mirror of
https://github.com/tesseract-ocr/tesseract.git
synced 2024-12-01 07:59:05 +08:00
Merge branch 'master' of https://github.com/tesseract-ocr/tesseract
* 'master' of https://github.com/tesseract-ocr/tesseract: (27 commits) Rework check for readable input file fix "mktemp -d --tmpdir" on Mac OS; see #1453 pgedit: Change some variables from global to local ones improve description of min_characters_to_try variable WERD_RES: Remove comparisons which are constant GENERIC_2D_ARRAY: Pass parameters by reference genericvector: Pass parameters by reference chop: Use more efficient float calculations for sqrt rect: Use more efficient float calculations for ceil, floor intproto: Use more efficient float calculations for floor genericvector: Rewrite code to satisfy static code analyzer Fix constructor for class Dict (uninitialized member variables) Fix use of wrong UNICHARSET lstmtraining: Remove dead code for purified model name combine_tessdata: Handle failures when extracting lstmtraining: Check write permission for output model implement parameter min_characters_to_try for minimum characters to try to skip page entirely. fixes #1729 Merge and enhance documentation on language and script models Document some more config options for tesseract Add Makefile rule to build HTML manpages ...
This commit is contained in:
Zdenko Podobný
commit
8598731daf
@ -12,6 +12,12 @@
|
||||
## About
|
||||
|
||||
This package contains an **OCR engine** - `libtesseract` and a **command line program** - `tesseract`.
|
||||
Tesseract 4 adds a new neural net (LSTM) based OCR engine which is focused
|
||||
on line recognition, but also still supports the legacy Tesseract OCR engine of
|
||||
Tesseract 3 which works by recognizing character patterns. Compatibility with
|
||||
Tesseract 3 is enabled by using the Legacy OCR Engine mode (--oem 0).
|
||||
It also needs traineddata files which support the legacy engine, for example
|
||||
those from the tessdata repository.
|
||||
|
||||
The lead developer is Ray Smith. The maintainer is Zdenko Podobny.
|
||||
For a list of contributors see [AUTHORS](https://github.com/tesseract-ocr/tesseract/blob/master/AUTHORS)
|
||||
|
||||
@ -6,7 +6,7 @@ asciidoc=asciidoc -d manpage
|
||||
|
||||
|
||||
man_MANS = \
|
||||
combine_lang_model.1 \
|
||||
combine_lang_model.1 \
|
||||
combine_tessdata.1 \
|
||||
dawg2wordlist.1 \
|
||||
lstmeval.1 \
|
||||
@ -31,9 +31,16 @@ endif
|
||||
|
||||
EXTRA_DIST = $(man_MANS) Doxyfile
|
||||
|
||||
.PHONY: html
|
||||
|
||||
html: $(patsubst %,%.html,$(man_MANS))
|
||||
|
||||
%: %.asc
|
||||
$(asciidoc) -o $@ $<
|
||||
|
||||
%.html: %.asc
|
||||
asciidoc -b html5 -o $@ $<
|
||||
|
||||
MAINTAINERCLEANFILES = $(man_MANS) Doxyfile
|
||||
|
||||
endif
|
||||
|
||||
@ -34,7 +34,9 @@ IN/OUT ARGUMENTS
|
||||
|
||||
'outputbase'::
|
||||
The basename of the output file (to which the appropriate extension
|
||||
will be appended). By default the output will be named 'outbase.txt'.
|
||||
will be appended). By default the output will be a text file
|
||||
with `.txt` added to the basename unless there are one or more
|
||||
'configfile' options which explicitly specify the desired output.
|
||||
|
||||
'stdout'::
|
||||
Instruction to sent output data to standard output
|
||||
@ -88,10 +90,21 @@ OPTIONS
|
||||
contains a list of variables and their values, one per line, with a
|
||||
space separating variable from value. Interesting config files
|
||||
include: +
|
||||
* hocr - Output in hOCR format instead of as a text file.
|
||||
* pdf - Output in pdf instead of a text file.
|
||||
* `hocr` - Output in hOCR format (file extension `.hocr`).
|
||||
* `pdf` - Output PDF (file extension `.pdf`).
|
||||
* `tsv` - Output TSV (file extension `.tsv`).
|
||||
* `txt` - Output plain text (file extension `.txt`).
|
||||
* `get.images` - Write images.
|
||||
* `logfile` - Write debug file `tesseract.log`.
|
||||
* `lstm.train` - Used for LSTM training.
|
||||
* `makebox` - Output box file.
|
||||
* `quiet` - Write debug file to /dev/null.
|
||||
|
||||
*Nota Bene:* The options '-l lang' and '--psm N' must occur
|
||||
It is possible to select several config files, for example
|
||||
`tesseract image.png demo hocr pdf txt` will create three output files
|
||||
`demo.hocr`, `demo.pdf` and `demo.txt` with the OCR results.
|
||||
|
||||
*Nota Bene:* The options `-l lang` and `--psm N` must occur
|
||||
before any 'configfile'.
|
||||
|
||||
|
||||
@ -110,19 +123,35 @@ SINGLE OPTIONS
|
||||
Returns the current version of the tesseract(1) executable.
|
||||
|
||||
'--list-langs'::
|
||||
List available languages for tesseract engine. Can be used with --tessdata-dir.
|
||||
List available languages for tesseract engine. Can be used with `--tessdata-dir`.
|
||||
|
||||
'--print-parameters'::
|
||||
Print tesseract parameters.
|
||||
|
||||
|
||||
|
||||
LANGUAGES
|
||||
---------
|
||||
LANGUAGES AND SCRIPTS
|
||||
---------------------
|
||||
|
||||
The currently available traineddata files for tesseract 4.0
|
||||
for the following languages are in
|
||||
(in https://github.com/tesseract-ocr/tessdata_fast):
|
||||
To recognize some text with Tesseract, it is normally necessary to specify
|
||||
the language(s) or script of the text (unless it is English text which is
|
||||
supported by default) using `-l lang`.
|
||||
|
||||
Selecting a language automatically also selects the language specific
|
||||
character set and dictionary (word list).
|
||||
|
||||
Selecting a script typically selects all characters of that script
|
||||
which can be from different languages. The dictionary which is included
|
||||
also contains a mix from different languages.
|
||||
In most cases, a script also supports English.
|
||||
So it is possible to recognize a language that has not been specifically
|
||||
trained for by using traineddata for the script it is written in.
|
||||
|
||||
https://github.com/tesseract-ocr/tessdata_fast provides fast language and
|
||||
script models which are also part of Linux distributions.
|
||||
|
||||
For Tesseract 4, `tessdata_fast` includes traineddata files for the
|
||||
following languages:
|
||||
|
||||
*afr* (Afrikaans),
|
||||
*amh* (Amharic),
|
||||
@ -245,17 +274,10 @@ for the following languages are in
|
||||
To use a non-standard language pack named *foo.traineddata*, set the
|
||||
*TESSDATA_PREFIX* environment variable so the file can be found at
|
||||
*TESSDATA_PREFIX*/tessdata/*foo*.traineddata and give Tesseract the
|
||||
argument '-l foo'.
