算法之KMeans（K-均值）

今天学习了下Kmeans算法，KMeans算法属于无监督学习的一种，主要通过不断迭代center中心点来使得cast损失函数最小化，即在方差最小的准则下进行不断迭代，当cast与上一次的迭代结果相同则终止迭代。但同时KMeans也存在相应缺点，即最后的聚类结果跟初始选定的中心点有关。
主要的公式如下所示：

主要的算法流程如下所示：

Code:

/*
 *作者：att0206
 *地点：上海师范大学
 *时间：2017/04/06
 *功能：实现对K-Means的学习
*/
#include<opencv2/opencv.hpp>
#include<opencv2/core/core.hpp>
#include<opencv2/highgui/highgui.hpp>
#include<opencv2/imgproc/imgproc.hpp>

using namespace::cv;
using namespace::std;

#define WINDOW_NAME1 "rstImage"
#define WINDOW_NAME2 "KMeans"

Mat rstImage;
Mat dstImage;

//声明K-Means
static void K_Means(Mat&,Mat&);
int main(int argc,char* argv[])
{
    rstImage = imread("1.jpg");
    imshow("rstImage",rstImage);
    K_Means(rstImage,dstImage);
    //cvtColor(rstImage,rstImage,CV_BGR2GRAY);
    //normalize(rstImage,dstImage,0,1,NORM_MINMAX);
    imshow("dst",dstImage);
    //HoughLines
    while((char)(waitKey(1)) != 27) //按下Esc键退出程序
    {}                             
    return 0;
}

static void K_Means(Mat& rstImage,Mat& result)  //定义一个K_Means算法  用于计算离中心点的最近的聚为一类
{
    int width = rstImage.cols;
    int height = rstImage.rows;
    int dims = rstImage.channels();
    //初始化定义
    int sampleCount = width*height;
    int clusterCount = 4;
    Mat points(sampleCount,dims,CV_32F,Scalar(10));
    Mat labels;
    Mat centers(clusterCount,1,points.type());

    //图像RGB到数据集转换
    int index = 0;
    for(int row = 0;row<height;row++)
    {
        for(int col = 0;col<width;col++)
        {
            index = row*width+col;
            Vec3b rgb = rstImage.at<Vec3b>(row,col);
            points.at<float>(index,0) = static_cast<int>(rgb[0]);
            points.at<float>(index,1) = static_cast<int>(rgb[1]);
            points.at<float>(index,2) = static_cast<int>(rgb[2]);
        }
    }
    //运行K-Means数据分类
    TermCriteria criteria = TermCriteria(CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 10, 1.0);
    kmeans(points, clusterCount, labels, criteria, 3, KMEANS_PP_CENTERS, centers);
    result = Mat::zeros(rstImage.size(), CV_8UC3);
    for(int row = 0; row < height; row++) {
        for (int col = 0; col < width; col++) {
            index = row*width + col;
            int label = labels.at<int>(index, 0);
            if (label == 1) {
                result.at<Vec3b>(row, col)[0] = 255;
                result.at<Vec3b>(row, col)[1] = 0;
                result.at<Vec3b>(row, col)[2] = 0;
                                                    }
            else if (label == 2) {
                 result.at<Vec3b>(row, col)[0] = 0;
                result.at<Vec3b>(row, col)[1] = 255;
                result.at<Vec3b>(row, col)[2] = 0;
                                    }
            else if (label == 3) {
                    result.at<Vec3b>(row, col)[0] = 0;
                    result.at<Vec3b>(row, col)[1] = 0;
                    result.at<Vec3b>(row, col)[2] = 255;
                                    }
            else if (label == 0) {
                    result.at<Vec3b>(row, col)[0] = 0;
                    result.at<Vec3b>(row, col)[1] = 255;
                    result.at<Vec3b>(row, col)[2] = 255;
                                }
                            }
                        }
        imshow("kmeans-demo", result);
}

output: