机器学习：K-Means分割数据（添加了详细注释）

K-Means分割数据（添加了详细注释）

在opencv中kmenas算法对应的教程，代码

#include<iostream>
#include<opencv2/opencv.hpp>
using namespace std;
using namespace cv;
int main()
{
	Mat img(500, 500, CV_8UC3);
	img = Scalar::all(255);
	RNG rng(12345);//随机数发生器
	Scalar colorTab[] = {
	Scalar(0,0,255),
	Scalar(0,255,0),
	Scalar(255,0,0),
	Scalar(0,255,255),
	Scalar(255,0,255)
	};//用于数据点的颜色显示
	int numCluster = rng.uniform(2, 5);//聚类个数4
	printf("number of cluster is %d\n",numCluster);
	int samplecount = rng.uniform(2, 1000);//随机生成samplecount个数据点591
	Mat points(samplecount, 1, CV_32FC2);//samplecount个float类型的数据点，以矩阵的形势呈现
	Mat labels;//kmeans算法后的label标签,里面存储了0,1,2,3四个像素值(有591个)(1x591)
	Mat centors;//中心点
	//生成随机数
	for (int k = 0; k < numCluster; k++)
	{
		//初始化中心点
		Point center;
		center.x = rng.uniform(0,img.cols);
		center.y = rng.uniform(0,img.rows);
		//cout << center << endl;
		//打印初始化中心点
		//circle(img, center, 7, Scalar(0, 0, 255), -1, 8);
		//Mat区块访问，只是创建数据头，改变同时改变
		//这把数据点分成四份
		Mat pointchunk = points.rowRange(k * samplecount / numCluster, k == numCluster - 1 ? samplecount : (k + 1) * samplecount / numCluster);
		//rng.fill对每个数据点进行赋值，使得数据点具有不同的，CV_32FC2的像素值范围
		//NORMAL是高斯分布，
		rng.fill(pointchunk,RNG::NORMAL,Scalar(center.x,center.y),Scalar(img.cols*0.05,img.rows*0.05));
	}
	//以上产生了四个以中心点位均值的四个聚类数据
	//cout << points << endl;
	//作用：将原数组（矩阵）打乱
	randShuffle(points,1,&rng);
	//cout << points << endl;
	//kmeans分类后，每个一类数据产生一个标签（0,1,2,3……）
	kmeans(points,numCluster,labels,TermCriteria(TermCriteria::EPS+TermCriteria::COUNT,10,0.1),3,KMEANS_PP_CENTERS,centors);
	//用不同值显示
	for (int i = 0; i < samplecount; i++)
	{
		int index = labels.at<int>(i);
		Point p = points.at<Point2f>(i);
		circle(img, p, 2, colorTab[index], -1, 8);
	}
	//每个聚类数据中心点显示
	for (size_t i = 0; i < centors.rows; i++)
	{
		float x = centors.at<float>(i, 0);
		float y = centors.at<float>(i, 1);
		circle(img,Point2f(x,y),8,colorTab[i],-1,8);

	}
	imshow("img", img);
	waitKey(0);
	return 0;

}