OpenCV中的kmeans和cvKMeans2算法有什么区别？

Question

我想在图片上找到主要的 N 种颜色。为此，我决定使用 KMeans 算法。我的项目是用 C 语言编写的，这就是我使用 cvKMeans2 算法的方式。但它给了我非常奇怪的结果。然后我决定在 OpenCV C++ 上尝试 kmeans 算法。它给了我更准确的结果。那么，我的错在哪里？有人可以向我解释吗？

1.我用这张图片做测试。

2。在 C 上实现。

#include <cv.h>
#include <highgui.h>

#define CLUSTERS 3


int main(int argc, char **argv) {

    const char *filename = "test_12.jpg";
    IplImage *tmp = cvLoadImage(filename);
    if (!tmp) {
        return -1;
    }

    IplImage *src = cvCloneImage(tmp);
    cvCvtColor(tmp, src, CV_BGR2RGB);

    CvMat *samples = cvCreateMat(src->height * src->width, 3, CV_32F);
    for (int i = 0; i < samples->height; i++) {
        samples->data.fl[i * 3 + 0] = (uchar) src->imageData[i * 3 + 0];
        samples->data.fl[i * 3 + 1] = (uchar) src->imageData[i * 3 + 1];
        samples->data.fl[i * 3 + 2] = (uchar) src->imageData[i * 3 + 2];
    }

    CvMat *labels = cvCreateMat(samples->height, 1, CV_32SC1);
    CvMat *centers = cvCreateMat(CLUSTERS, 3, CV_32FC1);

    int flags = 0;
    int attempts = 5;
    cvKMeans2(samples, CLUSTERS, labels,
              cvTermCriteria(CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, 10000, 0.005),
              attempts, 0, flags, centers);

    int rows = 40;
    int cols = 300;
    IplImage *des = cvCreateImage(cvSize(cols, rows), 8, 3);

    int part = 4000;
    int r = 0;
    int u = 0;
    for (int y = 0; y < 300; ++y) {
        for (int x = 0; x < 40; ++x) {
            if (u >= part) {
                r++;
                part = (r + 1) * part;
            }
            des->imageData[(300 * x + y) * 3 + 0] = static_cast<char>(centers->data.fl[r * 3 + 0]);
            des->imageData[(300 * x + y) * 3 + 1] = static_cast<char>(centers->data.fl[r * 3 + 1]);
            des->imageData[(300 * x + y) * 3 + 2] = static_cast<char>(centers->data.fl[r * 3 + 2]);
            u++;
        }
    }

    IplImage *dominant_colors = cvCloneImage(des);
    cvCvtColor(des, dominant_colors, CV_BGR2RGB);

    cvNamedWindow("dominant_colors", CV_WINDOW_AUTOSIZE);
    cvShowImage("dominant_colors", dominant_colors);
    cvWaitKey(0);
    cvDestroyWindow("dominant_colors");

    cvReleaseImage(&src);
    cvReleaseImage(&des);
    cvReleaseMat(&labels);
    cvReleaseMat(&samples);
    return 0;
}

3.在 C++ 上实现。

#include <cv.h>
#include <opencv/cv.hpp>

#define CLUSTERS 3

int main(int argc, char **argv) {
    const cv::Mat &tmp = cv::imread("test_12.jpg");
    cv::Mat src;
    cv::cvtColor(tmp, src, CV_BGR2RGB);

    cv::Mat samples(src.rows * src.cols, 3, CV_32F);

    for (int y = 0; y < src.rows; y++)
        for (int x = 0; x < src.cols; x++)
            for (int z = 0; z < 3; z++)
                samples.at<float>(y + x * src.rows, z) = src.at<cv::Vec3b>(y, x)[z];

    int attempts = 5;
    cv::Mat labels;
    cv::Mat centers;

    kmeans(samples, CLUSTERS, labels, cv::TermCriteria(CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, 1000, 0.005),
           attempts, cv::KMEANS_PP_CENTERS, centers);

    cv::Mat colors(cv::Size(CLUSTERS * 100, 30), tmp.type());
    int p = 100;
    int cluster_id = 0;
    for (int x = 0; x < CLUSTERS * 100; x++) {
        for (int y = 0; y < 30; y++) {
            if (x >= p) {
                cluster_id++;
                p = (cluster_id + 1) * 100;
            }
            colors.at<cv::Vec3b>(y, x)[0] = static_cast<uchar>(centers.at<float>(cluster_id, 0));
            colors.at<cv::Vec3b>(y, x)[1] = static_cast<uchar>(centers.at<float>(cluster_id, 1));
            colors.at<cv::Vec3b>(y, x)[2] = static_cast<uchar>(centers.at<float>(cluster_id, 2));
        }
    }

    cv::Mat dominant_colors;
    cv::cvtColor(colors, dominant_colors, CV_RGB2BGR);
    cv::imshow("dominant_colors", dominant_colors);
    cv::waitKey(0);

    return 0;
}

4. C 上的代码结果。

5. C++ 上的代码结果。

Answer 1

我发现了我的错误。它与IplImage 的 widthStep 字段有关。当我阅读here widthStep 时，出于性能原因，它被填充为 4 的倍数。如果 widthStep 等于 30，它将填充到 32。

int h = src->height;
int w = src->width;
int c = 3;
int delta = 0;
for (int i = 0, y = 0; i < h; ++i) {
    for (int j = 0; j < w; ++j) {
        for (int k = 0; k < c; ++k, y++) {
            samples->data.fl[i * w * c + c * j + k] = (uchar) src->imageData[delta + i * w * c + c * j + k];
        }
    }
    delta += src->widthStep - src->width * src->nChannels;
}

带指针

for (int x = 0, i = 0; x < src->height; ++x) {
    auto *ptr = (uchar *) (src->imageData + x * src->widthStep);
    for (int y = 0; y < src->width; ++y, i++) {
        for (int j = 0; j < 3; ++j) {
            samples->data.fl[i * 3 + j] = ptr[3 * y + j];
        }
    }
}