OpenCV使用k-means来分色图像

Question

我想在C ++接口（cv名称空间）中使用k-means和OpenCV对图像进行分色，我得到了奇怪的结果。我需要它来减少一些噪音。这是我的代码：

#include "cv.h"
#include "highgui.h"

using namespace cv;

int main() {
    Mat imageBGR, imageHSV, planeH, planeS, planeV;

    imageBGR = imread("fruits.jpg");
    imshow("original", imageBGR);

    cv::Mat labels, data;
    cv::Mat centers(8, 1, CV_32FC1);
    imageBGR.convertTo(data, CV_32F);

    cv::kmeans(data, 8, labels,
            cv::TermCriteria(CV_TERMCRIT_ITER, 10, 1.0),
            3, cv::KMEANS_PP_CENTERS, &centers);
    imshow("posterized hue", data);
    data.convertTo(data, CV_32FC3);

    waitKey();
    return 0;
}

但是我得到了一个奇怪的结果

第一张图片：原创

第二张图片：k-means之后。

有什么建议吗？

---

更新：正确的解决方案。也许有人可以帮我优化代码？

#include "cv.h"
#include "highgui.h"

#include <iostream>

using namespace cv;
using namespace std;

int main() {
    Mat src;

    src = imread("fruits.jpg");
    imshow("original", src);

    blur(src, src, Size(15,15));
    imshow("blurred", src);

    Mat p = Mat::zeros(src.cols*src.rows, 5, CV_32F);
    Mat bestLabels, centers, clustered;
    vector<Mat> bgr;
    cv::split(src, bgr);
    // i think there is a better way to split pixel bgr color
    for(int i=0; i<src.cols*src.rows; i++) {
        p.at<float>(i,0) = (i/src.cols) / src.rows;
        p.at<float>(i,1) = (i%src.cols) / src.cols;
        p.at<float>(i,2) = bgr[0].data[i] / 255.0;
        p.at<float>(i,3) = bgr[1].data[i] / 255.0;
        p.at<float>(i,4) = bgr[2].data[i] / 255.0;
    }

    int K = 8;
    cv::kmeans(p, K, bestLabels,
            TermCriteria( CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, 10, 1.0),
            3, KMEANS_PP_CENTERS, centers);

    int colors[K];
    for(int i=0; i<K; i++) {
        colors[i] = 255/(i+1);
    }
    // i think there is a better way to do this mayebe some Mat::reshape?
    clustered = Mat(src.rows, src.cols, CV_32F);
    for(int i=0; i<src.cols*src.rows; i++) {
        clustered.at<float>(i/src.cols, i%src.cols) = (float)(colors[bestLabels.at<int>(0,i)]);
//      cout << bestLabels.at<int>(0,i) << " " << 
//              colors[bestLabels.at<int>(0,i)] << " " << 
//              clustered.at<float>(i/src.cols, i%src.cols) << " " <<
//              endl;
    }

    clustered.convertTo(clustered, CV_8U);
    imshow("clustered", clustered);

    waitKey();
    return 0;
}

结果：

Answer 1

我不是OpenCV的专家，因此我将提供与您的问题相关的一般性建议K-means采用基本上是矩阵的向量列表：

[x0, y0, r0, g0, b0]
[x1, y1, r1, g1, b1]
[x2, y2, r2, g2, b2]
.
.
.

你正在给它一个不起作用的图像。首先必须将图像转换为此k均值矩阵格式。对于源图像的每个像素，在结果矩阵中有一行。另请注意，您应该缩放值，使它们都具有相似的值。如果不这样做，x和y坐标通常会比颜色高得多“重力”，导致结果不令人满意。 C ++伪代码：

int pixel_index = 0;
for (int y = 0; y < image height; y++)  {
  for (int x = 0; x < image width; x++)  {
     matrix[pixel_index][0] = (float)x / image width;
     matrix[pixel_index][1] = (float)y / image height;
     matrix[pixel_index][2] = (float)pixel(x, y).r / 255.0f;
     matrix[pixel_index][3] = (float)pixel(x, y).g / 255.0f;
     matrix[pixel_index][4] = (float)pixel(x, y).b / 255.0f;
  }
}
// Pass the matrix to kmeans...

因此，您将获得每个像素的标签，这些标签对应于已分配给它的群集。然后，您需要确定群集的颜色 - 这可以从获取中心像素颜色值到计算群集的平均/中值颜色。确定颜色后，只需移动图像并将像素设置为其簇颜色：

for (int y = 0; y < image height; y++)  {
  for (int x = 0; x < image width; x++)  {
     int index = y * image width + x;  // This corresponds to pixel_index above
     int cluster_index = labels[index]; // 0 to 7 in your case
     Color color = colors[cluster_index];  // Colors is an array of 8 colors of the clusters
     image.setpixel(x, y, color)
  }
}

如果您更喜欢使用HSV而不是RGB，只需使用HSV值而不是RGB值。

OpenCV可能具有完全执行上述转换的功能，但我无法使用Google快速找到它们。

Answer 2

如果您不需要k-means中的x，y坐标，则可以使用reshape命令更快地排列数据：

  int origRows = img.rows;
  notes << "original image is: " << img.rows << "x" << img.cols << endl;
  Mat colVec = img.reshape(1, img.rows*img.cols); // change to a Nx3 column vector
  cout << "colVec is of size: " << colVec.rows << "x" << colVec.cols << endl;
  Mat colVecD, bestLabels, centers, clustered;
  int attempts = 5;
  int clusts = 8;
  double eps = 0.001;
  colVec.convertTo(colVecD, CV_32FC3, 1.0/255.0); // convert to floating point
  double compactness = kmeans(colVecD, clusts, bestLabels, 
        TermCriteria(CV_TERMCRIT_EPS+CV_TERMCRIT_ITER, attempts, eps), 
        attempts, KMEANS_PP_CENTERS, centers);
  Mat labelsImg = bestLabels.reshape(1, origRows); // single channel image of labels
  cout << "Compactness = " << compactness << endl;