k均值

算法流程如下：

1.输入数据集合和类别数K（由用户指定）。

2.随机分配类别中心点的位置。

3.将每个店放入离它最近的类别中心点所在的集合。

4.移动类别中心点到他所在集合的中心。

5.转到第三步，直到收敛。

opencv里提供的实例代码如下：

#include "StdAfx.h"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/core/core.hpp"
#include <iostream>

using namespace cv;
using namespace std;

// static void help()
// {
//     cout << "\nThis program demonstrates kmeans clustering.\n"
//             "It generates an image with random points, then assigns a random number of cluster\n"
//             "centers and uses kmeans to move those cluster centers to their representitive location\n"
//             "Call\n"
//             "./kmeans\n" << endl;
// }

int main( int /*argc*/, char** /*argv*/ )
{
const int MAX_CLUSTERS = 8;                  //类别个数上限
Scalar colorTab[] =                          //返回的类别显示的颜色
{
Scalar(0, 0, 255),
Scalar(0,255,0),
Scalar(255,100,100),
Scalar(255,0,255),
Scalar(0,255,255)
};

Mat img(500, 500, CV_8UC3);
RNG rng(12345);

for(;;)
{
int k, clusterCount = rng.uniform(2, MAX_CLUSTERS+1);//类别个数随机产生
int i, sampleCount = rng.uniform(1, 1001);
Mat points(sampleCount, 1, CV_32FC2), labels;

clusterCount = MIN(clusterCount, sampleCount);
Mat centers;

/* generate random sample from multigaussian distribution */
for( k = 0; k < clusterCount; k++ )
{
Point center;
center.x = rng.uniform(0, img.cols);
center.y = rng.uniform(0, img.rows);
Mat pointChunk = points.rowRange(k*sampleCount/clusterCount,
k == clusterCount - 1 ? sampleCount :
(k+1)*sampleCount/clusterCount);
rng.fill(pointChunk, CV_RAND_NORMAL, Scalar(center.x, center.y), Scalar(img.cols*0.05, img.rows*0.05));
}

randShuffle(points, 1, &rng);

kmeans(points, clusterCount, labels,
TermCriteria( CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 10, 1.0),
3, KMEANS_PP_CENTERS, centers);

img = Scalar::all(0);

for( i = 0; i < sampleCount; i++ )
{
int clusterIdx = labels.at<int>(i);
Point ipt = points.at<Point2f>(i);
circle( img, ipt, 2, colorTab[clusterIdx], CV_FILLED, CV_AA );
}

imshow("clusters", img);

char key = (char)waitKey();
if( key == 27 || key == 'q' || key == 'Q' ) // 'ESC'
break;
}

return 0;
}

　　opencv实例代码中随机数占用了太多篇幅，不利用更快理解k均值算法，可以自己写一组数多进行测试感受下，比如：

#include "StdAfx.h"
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/core/core.hpp"
#include <iostream>

using namespace cv;
using namespace std;

// static void help()
// {
//     cout << "\nThis program demonstrates kmeans clustering.\n"
//             "It generates an image with random points, then assigns a random number of cluster\n"
//             "centers and uses kmeans to move those cluster centers to their representitive location\n"
//             "Call\n"
//             "./kmeans\n" << endl;
// }

int main( int /*argc*/, char** /*argv*/ )
{
const int MAX_CLUSTERS = 8;                  //类别个数上限
Scalar colorTab[] =                          //返回的类别显示的颜色
{
Scalar(0, 0, 255),
Scalar(0, 255, 0),
Scalar(255, 100, 100),
Scalar(255, 0, 255),
Scalar(0, 255, 255)
};

Mat img(500, 500, CV_8UC3);
RNG rng(12345);

//for (;;)
//{
int k, clusterCount =3/* rng.uniform(2, MAX_CLUSTERS + 1)*/;//类别个数随机产生
int i, sampleCount = 6/*rng.uniform(1, 1001)*/;
Mat points(sampleCount, 1, CV_32FC2), labels;
//struct point_xy
//{

//};
Point2f point_xy[6], center;
center.x = 300;
center.y =300;

point_xy[0].x = 100 + center.x;
point_xy[0].y = 100 + center.y;

point_xy[1].x = 110 + center.x;
point_xy[1].y = 120 + center.y;

point_xy[2].x = 1 + center.x;
point_xy[2].y = 1 + center.y;

point_xy[3].x = 120 + center.x;
point_xy[3].y = 120 + center.y;

point_xy[4].x = 169 + center.x;
point_xy[4].y = 140 + center.y;

point_xy[5].x = 130 + center.x;
point_xy[5].y = 130 + center.y;
for (int j = 0; j < sampleCount;j++)
{
point_xy[j].x = point_xy[j].x;
point_xy[j].y = point_xy[j].y;
}
for (int j = 0; j < sampleCount; j++)
{

points.at<Point2f>(j).x = point_xy[j].x ;
points.at<Point2f>(j).y = point_xy[j].y ;
}

for (int j = 0; j < sampleCount; j++)
{
points.at<Point2f>(j) = point_xy[j];
}

clusterCount = MIN(clusterCount, sampleCount);
Mat centers;

/* generate random sample from multigaussian distribution */
//for (k = 0; k < clusterCount; k++)
//{
//	Point center;
//	center.x = rng.uniform(0, img.cols);
//	center.y = rng.uniform(0, img.rows);
//	Mat pointChunk = points.rowRange(k*sampleCount / clusterCount,
//		k == clusterCount - 1 ? sampleCount :
//		(k + 1)*sampleCount / clusterCount);
//	rng.fill(pointChunk, CV_RAND_NORMAL, Scalar(center.x, center.y), Scalar(img.cols*0.05, img.rows*0.05));
//}

/*randShuffle(points, 1, &rng);*/

kmeans(points, clusterCount, labels,
TermCriteria(CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 10, 1.0),
3, KMEANS_PP_CENTERS, centers);

img = Scalar::all(0);

for (i = 0; i < sampleCount; i++)
{
int clusterIdx = labels.at<int>(i);
Point ipt = points.at<Point2f>(i);
circle(img, ipt, 2, colorTab[clusterIdx], CV_FILLED, CV_AA);
}

imshow("clusters", img);

char key = (char)waitKey();

return 0;
}