m3,m4-m5,...]\n"
         "<csv filename> is the name of training data file in comma-separated value format\n\n");
 }
 
-
-static int count_classes(CvMLData& data)
+static void train_and_print_errs(Ptr<StatModel> model, const Ptr<TrainData>& data)
 {
-    cv::Mat r = cv::cvarrToMat(data.get_responses());
-    std::map<int, int> rmap;
-    int i, n = (int)r.total();
-    for( i = 0; i < n; i++ )
+    bool ok = model->train(data);
+    if( !ok )
     {
-        float val = r.at<float>(i);
-        int ival = cvRound(val);
-        if( ival != val )
-            return -1;
-        rmap[ival] = 1;
+        printf("Training failed\n");
     }
-    return (int)rmap.size();
-}
-
-static void print_result(float train_err, float test_err, const CvMat* _var_imp)
-{
-    printf( "train error    %f\n", train_err );
-    printf( "test error    %f\n\n", test_err );
-
-    if (_var_imp)
+    else
     {
-        cv::Mat var_imp = cv::cvarrToMat(_var_imp), sorted_idx;
-        cv::sortIdx(var_imp, sorted_idx, CV_SORT_EVERY_ROW + CV_SORT_DESCENDING);
-
-        printf( "variable importance:\n" );
-        int i, n = (int)var_imp.total();
-        int type = var_imp.type();
-        CV_Assert(type == CV_32F || type == CV_64F);
-
-        for( i = 0; i < n; i++)
-        {
-            int k = sorted_idx.at<int>(i);
-            printf( "%d\t%f\n", k, type == CV_32F ? var_imp.at<float>(k) : var_imp.at<double>(k));
-        }
+        printf( "train error: %f\n", model->calcError(data, false, noArray()) );
+        printf( "test error: %f\n\n", model->calcError(data, true, noArray()) );
     }
-    printf("\n");
 }
 
 int main(int argc, char** argv)
@@ -69,14 +41,14 @@ int main(int argc, char** argv)
     }
     const char* filename = 0;
     int response_idx = 0;
-    bool categorical_response = false;
+    std::string typespec;
 
     for(int i = 1; i < argc; i++)
     {
         if(strcmp(argv[i], "-r") == 0)
             sscanf(argv[++i], "%d", &response_idx);
-        else if(strcmp(argv[i], "-c") == 0)
-            categorical_response = true;
+        else if(strcmp(argv[i], "-ts") == 0)
+            typespec = argv[++i];
         else if(argv[i][0] != '-' )
             filename = argv[i];
         else
@@ -88,52 +60,32 @@ int main(int argc, char** argv)
     }
 
     printf("\nReading in %s...\n\n",filename);
-    CvDTree dtree;
-    CvBoost boost;
-    CvRTrees rtrees;
-    CvERTrees ertrees;
-    CvGBTrees gbtrees;
+    const double train_test_split_ratio = 0.5;
 
-    CvMLData data;
+    Ptr<TrainData> data = TrainData::loadFromCSV(filename, 0, response_idx, response_idx+1, typespec);
 
-
-    CvTrainTestSplit spl( 0.5f );
-
-    if ( data.read_csv( filename ) == 0)
+    if( data.empty() )
     {
-        data.set_response_idx( response_idx );
-        if(categorical_response)
-            data.change_var_type( response_idx, CV_VAR_CATEGORICAL );
-        data.set_train_test_split( &spl );
-
-        printf("======DTREE=====\n");
-        dtree.train( &data, CvDTreeParams( 10, 2, 0, false, 16, 0, false, false, 0 ));
-        print_result( dtree.calc_error( &data, CV_TRAIN_ERROR), dtree.calc_error( &data, CV_TEST_ERROR ), dtree.get_var_importance() );
-
-        if( categorical_response && count_classes(data) == 2 )
-        {
-        printf("======BOOST=====\n");
-        boost.train( &data, CvBoostParams(CvBoost::DISCRETE, 100, 0.95, 2, false, 0));
-        print_result( boost.calc_error( &data, CV_TRAIN_ERROR ), boost.calc_error( &data, CV_TEST_ERROR ), 0 ); //doesn't compute importance
-        }
-
-        printf("======RTREES=====\n");
-        rtrees.train( &data, CvRTParams( 10, 2, 0, false, 16, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ));
-        print_result( rtrees.calc_error( &data, CV_TRAIN_ERROR), rtrees.calc_error( &data, CV_TEST_ERROR ), rtrees.get_var_importance() );
-
-        printf("======ERTREES=====\n");
-        ertrees.train( &data, CvRTParams( 18, 2, 0, false, 16, 0, true, 0, 100, 0, CV_TERMCRIT_ITER ));
-        print_result( ertrees.calc_error( &data, CV_TRAIN_ERROR), ertrees.calc_error( &data, CV_TEST_ERROR ), ertrees.get_var_importance() );
-
-        printf("======GBTREES=====\n");
-        if (categorical_response)
-            gbtrees.train( &data, CvGBTreesParams(CvGBTrees::DEVIANCE_LOSS, 100, 0.1f, 0.8f, 5, false));
-        else
-            gbtrees.train( &data, CvGBTreesParams(CvGBTrees::SQUARED_LOSS, 100, 0.1f, 0.8f, 5, false));
-        print_result( gbtrees.calc_error( &data, CV_TRAIN_ERROR), gbtrees.calc_error( &data, CV_TEST_ERROR ), 0 ); //doesn't compute importance
+        printf("ERROR: File %s can not be read\n", filename);
+        return 0;
     }
-    else
-        printf("File can not be read");
+
+    data->setTrainTestSplitRatio(train_test_split_ratio);
+
+    printf("======DTREE=====\n");
+    Ptr<DTrees> dtree = DTrees::create(DTrees::Params( 10, 2, 0, false, 16, 0, false, false, Mat() ));
+    train_and_print_errs(dtree, data);
+
+    if( (int)data->getClassLabels().total() <= 2 ) // regression or 2-class classification problem
+    {
+        printf("======BOOST=====\n");
+        Ptr<Boost> boost = Boost::create(Boost::Params(Boost::GENTLE, 100, 0.95, 2, false, Mat()));
+        train_and_print_errs(boost, data);
+    }
+
+    printf("======RTREES=====\n");
+    Ptr<RTrees> rtrees = RTrees::create(RTrees::Params(10, 2, 0, false, 16, Mat(), false, 0, TermCriteria(TermCriteria::MAX_ITER, 100, 0)));
+    train_and_print_errs(rtrees, data);
 
     return 0;
 }

samples/cpp/tutorial_code/ml/introduction_to_svm/introduction_to_svm.cpp

@@ -4,29 +4,29 @@
 #include <opencv2/ml/ml.hpp>
 
 using namespace cv;
+using namespace cv::ml;
 
-int main()
+int main(int, char**)
 {
     // Data for visual representation
     int width = 512, height = 512;
     Mat image = Mat::zeros(height, width, CV_8UC3);
 
     // Set up training data
-    float labels[4] = {1.0, -1.0, -1.0, -1.0};
-    Mat labelsMat(4, 1, CV_32FC1, labels);
+    int labels[4] = {1, -1, -1, -1};
+    Mat labelsMat(4, 1, CV_32SC1, labels);
 
     float trainingData[4][2] = { {501, 10}, {255, 10}, {501, 255}, {10, 501} };
     Mat trainingDataMat(4, 2, CV_32FC1, trainingData);
 
     // Set up SVM's parameters
-    CvSVMParams params;
-    params.svm_type    = CvSVM::C_SVC;
-    params.kernel_type = CvSVM::LINEAR;
-    params.term_crit   = cvTermCriteria(CV_TERMCRIT_ITER, 100, 1e-6);
+    SVM::Params params;
+    params.svmType    = SVM::C_SVC;
+    params.kernelType = SVM::LINEAR;
+    params.termCrit   = TermCriteria(TermCriteria::MAX_ITER, 100, 1e-6);
 
     // Train the SVM
-    CvSVM SVM;
-    SVM.train(trainingDataMat, labelsMat, Mat(), Mat(), params);
+    Ptr<SVM> svm = StatModel::train<SVM>(trainingDataMat, ROW_SAMPLE, labelsMat, params);
 
     Vec3b green(0,255,0), blue (255,0,0);
     // Show the decision regions given by the SVM
@@ -34,30 +34,30 @@ int main()
         for (int j = 0; j < image.cols; ++j)
         {
             Mat sampleMat = (Mat_<float>(1,2) << j,i);
-            float response = SVM.predict(sampleMat);
+            float response = svm->predict(sampleMat);
 
             if (response == 1)
                 image.at<Vec3b>(i,j)  = green;
             else if (response == -1)
-                 image.at<Vec3b>(i,j)  = blue;
+                image.at<Vec3b>(i,j)  = blue;
         }
 