|
||||
argument `-l foo`.
|
||||
|
||||
SCRIPTS
|
||||
-------
|
||||
|
||||
The traineddata files for the following scripts for tesseract 4.0
|
||||
are also in https://github.com/tesseract-ocr/tessdata_fast.
|
||||
|
||||
In most cases, each of these contains all the languages that use that script PLUS English.
|
||||
So it is possible to recognize a language that has not been specifically trained for
|
||||
by using traineddata for the script it is written in.
|
||||
For Tesseract 4, `tessdata_fast` includes traineddata files for the
|
||||
following scripts:
|
||||
|
||||
Arabic,
|
||||
Armenian,
|
||||
@ -295,6 +317,18 @@ Thai,
|
||||
Tibetan,
|
||||
Vietnamese.
|
||||
|
||||
The same languages and scripts are available from
|
||||
https://github.com/tesseract-ocr/tessdata_best.
|
||||
`tessdata_best` provides slow language and script models.
|
||||
These models are needed for training. They also can give better OCR results,
|
||||
but the recognition takes much more time.
|
||||
|
||||
Both `tessdata_fast` and `tessdata_best` only support the LSTM OCR engine.
|
||||
|
||||
There is a third repository, https://github.com/tesseract-ocr/tessdata,
|
||||
with models which support both the Tesseract 3 legacy OCR engine and the
|
||||
Tesseract 4 LSTM OCR engine.
|
||||
|
||||
|
||||
CONFIG FILES AND AUGMENTING WITH USER DATA
|
||||
------------------------------------------
|
||||
@ -364,18 +398,29 @@ scripts are now included to allow anyone to reproduce some of these tests.
|
||||
See <https://github.com/tesseract-ocr/tesseract/wiki/TestingTesseract> for more
|
||||
details.
|
||||
|
||||
Tesseract 3.00 adds a number of new languages, including Chinese, Japanese,
|
||||
and Korean. It also introduces a new, single-file based system of managing
|
||||
Tesseract 3.00 added a number of new languages, including Chinese, Japanese,
|
||||
and Korean. It also introduced a new, single-file based system of managing
|
||||
language data.
|
||||
|
||||
Tesseract 3.02 adds BiDirectional text support, the ability to recognize
|
||||
Tesseract 3.02 added BiDirectional text support, the ability to recognize
|
||||
multiple languages in a single image, and improved layout analysis.
|
||||
|
||||
For further details, see the file ReleaseNotes included with the distribution.
|
||||
Tesseract 4 adds a new neural net (LSTM) based OCR engine which is focused
|
||||
on line recognition, but also still supports the legacy Tesseract OCR engine of
|
||||
Tesseract 3 which works by recognizing character patterns. Compatibility with
|
||||
Tesseract 3 is enabled by `--oem 0`. This also needs traineddata files which
|
||||
support the legacy engine, for example those from the tessdata repository
|
||||
(https://github.com/tesseract-ocr/tessdata).
|
||||
|
||||
For further details, see the release notes in the Tesseract wiki
|
||||
(<https://github.com/tesseract-ocr/tesseract/wiki/ReleaseNotes>).
|
||||
|
||||
|
||||
RESOURCES
|
||||
---------
|
||||
Main web site: <https://github.com/tesseract-ocr> +
|
||||
User forum: <http://groups.google.com/group/tesseract-ocr> +
|
||||
Wiki: <https://github.com/tesseract-ocr/tesseract/wiki> +
|
||||
Information on training: <https://github.com/tesseract-ocr/tesseract/wiki/TrainingTesseract>
|
||||
|
||||
SEE ALSO
|
||||
@ -396,6 +441,9 @@ Pingping Xiu, Pong Eksombatchai (Chantat), Ranjith Unnikrishnan, Raquel
|
||||
Romano, Ray Smith, Rika Antonova, Robert Moss, Samuel Charron, Sheelagh
|
||||
Lloyd, Shobhit Saxena, and Thomas Kielbus.
|
||||
|
||||
For a list of contributors see
|
||||
<https://github.com/tesseract-ocr/tesseract/blob/master/AUTHORS>.
|
||||
|
||||
COPYING
|
||||
-------
|
||||
Licensed under the Apache License, Version 2.0
|
||||
|
||||
@ -1130,6 +1130,15 @@ bool TessBaseAPI::ProcessPagesInternal(const char* filename,
|
||||
buf.assign((std::istreambuf_iterator<char>(std::cin)),
|
||||
(std::istreambuf_iterator<char>()));
|
||||
data = reinterpret_cast<const l_uint8 *>(buf.data());
|
||||
} else {
|
||||
// Check whether the input file can be read.
|
||||
if (FILE* file = fopen(filename, "rb")) {
|
||||
fclose(file);
|
||||
} else {
|
||||
fprintf(stderr, "Error, cannot read input file %s: %s\n",
|
||||
filename, strerror(errno));
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
// Here is our autodetection
|
||||
|
||||
@ -75,6 +75,7 @@ class Trie;
|
||||
class Wordrec;
|
||||
|
||||
typedef int (Dict::*DictFunc)(void* void_dawg_args,
|
||||
const UNICHARSET& unicharset,
|
||||
UNICHAR_ID unichar_id, bool word_end) const;
|
||||
typedef double (Dict::*ProbabilityInContextFunc)(const char* lang,
|
||||
const char* context,
|
||||
|
||||
@ -367,11 +367,15 @@ static void ParseArgs(const int argc, char** argv, const char** lang,
|
||||
*arg_i = i;
|
||||
|
||||
if (*pagesegmode == tesseract::PSM_OSD_ONLY) {
|
||||
// That mode requires osd.traineddata, no other language or script files.
|
||||
// OSD = orientation and script detection.
|
||||
if (*lang != nullptr && strcmp(*lang, "osd")) {
|
||||
fprintf(stderr, "Warning, ignoring -l %s for --psm 0\n", *lang);
|
||||
// If the user explicitly specifies a language (other than osd)
|
||||
// or a script, only orientation can be detected.
|
||||
fprintf(stderr, "Warning, detects only orientation with -l %s\n", *lang);
|
||||
} else {
|
||||
// That mode requires osd.traineddata to detect orientation and script.
