mirror of
https://github.com/opencv/opencv.git
synced 2024-12-12 23:49:36 +08:00
292 lines
12 KiB
TeX
292 lines
12 KiB
TeX
\section{Clustering}
|
|
|
|
\ifCPy
|
|
|
|
\cvCPyFunc{KMeans2}
|
|
Splits set of vectors by a given number of clusters.
|
|
|
|
\cvdefC{int cvKMeans2(const CvArr* samples, int nclusters,\par
|
|
CvArr* labels, CvTermCriteria termcrit,\par
|
|
int attempts=1, CvRNG* rng=0, \par
|
|
int flags=0, CvArr* centers=0,\par
|
|
double* compactness=0);}
|
|
\cvdefPy{KMeans2(samples,nclusters,labels,termcrit)-> None}
|
|
|
|
\begin{description}
|
|
\cvarg{samples}{Floating-point matrix of input samples, one row per sample}
|
|
\cvarg{nclusters}{Number of clusters to split the set by}
|
|
\cvarg{labels}{Output integer vector storing cluster indices for every sample}
|
|
\cvarg{termcrit}{Specifies maximum number of iterations and/or accuracy (distance the centers can move by between subsequent iterations)}
|
|
\ifC
|
|
\cvarg{attempts}{How many times the algorithm is executed using different initial labelings. The algorithm returns labels that yield the best compactness (see the last function parameter)}
|
|
\cvarg{rng}{Optional external random number generator; can be used to fully control the function behaviour}
|
|
\cvarg{flags}{Can be 0 or \texttt{CV\_KMEANS\_USE\_INITIAL\_LABELS}. The latter
|
|
value means that during the first (and possibly the only) attempt, the
|
|
function uses the user-supplied labels as the initial approximation
|
|
instead of generating random labels. For the second and further attempts,
|
|
the function will use randomly generated labels in any case}
|
|
\cvarg{centers}{The optional output array of the cluster centers}
|
|
\cvarg{compactness}{The optional output parameter, which is computed as
|
|
$\sum_i ||\texttt{samples}_i - \texttt{centers}_{\texttt{labels}_i}||^2$
|
|
after every attempt; the best (minimum) value is chosen and the
|
|
corresponding labels are returned by the function. Basically, the
|
|
user can use only the core of the function, set the number of
|
|
attempts to 1, initialize labels each time using a custom algorithm
|
|
(\texttt{flags=CV\_KMEAN\_USE\_INITIAL\_LABELS}) and, based on the output compactness
|
|
or any other criteria, choose the best clustering.}
|
|
\fi
|
|
\end{description}
|
|
|
|
The function \texttt{cvKMeans2} implements a k-means algorithm that finds the
|
|
centers of \texttt{nclusters} clusters and groups the input samples
|
|
around the clusters. On output, $\texttt{labels}_i$ contains a cluster index for
|
|
samples stored in the i-th row of the \texttt{samples} matrix.
|
|
|
|
\ifC
|
|
% Example: Clustering random samples of multi-gaussian distribution with k-means
|
|
\begin{lstlisting}
|
|
#include "cxcore.h"
|
|
#include "highgui.h"
|
|
|
|
void main( int argc, char** argv )
|
|
{
|
|
#define MAX_CLUSTERS 5
|
|
CvScalar color_tab[MAX_CLUSTERS];
|
|
IplImage* img = cvCreateImage( cvSize( 500, 500 ), 8, 3 );
|
|
CvRNG rng = cvRNG(0xffffffff);
|
|
|
|
color_tab[0] = CV_RGB(255,0,0);
|
|
color_tab[1] = CV_RGB(0,255,0);
|
|
color_tab[2] = CV_RGB(100,100,255);
|
|
color_tab[3] = CV_RGB(255,0,255);
|
|
color_tab[4] = CV_RGB(255,255,0);
|
|
|
|
cvNamedWindow( "clusters", 1 );
|
|
|
|
for(;;)
|
|
{
|
|
int k, cluster_count = cvRandInt(&rng)%MAX_CLUSTERS + 1;
|
|
int i, sample_count = cvRandInt(&rng)%1000 + 1;
|
|
CvMat* points = cvCreateMat( sample_count, 1, CV_32FC2 );
|
|
CvMat* clusters = cvCreateMat( sample_count, 1, CV_32SC1 );
|
|
|
|
/* generate random sample from multigaussian distribution */
|
|
for( k = 0; k < cluster_count; k++ )
|
|
{
|
|
CvPoint center;
|
|
CvMat point_chunk;
|
|
center.x = cvRandInt(&rng)%img->width;
|
|
center.y = cvRandInt(&rng)%img->height;
|
|
cvGetRows( points,
|
|
&point_chunk,
|
|
k*sample_count/cluster_count,
|
|
(k == (cluster_count - 1)) ?