     // Show the training data
     int thickness = -1;
     int lineType = 8;
-    circle(	image, Point(501,  10), 5, Scalar(  0,   0,   0), thickness, lineType);
-    circle(	image, Point(255,  10), 5, Scalar(255, 255, 255), thickness, lineType);
-    circle(	image, Point(501, 255), 5, Scalar(255, 255, 255), thickness, lineType);
-    circle(	image, Point( 10, 501), 5, Scalar(255, 255, 255), thickness, lineType);
+    circle(	image, Point(501,  10), 5, Scalar(  0,   0,   0), thickness, lineType );
+    circle(	image, Point(255,  10), 5, Scalar(255, 255, 255), thickness, lineType );
+    circle(	image, Point(501, 255), 5, Scalar(255, 255, 255), thickness, lineType );
+    circle(	image, Point( 10, 501), 5, Scalar(255, 255, 255), thickness, lineType );
 
     // Show support vectors
     thickness = 2;
     lineType  = 8;
-    int c     = SVM.get_support_vector_count();
+    Mat sv = svm->getSupportVectors();
 
-    for (int i = 0; i < c; ++i)
+    for (int i = 0; i < sv.rows; ++i)
     {
-        const float* v = SVM.get_support_vector(i);
+        const float* v = sv.ptr<float>(i);
         circle(	image,  Point( (int) v[0], (int) v[1]),   6,  Scalar(128, 128, 128), thickness, lineType);
     }
 

samples/cpp/tutorial_code/ml/non_linear_svms/non_linear_svms.cpp

@@ -8,6 +8,7 @@
 #define FRAC_LINEAR_SEP		0.9f	    // Fraction of samples which compose the linear separable part
 
 using namespace cv;
+using namespace cv::ml;
 using namespace std;
 
 static void help()
@@ -30,7 +31,7 @@ int main()
 
     //--------------------- 1. Set up training data randomly ---------------------------------------
     Mat trainData(2*NTRAINING_SAMPLES, 2, CV_32FC1);
-    Mat labels   (2*NTRAINING_SAMPLES, 1, CV_32FC1);
+    Mat labels   (2*NTRAINING_SAMPLES, 1, CV_32SC1);
 
     RNG rng(100); // Random value generation class
 
@@ -71,16 +72,15 @@ int main()
     labels.rowRange(NTRAINING_SAMPLES, 2*NTRAINING_SAMPLES).setTo(2);  // Class 2
 
     //------------------------ 2. Set up the support vector machines parameters --------------------
-    CvSVMParams params;
-    params.svm_type    = SVM::C_SVC;
+    SVM::Params params;
+    params.svmType    = SVM::C_SVC;
     params.C 		   = 0.1;
-    params.kernel_type = SVM::LINEAR;
-    params.term_crit   = TermCriteria(CV_TERMCRIT_ITER, (int)1e7, 1e-6);
+    params.kernelType = SVM::LINEAR;
+    params.termCrit   = TermCriteria(TermCriteria::MAX_ITER, (int)1e7, 1e-6);
 
     //------------------------ 3. Train the svm ----------------------------------------------------
     cout << "Starting training process" << endl;
-    CvSVM svm;
-    svm.train(trainData, labels, Mat(), Mat(), params);
+    Ptr<SVM> svm = StatModel::train<SVM>(trainData, ROW_SAMPLE, labels, params);
     cout << "Finished training process" << endl;
 
     //------------------------ 4. Show the decision regions ----------------------------------------
@@ -89,7 +89,7 @@ int main()
         for (int j = 0; j < I.cols; ++j)
         {
             Mat sampleMat = (Mat_<float>(1,2) << i, j);
-            float response = svm.predict(sampleMat);
+            float response = svm->predict(sampleMat);
 
             if      (response == 1)    I.at<Vec3b>(j, i)  = green;
             else if (response == 2)    I.at<Vec3b>(j, i)  = blue;
@@ -117,11 +117,11 @@ int main()
     //------------------------- 6. Show support vectors --------------------------------------------
     thick = 2;
     lineType  = 8;
-    int x     = svm.get_support_vector_count();
+    Mat sv = svm->getSupportVectors();
 
-    for (int i = 0; i < x; ++i)
+    for (int i = 0; i < sv.rows; ++i)
     {
-        const float* v = svm.get_support_vector(i);
+        const float* v = sv.ptr<float>(i);
         circle(	I,  Point( (int) v[0], (int) v[1]), 6, Scalar(128, 128, 128), thick, lineType);
     }