c++ - fastNlMeansDenoising() 不滤除噪声

Question

我正在尝试通过 opencv fastNlMeansDenoising() 函数去除噪声。但是我的输出图像与原始噪声图像相同。

输入图片:

代码:

#include <iostream>

#include <opencv2/opencv.hpp>

#include <opencv2/highgui/highgui.hpp>

#include <opencv2/imgproc/imgproc.hpp>

using namespace std;

using namespace cv;


int main() {

    Mat img = imread("noisy.jpg");

    if (!img.data) {
        cout << "File not found" << endl;
        return -1;
    }

    // first copy the image
    Mat img_gray = img.clone();
    cvtColor(img, img_gray, CV_RGB2GRAY);

    Mat img1;
    //fastNlMeansDenoising(img_gray, img1, 3.0, 7, 21);
    cv::fastNlMeansDenoising(img_gray, img1, 3.0, 7, 21);

    imshow("img1", img1);

    waitKey();

    return 0;
}

输出图像:

我看不到任何平滑效果。我不明白这是为什么。请帮助我使用此功能来消除噪音。谢谢

Answer 1

在OpenCV中，函数定义如下

void fastNlMeansDenoising(InputArray src, OutputArray dst, float h=3, int templateWindowSize=7, int searchWindowSize=21 )

在哪里

Parameters: src – Input 8-bit 1-channel, 2-channel or 3-channel

image. dst – Output image with the same size and type as src .

templateWindowSize – Size in pixels of the template patch that is usedto compute weights. Should be odd. Recommended value 7 pixels

searchWindowSize – Size in pixels of the window that is used tocompute weighted average for given pixel. Should be odd. Affectperformance linearly: greater

searchWindowsSize - greater denoisingtime. Recommended value 21 pixels

h – Parameter regulating filterstrength. Big h value perfectly removes noise but also removes imagedetails, smaller h value preserves details but also preserves somenoise

因此，为了去除噪声，我不得不增加滤波器强度参数h，大的h值完美地去除了噪声，但较小的h值保留了细节，也保留了一些噪声。

所以我通过使用这样的函数完美地消除了噪声:

fastNlMeansDenoising(img_gray, img1, 30.0, 7, 21);

输出:

注意:此函数在 Debug模式下的执行时间太慢。为了稍微加快执行时间，最好在 Release模式下运行它。