|
|
sample_count :
|
|
(k+1)*sample_count/cluster_count );
|
|
cvRandArr( &rng, &point_chunk, CV_RAND_NORMAL,
|
|
cvScalar(center.x,center.y,0,0),
|
|
cvScalar(img->width/6, img->height/6,0,0) );
|
|
}
|
|
|
|
/* shuffle samples */
|
|
for( i = 0; i < sample_count/2; i++ )
|
|
{
|
|
CvPoint2D32f* pt1 =
|
|
(CvPoint2D32f*)points->data.fl + cvRandInt(&rng)%sample_count;
|
|
CvPoint2D32f* pt2 =
|
|
(CvPoint2D32f*)points->data.fl + cvRandInt(&rng)%sample_count;
|
|
CvPoint2D32f temp;
|
|
CV_SWAP( *pt1, *pt2, temp );
|
|
}
|
|
|
|
cvKMeans2( points, cluster_count, clusters,
|
|
cvTermCriteria( CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 10, 1.0 ));
|
|
|
|
cvZero( img );
|
|
|
|
for( i = 0; i < sample_count; i++ )
|
|
{
|
|
CvPoint2D32f pt = ((CvPoint2D32f*)points->data.fl)[i];
|
|
int cluster_idx = clusters->data.i[i];
|
|
cvCircle( img,
|
|
cvPointFrom32f(pt),
|
|
2,
|
|
color_tab[cluster_idx],
|
|
CV_FILLED );
|
|
}
|
|
|
|
cvReleaseMat( &points );
|
|
cvReleaseMat( &clusters );
|
|
|
|
cvShowImage( "clusters", img );
|
|
|
|
int key = cvWaitKey(0);
|
|
if( key == 27 )
|
|
break;
|
|
}
|
|
}
|
|
\end{lstlisting}
|
|
|
|
\cvCPyFunc{SeqPartition}
|
|
Splits a sequence into equivalency classes.
|
|
|
|
\cvdefC{
|
|
int cvSeqPartition( \par const CvSeq* seq,\par CvMemStorage* storage,\par CvSeq** labels,\par CvCmpFunc is\_equal,\par void* userdata );
|
|
}
|
|
|
|
\begin{description}
|
|
\cvarg{seq}{The sequence to partition}
|
|
\cvarg{storage}{The storage block to store the sequence of equivalency classes. If it is NULL, the function uses \texttt{seq->storage} for output labels}
|
|
\cvarg{labels}{Ouput parameter. Double pointer to the sequence of 0-based labels of input sequence elements}
|
|
\cvarg{is\_equal}{The relation function that should return non-zero if the two particular sequence elements are from the same class, and zero otherwise. The partitioning algorithm uses transitive closure of the relation function as an equivalency critria}
|
|
\cvarg{userdata}{Pointer that is transparently passed to the \texttt{is\_equal} function}
|
|
\end{description}
|
|
|
|
\begin{lstlisting}
|
|
typedef int (CV_CDECL* CvCmpFunc)(const void* a, const void* b, void* userdata);
|
|
\end{lstlisting}
|
|
|
|
The function \texttt{cvSeqPartition} implements a quadratic algorithm for
|
|
splitting a set into one or more equivalancy classes. The function
|
|
returns the number of equivalency classes.
|
|
|
|
% Example: Partitioning a 2d point set
|
|
\begin{lstlisting}
|
|
|
|
#include "cxcore.h"
|
|
#include "highgui.h"
|
|
#include <stdio.h>
|
|
|
|
CvSeq* point_seq = 0;
|
|
IplImage* canvas = 0;
|
|
CvScalar* colors = 0;
|
|
int pos = 10;
|
|
|
|
int is_equal( const void* _a, const void* _b, void* userdata )
|
|
{
|
|
CvPoint a = *(const CvPoint*)_a;
|
|
CvPoint b = *(const CvPoint*)_b;
|
|
double threshold = *(double*)userdata;
|
|
return (double)((a.x - b.x)*(a.x - b.x) + (a.y - b.y)*(a.y - b.y)) <=
|
|
threshold;
|
|
}
|
|
|
|
void on_track( int pos )
|
|
{
|
|
CvSeq* labels = 0;
|
|
double threshold = pos*pos;
|
|
int i, class_count = cvSeqPartition( point_seq,
|
|
0,
|
|
&labels,
|
|
is_equal,
|
|
&threshold );
|
|
printf("%4d classes\n", class_count );
|
|
cvZero( canvas );
|
|
|
|
for( i = 0; i < labels->total; i++ )
|
|
{
|
|
CvPoint pt = *(CvPoint*)cvGetSeqElem( point_seq, i );
|
|
CvScalar color = colors[*(int*)cvGetSeqElem( labels, i )];
|
|
cvCircle( canvas, pt, 1, color, -1 );
|
|
}
|
|
|
|
cvShowImage( "points", canvas );
|
|
}
|
|
|
|
int main( int argc, char** argv )
|
|
{
|
|
CvMemStorage* storage = cvCreateMemStorage(0);
|
|
point_seq = cvCreateSeq( CV_32SC2,
|
|
sizeof(CvSeq),
|
|
sizeof(CvPoint),
|
|
storage );
|
|
CvRNG rng = cvRNG(0xffffffff);
|
|
|
|
int width = 500, height = 500;
|
|
int i, count = 1000;
|
|
canvas = cvCreateImage( cvSize(width,height), 8, 3 );
|
|
|
|
colors = (CvScalar*)cvAlloc( count*sizeof(colors[0]) );
|
|
for( i = 0; i < count; i++ )
|
|
{
|
|
CvPoint pt;
|
|
int icolor;
|
|
pt.x = cvRandInt( &rng ) % width;
|
|
pt.y = cvRandInt( &rng ) % height;
|
|
cvSeqPush( point_seq, &pt );
|
|
icolor = cvRandInt( &rng ) | 0x00404040;
|
|
colors[i] = CV_RGB(icolor & 255,
|
|
(icolor >> 8)&255,
|
|
(icolor >> 16)&255);
|
|
}
|
|
|
|
cvNamedWindow( "points", 1 );
|
|
cvCreateTrackbar( "threshold", "points", &pos, 50, on_track );
|
|
on_track(pos);
|
|
cvWaitKey(0);
|
|
return 0;
|
|
}
|
|
\end{lstlisting}
|
|
|
|
\fi
|
|
|
|
\fi
|
|
|
|
\ifCpp
|
|
|
|
\cvCppFunc{kmeans}
|
|
Finds the centers of clusters and groups the input samples around the clusters.