|
||||
*lang = "osd";
|
||||
}
|
||||
*lang = "osd";
|
||||
}
|
||||
|
||||
if (*outputbase == nullptr && noocr == false) {
|
||||
@ -530,13 +534,6 @@ int main(int argc, char** argv) {
|
||||
return EXIT_SUCCESS;
|
||||
}
|
||||
|
||||
if (FILE* file = fopen(image, "r")) {
|
||||
fclose(file);
|
||||
} else {
|
||||
fprintf(stderr, "Cannot open input file: %s\n", image);
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
|
||||
FixPageSegMode(&api, pagesegmode);
|
||||
|
||||
if (dpi) {
|
||||
|
||||
@ -36,9 +36,6 @@
|
||||
#include <algorithm>
|
||||
#include <memory>
|
||||
|
||||
const int kMinCharactersToTry = 50;
|
||||
const int kMaxCharactersToTry = 5 * kMinCharactersToTry;
|
||||
|
||||
const float kSizeRatioToReject = 2.0;
|
||||
const int kMinAcceptableBlobHeight = 10;
|
||||
|
||||
@ -278,6 +275,8 @@ int os_detect_blobs(const GenericVector<int>* allowed_scripts,
|
||||
BLOBNBOX_CLIST* blob_list, OSResults* osr,
|
||||
tesseract::Tesseract* tess) {
|
||||
OSResults osr_;
|
||||
int minCharactersToTry = tess->min_characters_to_try;
|
||||
int maxCharactersToTry = 5 * minCharactersToTry;
|
||||
if (osr == nullptr)
|
||||
osr = &osr_;
|
||||
|
||||
@ -286,13 +285,13 @@ int os_detect_blobs(const GenericVector<int>* allowed_scripts,
|
||||
ScriptDetector s(allowed_scripts, osr, tess);
|
||||
|
||||
BLOBNBOX_C_IT filtered_it(blob_list);
|
||||
int real_max = std::min(filtered_it.length(), kMaxCharactersToTry);
|
||||
int real_max = std::min(filtered_it.length(), maxCharactersToTry);
|
||||
// tprintf("Total blobs found = %d\n", blobs_total);
|
||||
// tprintf("Number of blobs post-filtering = %d\n", filtered_it.length());
|
||||
// tprintf("Number of blobs to try = %d\n", real_max);
|
||||
|
||||
// If there are too few characters, skip this page entirely.
|
||||
if (real_max < kMinCharactersToTry / 2) {
|
||||
if (real_max < minCharactersToTry / 2) {
|
||||
tprintf("Too few characters. Skipping this page\n");
|
||||
return 0;
|
||||
}
|
||||
@ -307,7 +306,7 @@ int os_detect_blobs(const GenericVector<int>* allowed_scripts,
|
||||
int num_blobs_evaluated = 0;
|
||||
for (int i = 0; i < real_max; ++i) {
|
||||
if (os_detect_blob(blobs[sequence.GetVal()], &o, &s, osr, tess)
|
||||
&& i > kMinCharactersToTry) {
|
||||
&& i > minCharactersToTry) {
|
||||
break;
|
||||
}
|
||||
++num_blobs_evaluated;
|
||||
|
||||
@ -100,15 +100,15 @@ enum ColorationMode {
|
||||
*
|
||||
*/
|
||||
|
||||
ScrollView* image_win;
|
||||
ParamsEditor* pe;
|
||||
bool stillRunning = false;
|
||||
static ScrollView* image_win;
|
||||
static ParamsEditor* pe;
|
||||
static bool stillRunning = false;
|
||||
|
||||
ScrollView* bln_word_window = nullptr; // baseline norm words
|
||||
static ScrollView* bln_word_window = nullptr; // baseline norm words
|
||||
|
||||
CMD_EVENTS mode = CHANGE_DISP_CMD_EVENT; // selected words op
|
||||
static CMD_EVENTS mode = CHANGE_DISP_CMD_EVENT; // selected words op
|
||||
|
||||
bool recog_done = false; // recog_all_words was called
|
||||
static bool recog_done = false; // recog_all_words was called
|
||||
|
||||
// These variables should remain global, since they are only used for the
|
||||
// debug mode (in which only a single Tesseract thread/instance will exist).
|
||||
|
||||
@ -397,6 +397,9 @@ Tesseract::Tesseract()
|
||||
INT_MEMBER(jpg_quality, 85, "Set JPEG quality level", this->params()),
|
||||
INT_MEMBER(user_defined_dpi, 0, "Specify DPI for input image",
|
||||
this->params()),
|
||||
INT_MEMBER(min_characters_to_try, 50,
|
||||
"Specify minimum characters to try during OSD",
|
||||
this->params()),
|
||||
STRING_MEMBER(unrecognised_char, "|",
|
||||
"Output char for unidentified blobs", this->params()),
|
||||
INT_MEMBER(suspect_level, 99, "Suspect marker level", this->params()),
|
||||
|
||||
@ -1043,6 +1043,8 @@ class Tesseract : public Wordrec {
|
||||
"Create PDF with only one invisible text layer");
|
||||
INT_VAR_H(jpg_quality, 85, "Set JPEG quality level");
|
||||
INT_VAR_H(user_defined_dpi, 0, "Specify DPI for input image");
|
||||
INT_VAR_H(min_characters_to_try, 50,
|
||||
"Specify minimum characters to try during OSD");
|
||||
STRING_VAR_H(unrecognised_char, "|",
|
||||
"Output char for unidentified blobs");
|
||||
INT_VAR_H(suspect_level, 99, "Suspect marker level");
|
||||
|
||||
@ -365,7 +365,7 @@ class GENERIC_2D_ARRAY {
|
||||
}
|
||||
|
||||
// Accumulates the element-wise sums of squares of src into *this.
|
||||
void SumSquares(const GENERIC_2D_ARRAY<T>& src, T decay_factor) {
|
||||
void SumSquares(const GENERIC_2D_ARRAY<T>& src, const T& decay_factor) {
|
||||
T update_factor = 1.0 - decay_factor;
|
||||
int size = num_elements();
|
||||
for (int i = 0; i < size; ++i) {
|
||||
@ -377,7 +377,7 @@ class GENERIC_2D_ARRAY {
|
||||
// Scales each element using the adam algorithm, ie array_[i] by
|
||||
// sqrt(sqsum[i] + epsilon)).
