Edges and hues keeping denoising algorithm for color images

Based on the unique color separation characteristics of HSI space, noise removal of color images contaminated by high noise is investigated. The color image is first projected into the color feature space HSI, and the color information is separated from the luminance feature information, and then the color components H and S in this space are processed by the distance threshold denoising method in polar coordinates to remove the noise without distorting the color. At the same time, the luminance feature component I is guided filtered to effectively remove the noise while preserving the edge information of the original image; finally, the corresponding inverse conversion is performed to obtain the final color image. The algorithm has some improvement in eliminating color noise, maintaining hue, and protecting image details compared with previous algorithms, which is more in line with the visual requirements of human eyes.