OpenCV Q&A Forum - RSS feedhttp://answers.opencv.org/questions/OpenCV answersenCopyright <a href="http://www.opencv.org">OpenCV foundation</a>, 2012-2018.Fri, 22 Jan 2016 01:38:44 -0600How to remove specific noises?http://answers.opencv.org/question/84929/how-to-remove-specific-noises/ I am doing a image processing project which is about the noise removal. I use erode() function, dilate() function, and fastNlMeansDenoising() function to remove small pattern noises. It is successful but not perfect for all my sample images.
Thus, I proposed a method that is to detect that specific color of noises and remove the similar color of those noises. As the color of noises is a majority in the image, I could detect that kind of color. But how can I do that?cv_newFri, 22 Jan 2016 01:38:44 -0600http://answers.opencv.org/question/84929/isotropic linear diffusion smoothinghttp://answers.opencv.org/question/70552/isotropic-linear-diffusion-smoothing/I want to apply the denoising filter I named in the title which is based on the following equations:
![image description](/upfiles/14418822702340028.png)
where `d` is a scalar constant diffusivity parameter, `I(x, y)` is the initial noisy image, and `u(x, y, t)`
is the image obtained after a diffusion time `t` lets say 5, 10 and 30. However, I am quite confused about which function to use and how, in order to achieve this in OpenCV. I have the feeling that it is quite simple but for some reason I am confused. Does anyone have an idea?
Here is a sample image:
![image description](/upfiles/1441883251877551.png)
----------------------
UPDATE
-------------------------------------------------
this is the result images after following @LBerger 's code, they are in time `t = 0`/`t = 4` and `d = 1`:
![image description](/upfiles/14419938046518315.png) ![image description](/upfiles/14419938112056689.png)
, is it expected to be like that?
I think that something is wrong, because I am trying also to compare it with the gaussian smoothing. And according to the following formula:
![image description](/upfiles/14419945979427592.png)
where `Gā2t (x, y)` is the Gaussian kernel. This proves that performing isotropic linear diffusion for a time `t` with `d = 1` is exactly equivalent to performing Gaussian smoothing with a `Ļ = ā(2t)`
and applying the gaussian filter with the following code:
void gaussian_2D_convolution(const cv::Mat& src, cv::Mat& dst, const float sigma, const int ksize_x = 0, const int ksize_y = 0)
{
int ksize_x_ = ksize_x, ksize_y_ = ksize_y;
// Compute an appropriate kernel size according to the specified sigma
if (sigma > ksize_x || sigma > ksize_y || ksize_x == 0 || ksize_y == 0)
{
ksize_x_ = (int)ceil(2.0f*(1.0f + (sigma - 0.8f) / (0.3f)));
ksize_y_ = ksize_x_;
}
// The kernel size must be and odd number
if ((ksize_x_ % 2) == 0)
{
ksize_x_ += 1;
}
if ((ksize_y_ % 2) == 0)
{
ksize_y_ += 1;
}
// Perform the Gaussian Smoothing
GaussianBlur(src, dst, Size(ksize_x_, ksize_y_), sigma, sigma, BORDER_DEFAULT);
// show result
std::ostringstream out;
out << std::setprecision(1) << std::fixed << sigma;
String title = "sigma: " + out.str();
imshow(title, dst);
imwrite("gaussian/" + title + ".png", dst);
waitKey(260);
}
and calling it with `gaussian_2D_convolution(img, smoothed, sqrt(2*5));` the two results of gaussian smoothing and isotropic linear smoothing in time `t = 5` are respectively:
![image description](/upfiles/1441995064639903.png) ![image description](/upfiles/14419950724472886.png)
which are for sure not similar :-(.theodoreThu, 10 Sep 2015 06:08:09 -0500http://answers.opencv.org/question/70552/