|
||||
void AdamUpdate(const GENERIC_2D_ARRAY<T>& sum,
|
||||
const GENERIC_2D_ARRAY<T>& sqsum, T epsilon) {
|
||||
const GENERIC_2D_ARRAY<T>& sqsum, const T& epsilon) {
|
||||
int size = num_elements();
|
||||
for (int i = 0; i < size; ++i) {
|
||||
array_[i] += sum.array_[i] / (sqrt(sqsum.array_[i]) + epsilon);
|
||||
|
||||
@ -363,10 +363,10 @@ class WERD_RES : public ELIST_LINK {
|
||||
blob_index >= best_choice->length())
|
||||
return nullptr;
|
||||
UNICHAR_ID id = best_choice->unichar_id(blob_index);
|
||||
if (id < 0 || id >= uch_set->size() || id == INVALID_UNICHAR_ID)
|
||||
if (id < 0 || id >= uch_set->size())
|
||||
return nullptr;
|
||||
UNICHAR_ID mirrored = uch_set->get_mirror(id);
|
||||
if (in_rtl_context && mirrored > 0 && mirrored != INVALID_UNICHAR_ID)
|
||||
if (in_rtl_context && mirrored > 0)
|
||||
id = mirrored;
|
||||
return uch_set->id_to_unichar_ext(id);
|
||||
}
|
||||
@ -375,7 +375,7 @@ class WERD_RES : public ELIST_LINK {
|
||||
if (blob_index < 0 || blob_index >= raw_choice->length())
|
||||
return nullptr;
|
||||
UNICHAR_ID id = raw_choice->unichar_id(blob_index);
|
||||
if (id < 0 || id >= uch_set->size() || id == INVALID_UNICHAR_ID)
|
||||
if (id < 0 || id >= uch_set->size())
|
||||
return nullptr;
|
||||
return uch_set->id_to_unichar(id);
|
||||
}
|
||||
|
||||
@ -21,7 +21,7 @@
|
||||
#define RECT_H
|
||||
|
||||
#include <algorithm> // for std::max, std::min
|
||||
#include <cmath> // for ceil, floor
|
||||
#include <cmath> // for std::ceil, std::floor
|
||||
#include <cstdint> // for INT16_MAX
|
||||
#include <cstdio> // for FILE
|
||||
#include "platform.h" // for DLLSYM
|
||||
@ -162,29 +162,33 @@ class DLLSYM TBOX { // bounding box
|
||||
|
||||
void move( // move box
|
||||
const FCOORD vec) { // by float vector
|
||||
bot_left.set_x ((int16_t) floor (bot_left.x () + vec.x ()));
|
||||
bot_left.set_x(static_cast<int16_t>(std::floor(bot_left.x() + vec.x())));
|
||||
// round left
|
||||
bot_left.set_y ((int16_t) floor (bot_left.y () + vec.y ()));
|
||||
bot_left.set_y(static_cast<int16_t>(std::floor(bot_left.y() + vec.y())));
|
||||
// round down
|
||||
top_right.set_x ((int16_t) ceil (top_right.x () + vec.x ()));
|
||||
top_right.set_x(static_cast<int16_t>(std::ceil(top_right.x() + vec.x())));
|
||||
// round right
|
||||
top_right.set_y ((int16_t) ceil (top_right.y () + vec.y ()));
|
||||
top_right.set_y(static_cast<int16_t>(std::ceil(top_right.y() + vec.y())));
|
||||
// round up
|
||||
}
|
||||
|
||||
void scale( // scale box
|
||||
const float f) { // by multiplier
|
||||
bot_left.set_x ((int16_t) floor (bot_left.x () * f)); // round left
|
||||
bot_left.set_y ((int16_t) floor (bot_left.y () * f)); // round down
|
||||
top_right.set_x ((int16_t) ceil (top_right.x () * f)); // round right
|
||||
top_right.set_y ((int16_t) ceil (top_right.y () * f)); // round up
|
||||
// round left
|
||||
bot_left.set_x(static_cast<int16_t>(std::floor(bot_left.x() * f)));
|
||||
// round down
|
||||
bot_left.set_y(static_cast<int16_t>(std::floor(bot_left.y() * f)));
|
||||
// round right
|
||||
top_right.set_x(static_cast<int16_t>(std::ceil(top_right.x() * f)));
|
||||
// round up
|
||||
top_right.set_y(static_cast<int16_t>(std::ceil(top_right.y() * f)));
|
||||
}
|
||||
void scale( // scale box
|
||||
const FCOORD vec) { // by float vector
|
||||
bot_left.set_x ((int16_t) floor (bot_left.x () * vec.x ()));
|
||||
bot_left.set_y ((int16_t) floor (bot_left.y () * vec.y ()));
|
||||
top_right.set_x ((int16_t) ceil (top_right.x () * vec.x ()));
|
||||
top_right.set_y ((int16_t) ceil (top_right.y () * vec.y ()));
|
||||
bot_left.set_x(static_cast<int16_t>(std::floor(bot_left.x() * vec.x())));
|
||||
bot_left.set_y(static_cast<int16_t>(std::floor(bot_left.y() * vec.y())));
|
||||
top_right.set_x(static_cast<int16_t>(std::ceil(top_right.x() * vec.x())));
|
||||
top_right.set_y(static_cast<int16_t>(std::ceil(top_right.y() * vec.y())));
|
||||
}
|
||||
|
||||
// rotate doesn't enlarge the box - it just rotates the bottom-left
|
||||
@ -314,8 +318,10 @@ class DLLSYM TBOX { // bounding box
|
||||
inline TBOX::TBOX( // constructor
|
||||
const FCOORD pt // floating centre
|
||||
) {
|
||||
bot_left = ICOORD ((int16_t) floor (pt.x ()), (int16_t) floor (pt.y ()));
|
||||
top_right = ICOORD ((int16_t) ceil (pt.x ()), (int16_t) ceil (pt.y ()));
|
||||
bot_left = ICOORD(static_cast<int16_t>(std::floor(pt.x())),
|
||||
static_cast<int16_t>(std::floor(pt.y())));
|
||||
top_right = ICOORD(static_cast<int16_t>(std::ceil(pt.x())),
|
||||
static_cast<int16_t>(std::ceil(pt.y())));
|
||||
}
|
||||
|
||||
|
||||
|
||||
@ -39,7 +39,7 @@ class GenericVector {
|
||||
GenericVector() {
|
||||
init(kDefaultVectorSize);
|
||||
}
|
||||
GenericVector(int size, T init_val) {
|
||||
GenericVector(int size, const T& init_val) {
|
||||
init(size);
|
||||
init_to_size(size, init_val);
|
||||
}
|
||||
@ -60,7 +60,7 @@ class GenericVector {
|
||||
void double_the_size();
|
||||
|
||||
// Resizes to size and sets all values to t.
|
||||
void init_to_size(int size, T t);
|
||||
void init_to_size(int size, const T& t);
|
||||
// Resizes to size without any initialization.
|
||||
void resize_no_init(int size) {
|
||||
reserve(size);
|
||||
@ -101,31 +101,31 @@ class GenericVector {
|
||||
// Return the index of the T object.
|
||||
// This method NEEDS a compare_callback to be passed to
|
||||
// set_compare_callback.
|
||||
int get_index(T object) const;
|
||||
int get_index(const T& object) const;
|
||||
|
||||
// Return true if T is in the array
|
||||
bool contains(T object) const;
|
||||
bool contains(const T& object) const;
|
||||
|
||||
// Return true if the index is valid
|
||||
T contains_index(int index) const;
|
||||
|
||||
// Push an element in the end of the array
|
||||
int push_back(T object);
|
||||
void operator+=(T t);
|
||||
void operator+=(const T& t);
|
||||
|
||||
// Push an element in the end of the array if the same
|
||||
// element is not already contained in the array.
|
||||
int push_back_new(T object);
|
||||
int push_back_new(const T& object);
|
||||
|
||||
// Push an element in the front of the array
|
||||
// Note: This function is O(n)
|
||||
int push_front(T object);
|
||||
int push_front(const T& object);
|
||||
|
||||
// Set the value at the given index
|
||||
void set(T t, int index);
|
||||
void set(const T& t, int index);
|
||||
|
||||
// Insert t at the given index, push other elements to the right.
|
||||
void insert(T t, int index);
|
||||
void insert(const T& t, int index);
|
||||
|
||||
// Removes an element at the given index and
|
||||
// shifts the remaining elements to the left.
|
||||
@ -705,7 +705,7 @@ void GenericVector<T>::double_the_size() {
|
||||
|
||||
// Resizes to size and sets all values to t.