|
|
\cvdefCpp{double kmeans( const Mat\& samples, int clusterCount, Mat\& labels,\par
|
|
TermCriteria termcrit, int attempts,\par
|
|
int flags, Mat* centers );}
|
|
\begin{description}
|
|
\cvarg{samples}{Floating-point matrix of input samples, one row per sample}
|
|
\cvarg{clusterCount}{The number of clusters to split the set by}
|
|
\cvarg{labels}{The input/output integer array that will store the cluster indices for every sample}
|
|
\cvarg{termcrit}{Specifies maximum number of iterations and/or accuracy (distance the centers can move by between subsequent iterations)}
|
|
|
|
\cvarg{attempts}{How many times the algorithm is executed using different initial labelings. The algorithm returns the labels that yield the best compactness (see the last function parameter)}
|
|
\cvarg{flags}{It can take the following values:
|
|
\begin{description}
|
|
\cvarg{KMEANS\_RANDOM\_CENTERS}{Random initial centers are selected in each attempt}
|
|
\cvarg{KMEANS\_PP\_CENTERS}{Use kmeans++ center initialization by Arthur and Vassilvitskii}
|
|
\cvarg{KMEANS\_USE\_INITIAL\_LABELS}{During the first (and possibly the only) attempt, the
|
|
function uses the user-supplied labels instaed of computing them from the initial centers. For the second and further attempts, the function will use the random or semi-random centers (use one of \texttt{KMEANS\_*\_CENTERS} flag to specify the exact method)}
|
|
\end{description}}
|
|
\cvarg{centers}{The output matrix of the cluster centers, one row per each cluster center}
|
|
\end{description}
|
|
|
|
The function \texttt{kmeans} implements a k-means algorithm that finds the
|
|
centers of \texttt{clusterCount} clusters and groups the input samples
|
|
around the clusters. On output, $\texttt{labels}_i$ contains a 0-based cluster index for
|
|
the sample stored in the $i^{th}$ row of the \texttt{samples} matrix.
|
|
|
|
The function returns the compactness measure, which is computed as
|
|
\[
|
|
\sum_i \|\texttt{samples}_i - \texttt{centers}_{\texttt{labels}_i}\|^2
|
|
\]
|
|
after every attempt; the best (minimum) value is chosen and the
|
|
corresponding labels and the compactness value are returned by the function.
|
|
Basically, the user can use only the core of the function, set the number of
|
|
attempts to 1, initialize labels each time using some custom algorithm and pass them with
|
|
\par (\texttt{flags}=\texttt{KMEANS\_USE\_INITIAL\_LABELS}) flag, and then choose the best (most-compact) clustering.
|
|
|
|
\cvCppFunc{partition}
|
|
Splits an element set into equivalency classes.
|
|
|
|
\cvdefCpp{template<typename \_Tp, class \_EqPredicate> int\newline
|
|
partition( const vector<\_Tp>\& vec, vector<int>\& labels,\par
|
|
\_EqPredicate predicate=\_EqPredicate());}
|
|
\begin{description}
|
|
\cvarg{vec}{The set of elements stored as a vector}
|
|
\cvarg{labels}{The output vector of labels; will contain as many elements as \texttt{vec}. Each label \texttt{labels[i]} is 0-based cluster index of \texttt{vec[i]}}
|
|
\cvarg{predicate}{The equivalence predicate (i.e. pointer to a boolean function of two arguments or an instance of the class that has the method \texttt{bool operator()(const \_Tp\& a, const \_Tp\& b)}. The predicate returns true when the elements are certainly if the same class, and false if they may or may not be in the same class}
|
|
\end{description}
|
|
|
|
The generic function \texttt{partition} implements an $O(N^2)$ algorithm for
|
|
splitting a set of $N$ elements into one or more equivalency classes, as described in \url{http://en.wikipedia.org/wiki/Disjoint-set_data_structure}. The function
|
|
returns the number of equivalency classes.
|
|
|
|
|
|
\fi
|