[OpenCV] Samples 03: kmeans
注意Mat作为kmeans的参数的含义。
扩展：高维向量的聚类。
一、像素聚类
#include "opencv2/highgui.hpp"
#include "opencv2/core.hpp"
#include "opencv2/imgproc.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 = 5;
Scalar colorTab[] =
{
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(;;)
{
//Jeff --> The second parameter is non-inclusive boundary.
int k, clusterCount = rng.uniform(2, MAX_CLUSTERS+1);
int i, sampleCount = rng.uniform(2, 1001);
// int i, sampleCount = 10;
Mat points(sampleCount, 1, CV_32FC2), labels;
//一般来说，没有必要。sampleCount都远大于ClusterCount。
// clusterCount = MIN(clusterCount, sampleCount);
Mat centers;
/* Jeff --> generate random sample from multigaussian distribution 以某一个中心点，二维高斯分布分配点；主要是一个数学技巧。*/
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, RNG::NORMAL, Scalar(center.x, center.y), Scalar(img.cols*0.05, img.rows*0.05));
cout << pointChunk << endl;
}
//洗牌
randShuffle(points, 1, &rng);
std::cout << points << std::endl;
//Jeff --> Mat is vector here, including a list of points.
// labels: index of cluster for each points.
kmeans(points, clusterCount, labels,
TermCriteria( TermCriteria::EPS+TermCriteria::COUNT, 10, 1.0),
3, KMEANS_PP_CENTERS, centers);
//Jeff --> Draw point (tiny circle) with its color on black background.
img = Scalar::all(0);
// Step One: show sample points.
for( i = 0; i < sampleCount; i++ )
{
int clusterIdx = labels.at<int>(i);
Point ipt = points.at<Point2f>(i);
circle( img, ipt, 2, colorTab[clusterIdx], FILLED, LINE_AA );
}
// Step Two: show central points.
for( i = 0; i < clusterCount; i++ )
{
std::cout << centers.at<Point2f>(i) << std::endl;
}
imshow("clusters", img);
char key = (char)waitKey();
if( key == 27 || key == 'q' || key == 'Q' ) // 'ESC'
break;
}
return 0;
}
二、图像的kmeans降维处理
g++ -std=c++11 -pthread -fpermissive main.cpp -o output `pkg-config --cflags --libs opencv` -ldl
From: http://seiya-kumada.blogspot.com/2013/03/k-means-clustering.html【非常好】
#include <opencv2/highgui.hpp> #include <opencv2/core.hpp> #include <opencv2/imgproc.hpp> #include <iostream> using namespace cv; using namespace std; void show_result(const cv::Mat& labels, const cv::Mat& centers, int height, int width) { std::cout << "===\n"; std::cout << "labels: " << labels.rows << " " << labels.cols << std::endl; std::cout << "centers: " << centers.rows << " " << centers.cols << std::endl; assert(labels.type() == CV_32SC1); assert(centers.type() == CV_32FC1); cv::Mat rgb_image(height, width, CV_8UC3); cv::MatIterator_<cv::Vec3b> rgb_first = rgb_image.begin<cv::Vec3b>(); cv::MatIterator_<cv::Vec3b> rgb_last = rgb_image.end<cv::Vec3b>(); cv::MatConstIterator_<int> label_first = labels.begin<int>(); cv::Mat centers_u8; centers.convertTo(centers_u8, CV_8UC1, 255.0); cv::Mat centers_u8c3 = centers_u8.reshape(3); while ( rgb_first != rgb_last ) { const cv::Vec3b& rgb = centers_u8c3.ptr<cv::Vec3b>(*label_first)[0]; *rgb_first = rgb; ++rgb_first; ++label_first; } cv::imshow("tmp", rgb_image); cv::imwrite("./result.jpg", rgb_image); cv::waitKey(); } int main(int argc, const char * argv[]) { cv::Mat image = cv::imread("./d1.jpg"); if ( image.empty() ) { std::cout << "unable to load an input image\n"; return 1; } std::cout << "image: " << image.rows << ", " << image.cols << std::endl; assert(image.type() == CV_8UC3); cv::imshow("image", image); cv::Mat reshaped_image = image.reshape(1, image.cols * image.rows); std::cout << "reshaped image: " << reshaped_image.rows << ", " << reshaped_image.cols << std::endl; assert(reshaped_image.type() == CV_8UC1); //check0(image, reshaped_image); cv::Mat reshaped_image32f; reshaped_image.convertTo(reshaped_image32f, CV_32FC1, 1.0 / 255.0); std::cout << "reshaped image 32f: " << reshaped_image32f.rows << ", " << reshaped_image32f.cols << std::endl; assert(reshaped_image32f.type() == CV_32FC1); cv::Mat labels; int cluster_number = 3; cv::TermCriteria criteria {cv::TermCriteria::COUNT, 100, 1}; cv::Mat centers; cv::kmeans(reshaped_image32f, cluster_number, labels, criteria, 1, cv::KMEANS_RANDOM_CENTERS, centers); show_result(labels, centers, image.rows, image.cols); return 0; }
三、ROI的kmeans支持
原文：https://blog.csdn.net/fengbingchun/article/details/79395298
double kmeans( InputArray data, int K, InputOutputArray bestLabels,
TermCriteria criteria,
int attempts, int flags, OutputArray centers = noArray() );
接口的声明在include/opencv2/core.hpp文件中，实现在modules/core/src/kmeans.cpp文件中
(1)、data：为cv::Mat类型，每行代表一个样本，即特征，即mat.cols=特征长度，mat.rows=样本数，数据类型仅支持float；
(2)、K：指定聚类时划分为几类；
(3)、bestLabels：为cv::Mat类型，是一个长度为(样本数，1)的矩阵，即mat.cols=1,mat.rows=样本数；为K-Means算法的结果输出，指定每一个样本聚类到哪一个label中；
(4)、criteria：TermCriteria类，算法进行迭代时终止的条件，可以指定最大迭代次数，也可以指定预期的精度，也可以这两种同时指定；
(5)、attempts：指定K-Means算法执行的次数，每次算法执行的结果是不一样的，选择最好的那次结果输出；
(6)、flags：初始化均值点的方法，目前支持三种：KMEANS_RANDOM_CENTERS、KMEANS_PP_CENTERS、KMEANS_USE_INITIAL_LABELS；
(7)、centers：为cv::Mat类型，输出最终的均值点，mat.cols=特征长度，mat.rols=K.
// Color dimension reduction Mat processTagByKmean(Mat3b const tag, Option option) { int K = option.knnClusterNum; // 0. Prepare arguments for kmeans. cv::Mat reshaped_tag = tag.reshape(1, tag.cols * tag.rows); cv::Mat reshaped_tag32f, labels, centers; reshaped_tag.convertTo(reshaped_tag32f, CV_32FC1, 1.0 / 255.0);
// ------------------------------------------------------------------
// 1. do kmeans cv::kmeans(reshaped_tag32f, K, labels, TermCriteria(CV_TERMCRIT_EPS + CV_TERMCRIT_ITER, 10, 1.0), 3, KMEANS_PP_CENTERS, centers);
// ------------------------------------------------------------------
// 2. convert to rgb mat cv::Mat rgb_tag(tag.rows, tag.cols, CV_8UC3); cv::MatIterator_<cv::Vec3b> rgb_first = rgb_tag.begin<cv::Vec3b>(); cv::MatIterator_<cv::Vec3b> rgb_last = rgb_tag.end<cv::Vec3b>(); cv::MatConstIterator_<int> label_first = labels.begin<int>(); cv::Mat centers_u8; centers.convertTo(centers_u8, CV_8UC1, 255.0); cv::Mat centers_u8c3 = centers_u8.reshape(3); while (rgb_first != rgb_last) { const cv::Vec3b &rgb = centers_u8c3.ptr<cv::Vec3b>(*label_first)[0]; *rgb_first = rgb;
++rgb_first; ++label_first; } return rgb_tag; }
原文：https://blog.csdn.net/qq_22764813/article/details/52135686
如果Mat类型数据的深度和通道数不满足上面的要求，则需要使用convertTo()函数和cvtColor()函数来进行转换。
convertTo()函数负责转换数据类型不同的Mat，即可以将类似float型的Mat转换到imwrite()函数能够接受的类型。
而cvtColor()函数是负责转换不同通道的Mat，因为该函数的第4个参数就可以设置目的Mat数据的通道数（只是我们一般没有用到它，一般情况下这个函数是用来进行色彩空间转换的）。
另外也可以不用imwrite()函数来存图片数据，可以直接用通用的XML IO接口函数将数据存在XML或者YXML中。