|
||||
template <typename T>
|
||||
void GenericVector<T>::init_to_size(int size, T t) {
|
||||
void GenericVector<T>::init_to_size(int size, const T& t) {
|
||||
reserve(size);
|
||||
size_used_ = size;
|
||||
for (int i = 0; i < size; ++i)
|
||||
@ -740,7 +740,7 @@ T GenericVector<T>::pop_back() {
|
||||
|
||||
// Return the object from an index.
|
||||
template <typename T>
|
||||
void GenericVector<T>::set(T t, int index) {
|
||||
void GenericVector<T>::set(const T& t, int index) {
|
||||
assert(index >= 0 && index < size_used_);
|
||||
data_[index] = t;
|
||||
}
|
||||
@ -749,7 +749,7 @@ void GenericVector<T>::set(T t, int index) {
|
||||
// space for the new elements and inserts the given element
|
||||
// at the specified index.
|
||||
template <typename T>
|
||||
void GenericVector<T>::insert(T t, int index) {
|
||||
void GenericVector<T>::insert(const T& t, int index) {
|
||||
assert(index >= 0 && index <= size_used_);
|
||||
if (size_reserved_ == size_used_)
|
||||
double_the_size();
|
||||
@ -779,7 +779,7 @@ T GenericVector<T>::contains_index(int index) const {
|
||||
|
||||
// Return the index of the T object.
|
||||
template <typename T>
|
||||
int GenericVector<T>::get_index(T object) const {
|
||||
int GenericVector<T>::get_index(const T& object) const {
|
||||
for (int i = 0; i < size_used_; ++i) {
|
||||
assert(compare_cb_ != nullptr);
|
||||
if (compare_cb_->Run(object, data_[i]))
|
||||
@ -790,7 +790,7 @@ int GenericVector<T>::get_index(T object) const {
|
||||
|
||||
// Return true if T is in the array
|
||||
template <typename T>
|
||||
bool GenericVector<T>::contains(T object) const {
|
||||
bool GenericVector<T>::contains(const T& object) const {
|
||||
return get_index(object) != -1;
|
||||
}
|
||||
|
||||
@ -806,7 +806,7 @@ int GenericVector<T>::push_back(T object) {
|
||||
}
|
||||
|
||||
template <typename T>
|
||||
int GenericVector<T>::push_back_new(T object) {
|
||||
int GenericVector<T>::push_back_new(const T& object) {
|
||||
int index = get_index(object);
|
||||
if (index >= 0)
|
||||
return index;
|
||||
@ -815,7 +815,7 @@ int GenericVector<T>::push_back_new(T object) {
|
||||
|
||||
// Add an element in the array (front)
|
||||
template <typename T>
|
||||
int GenericVector<T>::push_front(T object) {
|
||||
int GenericVector<T>::push_front(const T& object) {
|
||||
if (size_used_ == size_reserved_)
|
||||
double_the_size();
|
||||
for (int i = size_used_; i > 0; --i)
|
||||
@ -826,7 +826,7 @@ int GenericVector<T>::push_front(T object) {
|
||||
}
|
||||
|
||||
template <typename T>
|
||||
void GenericVector<T>::operator+=(T t) {
|
||||
void GenericVector<T>::operator+=(const T& t) {
|
||||
push_back(t);
|
||||
}
|
||||
|
||||
@ -866,15 +866,14 @@ void GenericVector<T>::set_compare_callback(
|
||||
// Clear the array, calling the callback function if any.
|
||||
template <typename T>
|
||||
void GenericVector<T>::clear() {
|
||||
if (size_reserved_ > 0) {
|
||||
if (clear_cb_ != nullptr)
|
||||
for (int i = 0; i < size_used_; ++i)
|
||||
clear_cb_->Run(data_[i]);
|
||||
delete[] data_;
|
||||
data_ = nullptr;
|
||||
size_used_ = 0;
|
||||
size_reserved_ = 0;
|
||||
if (size_reserved_ > 0 && clear_cb_ != nullptr) {
|
||||
for (int i = 0; i < size_used_; ++i)
|
||||
clear_cb_->Run(data_[i]);
|
||||
}
|
||||
delete[] data_;
|
||||
data_ = nullptr;
|
||||
size_used_ = 0;
|
||||
size_reserved_ = 0;
|
||||
delete clear_cb_;
|
||||
clear_cb_ = nullptr;
|
||||
delete compare_cb_;
|
||||
|
||||
@ -20,7 +20,7 @@
|
||||
-----------------------------------------------------------------------------*/
|
||||
|
||||
#include <algorithm>
|
||||
#include <cmath>
|
||||
#include <cmath> // for std::floor
|
||||
#include <cstdio>
|
||||
#include <cassert>
|
||||
|
||||
@ -117,7 +117,7 @@ FILL_SPEC;
|
||||
#define CircularIncrement(i,r) (((i) < (r) - 1)?((i)++):((i) = 0))
|
||||
|
||||
/** macro for mapping floats to ints without bounds checking */
|
||||
#define MapParam(P,O,N) (floor (((P) + (O)) * (N)))
|
||||
#define MapParam(P,O,N) (std::floor(((P) + (O)) * (N)))
|
||||
|
||||
/*---------------------------------------------------------------------------
|
||||
Private Function Prototypes
|
||||
@ -1205,11 +1205,11 @@ void FillPPCircularBits(uint32_t ParamTable[NUM_PP_BUCKETS][WERDS_PER_PP_VECTOR]
|
||||
if (Spread > 0.5)
|
||||
Spread = 0.5;
|
||||
|
||||
FirstBucket = (int) floor ((Center - Spread) * NUM_PP_BUCKETS);
|
||||
FirstBucket = static_cast<int>(std::floor((Center - Spread) * NUM_PP_BUCKETS));
|
||||
if (FirstBucket < 0)
|
||||
FirstBucket += NUM_PP_BUCKETS;
|
||||
|
||||
LastBucket = (int) floor ((Center + Spread) * NUM_PP_BUCKETS);
|
||||
LastBucket = static_cast<int>(std::floor((Center + Spread) * NUM_PP_BUCKETS));
|
||||
if (LastBucket >= NUM_PP_BUCKETS)
|
||||
LastBucket -= NUM_PP_BUCKETS;
|
||||
if (debug) tprintf("Circular fill from %d to %d", FirstBucket, LastBucket);
|
||||
@ -1243,11 +1243,11 @@ void FillPPLinearBits(uint32_t ParamTable[NUM_PP_BUCKETS][WERDS_PER_PP_VECTOR],
|
||||
int Bit, float Center, float Spread, bool debug) {
|
||||
int i, FirstBucket, LastBucket;
|
||||
|
||||
FirstBucket = (int) floor ((Center - Spread) * NUM_PP_BUCKETS);
|
||||
FirstBucket = static_cast<int>(std::floor((Center - Spread) * NUM_PP_BUCKETS));
|
||||
if (FirstBucket < 0)
|
||||
FirstBucket = 0;
|
||||
|
||||
LastBucket = (int) floor ((Center + Spread) * NUM_PP_BUCKETS);
|
||||
LastBucket = static_cast<int>(std::floor((Center + Spread) * NUM_PP_BUCKETS));
|
||||
if (LastBucket >= NUM_PP_BUCKETS)
|
||||
LastBucket = NUM_PP_BUCKETS - 1;
|
||||
|
||||
@ -1736,7 +1736,7 @@ int TruncateParam(float Param, int Min, int Max, char *Id) {
|
||||
Id, Param, Max);
|
||||
Param = Max;
|
||||
}
|
||||
return static_cast<int>(floor(Param));
|
||||
return static_cast<int>(std::floor(Param));
|
||||
} /* TruncateParam */
|
||||
|
||||
|
||||
|
||||
@ -32,6 +32,11 @@ Dict::Dict(CCUtil *ccutil)
|
||||
probability_in_context_(&tesseract::Dict::def_probability_in_context),
|
||||
params_model_classify_(nullptr),
|
||||
ccutil_(ccutil),
|
||||
wildcard_unichar_id_(INVALID_UNICHAR_ID),
|
||||
apostrophe_unichar_id_(INVALID_UNICHAR_ID),
|
||||
question_unichar_id_(INVALID_UNICHAR_ID),
|
||||
slash_unichar_id_(INVALID_UNICHAR_ID),
|
||||
hyphen_unichar_id_(INVALID_UNICHAR_ID),
|
||||
STRING_MEMBER(user_words_file, "", "A filename of user-provided words.",
|
||||
getCCUtil()->params()),
|
||||
STRING_INIT_MEMBER(user_words_suffix, "",
|
||||
@ -167,7 +172,6 @@ Dict::Dict(CCUtil *ccutil)
|
||||
go_deeper_fxn_ = nullptr;
|
||||
hyphen_word_ = nullptr;
|
||||
last_word_on_line_ = false;
|
||||
hyphen_unichar_id_ = INVALID_UNICHAR_ID;
|
||||
document_words_ = nullptr;
|
||||
dawg_cache_ = nullptr;
|
||||
dawg_cache_is_ours_ = false;
|
||||
@ -361,10 +365,13 @@ void Dict::End() {
|
||||
// according to at least one of the dawgs in the dawgs_ vector.
|
||||
// See more extensive comments in dict.h where this function is declared.
|
||||
int Dict::def_letter_is_okay(void* void_dawg_args,
|
||||
const UNICHARSET& unicharset,
|
||||
UNICHAR_ID unichar_id,
|
||||
bool word_end) const {
|
||||
DawgArgs *dawg_args = static_cast<DawgArgs *>(void_dawg_args);
|
||||
|
||||
ASSERT_HOST(unicharset.contains_unichar_id(unichar_id));
|
||||
|
||||
if (dawg_debug_level >= 3) {
|
||||
tprintf("def_letter_is_okay: current unichar=%s word_end=%d"
|
||||
" num active dawgs=%d\n",
|
||||
@ -410,7 +417,7 @@ int Dict::def_letter_is_okay(void* void_dawg_args,
|
||||
for (int s = 0; s < slist.length(); ++s) {
|
||||
int sdawg_index = slist[s];
|
||||
const Dawg *sdawg = dawgs_[sdawg_index];
|
||||
UNICHAR_ID ch = char_for_dawg(unichar_id, sdawg);
|
||||
UNICHAR_ID ch = char_for_dawg(unicharset, unichar_id, sdawg);
|
||||
EDGE_REF dawg_edge = sdawg->edge_char_of(0, ch, word_end);
|
||||
if (dawg_edge != NO_EDGE) {
|
||||
if (dawg_debug_level >=3) {
|
||||
@ -477,7 +484,8 @@ int Dict::def_letter_is_okay(void* void_dawg_args,
|
||||
// Find the edge out of the node for the unichar_id.
|
||||
NODE_REF node = GetStartingNode(dawg, pos.dawg_ref);
|
||||
EDGE_REF edge = (node == NO_EDGE) ? NO_EDGE
|
||||
: dawg->edge_char_of(node, char_for_dawg(unichar_id, dawg), word_end);
|
||||
: dawg->edge_char_of(node, char_for_dawg(unicharset, unichar_id, dawg),
|
||||
word_end);
|
||||
|
||||
if (dawg_debug_level >= 3) {
|
||||
tprintf("Active dawg: [%d, " REFFORMAT "] edge=" REFFORMAT "\n",
|
||||
@ -759,7 +767,8 @@ int Dict::valid_word(const WERD_CHOICE &word, bool numbers_ok) const {
|
||||
int last_index = word_ptr->length() - 1;
|
||||
// Call letter_is_okay for each letter in the word.
|
||||
for (int i = hyphen_base_size(); i <= last_index; ++i) {
|
||||
if (!((this->*letter_is_okay_)(&dawg_args, word_ptr->unichar_id(i),
|
||||
if (!((this->*letter_is_okay_)(&dawg_args, *word_ptr->unicharset(),
|
||||
word_ptr->unichar_id(i),
|
||||
i == last_index))) break;
|
||||
// Swap active_dawgs, constraints with the corresponding updated vector.
|
||||
if (dawg_args.updated_dawgs == &(active_dawgs[1])) {
|
||||
|
||||
@ -351,15 +351,17 @@ class Dict {
|
||||
*/
|
||||
|
||||
//
|
||||
int def_letter_is_okay(void* void_dawg_args,
|
||||
int def_letter_is_okay(void* void_dawg_args, const UNICHARSET& unicharset,
|
||||
UNICHAR_ID unichar_id, bool word_end) const;
|
||||
|
||||
int (Dict::*letter_is_okay_)(void* void_dawg_args,
|
||||
const UNICHARSET& unicharset,
|
||||
UNICHAR_ID unichar_id, bool word_end) const;
|
||||
/// Calls letter_is_okay_ member function.
|
||||
int LetterIsOkay(void* void_dawg_args,
|
||||
int LetterIsOkay(void* void_dawg_args, const UNICHARSET& unicharset,
|
||||
UNICHAR_ID unichar_id, bool word_end) const {
|
||||
return (this->*letter_is_okay_)(void_dawg_args, unichar_id, word_end);
|
||||
return (this->*letter_is_okay_)(void_dawg_args,
|
||||
unicharset, unichar_id, word_end);
|
||||
}
|
||||
|
||||
|
||||
@ -428,11 +430,12 @@ class Dict {
|
||||
// Given a unichar from a string and a given dawg, return the unichar
|
||||
// we should use to match in that dawg type. (for example, in the number
|
||||
// dawg, all numbers are transformed to kPatternUnicharId).
|
||||
inline UNICHAR_ID char_for_dawg(UNICHAR_ID ch, const Dawg *dawg) const {
|
||||
UNICHAR_ID char_for_dawg(const UNICHARSET& unicharset, UNICHAR_ID ch,
|
||||
const Dawg *dawg) const {
|
||||
if (!dawg) return ch;
|
||||
switch (dawg->type()) {
|
||||
case DAWG_TYPE_NUMBER:
|
||||
return getUnicharset().get_isdigit(ch) ? Dawg::kPatternUnicharID : ch;
|
||||
return unicharset.get_isdigit(ch) ? Dawg::kPatternUnicharID : ch;
|
||||
default:
|
||||
return ch;
|
||||
}
|
||||
|
||||
@ -88,7 +88,7 @@ void Dict::go_deeper_dawg_fxn(
|
||||
++num_unigrams;
|
||||
word->append_unichar_id(uch_id, 1, 0.0, 0.0);
|
||||
unigrams_ok = (this->*letter_is_okay_)(
|
||||
&unigram_dawg_args,
|
||||
&unigram_dawg_args, *word->unicharset(),
|
||||
word->unichar_id(word_index+num_unigrams-1),
|
||||
word_ending && i == encoding.size() - 1);
|
||||
(*unigram_dawg_args.active_dawgs) = *(unigram_dawg_args.updated_dawgs);
|
||||
@ -111,7 +111,8 @@ void Dict::go_deeper_dawg_fxn(
|
||||
// Check which dawgs from the dawgs_ vector contain the word
|
||||
// up to and including the current unichar.
