cvKMeans2:机器学习算法—K均值-CSDN博客

K均值尝试找到数据的自然类别。用户设置类别个数，K均值迅速找到“好的”类别中心。“好的”意味着聚类的中心位于数据的自然类别中心。

void cvKMeans2( const CvArr* samples, int cluster_count,
CvArr* labels, CvTermCriteria termcrit );

samples
输入样本的浮点矩阵，每个样本一行。

cluster_count
所给定的聚类数目

labels
输出整数向量：每个样本对应的类别标识，在 cluster_count  内。

termcrit
指定聚类的最大迭代次数和／或精度（两次迭代引起的聚类中心的移动距离）

函数 cvKMeans2 执行 k-means 算法搜索 cluster_count 个类别的中心并对样本进行分类，输出 labels(i) 为样本 i 的类别标识。

#include "stdafx.h"
#include "cxcore.h"
#include "highgui.h" //包含highgui.h来使用窗口输出

int _tmain(int argc, _TCHAR* argv[])
{
#define MAX_CLUSTERS 5 //设置类别的颜色，个数（《=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 multivariate Gaussian 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 );
        }

//使用cvKMeans2()，直到聚类中心的最大移动小于1

        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 ) // 'ESC'，press then exit
            break;
    }

return 0;
}