|
||||
if (checked_unigrams || (this->*letter_is_okay_)(
|
||||
more_args, word->unichar_id(word_index), word_ending)) {
|
||||
more_args, *word->unicharset(), word->unichar_id(word_index),
|
||||
word_ending)) {
|
||||
// Add a new word choice
|
||||
if (word_ending) {
|
||||
if (dawg_debug_level) {
|
||||
|
||||
@ -771,7 +771,8 @@ void RecodeBeamSearch::ContinueDawg(int code, int unichar_id, float cert,
|
||||
return; // Can't continue if not a dict word.
|
||||
}
|
||||
PermuterType permuter = static_cast<PermuterType>(
|
||||
dict_->def_letter_is_okay(&dawg_args, unichar_id, false));
|
||||
dict_->def_letter_is_okay(&dawg_args,
|
||||
dict_->getUnicharset(), unichar_id, false));
|
||||
if (permuter != NO_PERM) {
|
||||
PushHeapIfBetter(kBeamWidths[0], code, unichar_id, permuter, false,
|
||||
word_start, dawg_args.valid_end, false, cert, prev,
|
||||
|
||||
@ -72,7 +72,7 @@ int main(int argc, char **argv) {
|
||||
tesseract::TessdataManager tm;
|
||||
if (argc > 1 && (!strcmp(argv[1], "-v") || !strcmp(argv[1], "--version"))) {
|
||||
printf("%s\n", tesseract::TessBaseAPI::Version());
|
||||
return 0;
|
||||
return EXIT_SUCCESS;
|
||||
} else if (argc == 2) {
|
||||
printf("Combining tessdata files\n");
|
||||
STRING lang = argv[1];
|
||||
@ -92,16 +92,22 @@ int main(int argc, char **argv) {
|
||||
// Initialize TessdataManager with the data in the given traineddata file.
|
||||
if (!tm.Init(argv[2])) {
|
||||
tprintf("Failed to read %s\n", argv[2]);
|
||||
exit(1);
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
printf("Extracting tessdata components from %s\n", argv[2]);
|
||||
if (strcmp(argv[1], "-e") == 0) {
|
||||
for (i = 3; i < argc; ++i) {
|
||||
errno = 0;
|
||||
if (tm.ExtractToFile(argv[i])) {
|
||||
printf("Wrote %s\n", argv[i]);
|
||||
} else {
|
||||
} else if (errno == 0) {
|
||||
printf("Not extracting %s, since this component"
|
||||
" is not present\n", argv[i]);
|
||||
return EXIT_FAILURE;
|
||||
} else {
|
||||
printf("Error, could not extract %s: %s\n",
|
||||
argv[i], strerror(errno));
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
}
|
||||
} else { // extract all the components
|
||||
@ -111,8 +117,13 @@ int main(int argc, char **argv) {
|
||||
if (*last != '.')
|
||||
filename += '.';
|
||||
filename += tesseract::kTessdataFileSuffixes[i];
|
||||
errno = 0;
|
||||
if (tm.ExtractToFile(filename.string())) {
|
||||
printf("Wrote %s\n", filename.string());
|
||||
} else if (errno != 0) {
|
||||
printf("Error, could not extract %s: %s\n",
|
||||
filename.string(), strerror(errno));
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -124,7 +135,7 @@ int main(int argc, char **argv) {
|
||||
if (rename(new_traineddata_filename, traineddata_filename.string()) != 0) {
|
||||
tprintf("Failed to create a temporary file %s\n",
|
||||
traineddata_filename.string());
|
||||
exit(1);
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
|
||||
// Initialize TessdataManager with the data in the given traineddata file.
|
||||
@ -135,17 +146,17 @@ int main(int argc, char **argv) {
|
||||
} else if (argc == 3 && strcmp(argv[1], "-c") == 0) {
|
||||
if (!tm.Init(argv[2])) {
|
||||
tprintf("Failed to read %s\n", argv[2]);
|
||||
exit(1);
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
tesseract::TFile fp;
|
||||
if (!tm.GetComponent(tesseract::TESSDATA_LSTM, &fp)) {
|
||||
tprintf("No LSTM Component found in %s!\n", argv[2]);
|
||||
exit(1);
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
tesseract::LSTMRecognizer recognizer;
|
||||
if (!recognizer.DeSerialize(&tm, &fp)) {
|
||||
tprintf("Failed to deserialize LSTM in %s!\n", argv[2]);
|
||||
exit(1);
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
recognizer.ConvertToInt();
|
||||
GenericVector<char> lstm_data;
|
||||
@ -155,7 +166,7 @@ int main(int argc, char **argv) {
|
||||
lstm_data.size());
|
||||
if (!tm.SaveFile(argv[2], nullptr)) {
|
||||
tprintf("Failed to write modified traineddata:%s!\n", argv[2]);
|
||||
exit(1);
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
} else if (argc == 3 && strcmp(argv[1], "-d") == 0) {
|
||||
// Initialize TessdataManager with the data in the given traineddata file.
|
||||
@ -186,4 +197,5 @@ int main(int argc, char **argv) {
|
||||
return 1;
|
||||
}
|
||||
tm.Directory();
|
||||
return EXIT_SUCCESS;
|
||||
}
|
||||
|
||||
@ -73,22 +73,27 @@ const int kNumPagesPerBatch = 100;
|
||||
int main(int argc, char **argv) {
|
||||
tesseract::CheckSharedLibraryVersion();
|
||||
ParseArguments(&argc, &argv);
|
||||
// Purify the model name in case it is based on the network string.
|
||||
if (FLAGS_model_output.empty()) {
|
||||
tprintf("Must provide a --model_output!\n");
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
if (FLAGS_traineddata.empty()) {
|
||||
tprintf("Must provide a --traineddata see training wiki\n");
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
STRING model_output = FLAGS_model_output.c_str();
|
||||
for (int i = 0; i < model_output.length(); ++i) {
|
||||
if (model_output[i] == '[' || model_output[i] == ']')
|
||||
model_output[i] = '-';
|
||||
if (model_output[i] == '(' || model_output[i] == ')')
|
||||
model_output[i] = '_';
|
||||
|
||||
// Check write permissions.
|
||||
STRING test_file = FLAGS_model_output.c_str();
|
||||
test_file += "_wtest";
|
||||
FILE* f = fopen(test_file.c_str(), "wb");
|
||||
if (f != nullptr) {
|
||||
fclose(f);
|
||||
remove(test_file.c_str());
|
||||
} else {
|
||||
tprintf("Error, model output cannot be written: %s\n", strerror(errno));
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
|
||||
// Setup the trainer.
|
||||
STRING checkpoint_file = FLAGS_model_output.c_str();
|
||||
checkpoint_file += "_checkpoint";
|
||||
@ -105,7 +110,7 @@ int main(int argc, char **argv) {
|
||||
if (!trainer.TryLoadingCheckpoint(FLAGS_continue_from.c_str(), nullptr)) {
|
||||
tprintf("Failed to read continue from: %s\n",
|
||||
FLAGS_continue_from.c_str());
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
if (FLAGS_debug_network) {
|
||||
trainer.DebugNetwork();
|
||||
@ -116,20 +121,20 @@ int main(int argc, char **argv) {
|
||||
FLAGS_model_output.c_str());
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
return EXIT_SUCCESS;
|
||||
}
|
||||
|
||||
// Get the list of files to process.
|
||||
if (FLAGS_train_listfile.empty()) {
|
||||
tprintf("Must supply a list of training filenames! --train_listfile\n");
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
GenericVector<STRING> filenames;
|
||||
if (!tesseract::LoadFileLinesToStrings(FLAGS_train_listfile.c_str(),
|
||||
&filenames)) {
|
||||
tprintf("Failed to load list of training filenames from %s\n",
|
||||
FLAGS_train_listfile.c_str());
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
|
||||
// Checkpoints always take priority if they are available.
|
||||
@ -145,7 +150,7 @@ int main(int argc, char **argv) {
|
||||
? FLAGS_continue_from.c_str()
|
||||
: FLAGS_old_traineddata.c_str())) {
|
||||
tprintf("Failed to continue from: %s\n", FLAGS_continue_from.c_str());
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
tprintf("Continuing from %s\n", FLAGS_continue_from.c_str());
|
||||
trainer.InitIterations();
|
||||
@ -155,7 +160,7 @@ int main(int argc, char **argv) {
|
||||
tprintf("Appending a new network to an old one!!");
|
||||
if (FLAGS_continue_from.empty()) {
|
||||
tprintf("Must set --continue_from for appending!\n");
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
}
|
||||
// We are initializing from scratch.
|
||||
@ -165,7 +170,7 @@ int main(int argc, char **argv) {
|
||||
FLAGS_adam_beta)) {
|
||||
tprintf("Failed to create network from spec: %s\n",
|
||||
FLAGS_net_spec.c_str());
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
trainer.set_perfect_delay(FLAGS_perfect_sample_delay);
|
||||
}
|
||||
@ -176,7 +181,7 @@ int main(int argc, char **argv) {
|
||||
: tesseract::CS_ROUND_ROBIN,
|
||||
FLAGS_randomly_rotate)) {
|
||||
tprintf("Load of images failed!!\n");
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
|
||||
tesseract::LSTMTester tester(static_cast<int64_t>(FLAGS_max_image_MB) *
|
||||
@ -186,7 +191,7 @@ int main(int argc, char **argv) {
|
||||
if (!tester.LoadAllEvalData(FLAGS_eval_listfile.c_str())) {
|
||||
tprintf("Failed to load eval data from: %s\n",
|
||||
FLAGS_eval_listfile.c_str());
|
||||
return 1;
|
||||
return EXIT_FAILURE;
|
||||
}
|
||||
tester_callback =
|
||||
NewPermanentTessCallback(&tester, &tesseract::LSTMTester::RunEvalAsync);
|
||||
@ -208,5 +213,5 @@ int main(int argc, char **argv) {
|
||||
FLAGS_max_iterations == 0));
|
||||
delete tester_callback;
|
||||
tprintf("Finished! Error rate = %g\n", trainer.best_error_rate());
|
||||
return 0;
|
||||
return EXIT_SUCCESS;
|
||||
} /* main */
|
||||
|
||||
@ -186,7 +186,11 @@ parse_flags() {
|
||||
|
||||
# Location where intermediate files will be created.
|
||||
TIMESTAMP=`date +%Y-%m-%d`
|
||||
if [ "$(uname)" == "Darwin" ];then
|
||||
TMP_DIR=$(mktemp -d -t ${LANG_CODE}-${TIMESTAMP}.XXX )
|
||||
else
|
||||
TMP_DIR=$(mktemp -d --tmpdir ${LANG_CODE}-${TIMESTAMP}.XXX )
|
||||
fi
|
||||
TRAINING_DIR=${TMP_DIR}
|
||||
# Location of log file for the whole run.
|
||||
LOG_FILE=${TRAINING_DIR}/tesstrain.log
|
||||
|
||||
@ -89,7 +89,6 @@ int Wordrec::angle_change(EDGEPT *point1, EDGEPT *point2, EDGEPT *point3) {
|
||||
VECTOR vector2;
|
||||
|
||||
int angle;
|
||||
float length;
|
||||
|
||||
/* Compute angle */
|
||||
vector1.x = point2->pos.x - point1->pos.x;
|
||||
@ -97,7 +96,7 @@ int Wordrec::angle_change(EDGEPT *point1, EDGEPT *point2, EDGEPT *point3) {
|
||||
vector2.x = point3->pos.x - point2->pos.x;
|
||||
vector2.y = point3->pos.y - point2->pos.y;
|
||||
/* Use cross product */
|
||||
length = (float)sqrt((float)LENGTH(vector1) * LENGTH(vector2));
|
||||
float length = std::sqrt(static_cast<float>(LENGTH(vector1)) * LENGTH(vector2));
|
||||
if ((int) length == 0)
|
||||
return (0);
|
||||
angle = static_cast<int>(floor(asin(CROSS (vector1, vector2) /
|
||||
|
||||
@ -853,7 +853,7 @@ LanguageModelDawgInfo *LanguageModel::GenerateDawgInfo(
|
||||
if (language_model_debug_level > 2)
|
||||
tprintf("Test Letter OK for unichar %d, normed %d\n",
|
||||
b.unichar_id(), normed_ids[i]);
|
||||
dict_->LetterIsOkay(&dawg_args_, normed_ids[i],
|
||||
dict_->LetterIsOkay(&dawg_args_, dict_->getUnicharset(), normed_ids[i],
|
||||
word_end && i == normed_ids.size() - 1);
|
||||
if (dawg_args_.permuter == NO_PERM) {
|
||||
break;
|
||||
|
||||
@ -1,3 +1,2 @@
|
||||
tessedit_create_hocr 1
|
||||
tessedit_pageseg_mode 1
|
||||
hocr_font_info 0
|
||||
|
||||
@ -1,2 +1 @@
|
||||
tessedit_create_pdf 1
|
||||
tessedit_pageseg_mode 1
|
||||
|
||||
@ -1,2 +1 @@
|
||||
tessedit_create_tsv 1
|
||||
tessedit_pageseg_mode 1
|
||||
|
||||
@ -1,2 +1 @@
|
||||
tessedit_write_unlv 1
|
||||
tessedit_pageseg_mode 6
|
||||
|
||||
Loading…
Reference in New Issue
Block a user