Image Highlight Removal based on Double Edge-preserving Filter

In order to effectively remove the highlights of the image while retaining the texture information and color information of the image. Based on the two-color reflection model, this paper proposes an image highlight removal method based on a double edge-preserving filter. First, the maximum diffuse reflection chromaticity is estimated by the MSF image principle and the specular detection algorithm proposed in this paper. Then based on the characteristic of local smoothness of the maximum diffuse reflection chromaticity, the maximum diffuse reflection chromaticity estimation value is used as the guide value of the joint bilateral filter and the guided filtering to separately processes the maximum chromaticity map of the image to make it quickly diffuse and spread in the neighborhood to remove the highlights in the image. Compared with the traditional method, the method in this paper can not only remove the image highlights more efficiently, but also retain the color and texture information of the image to a greater extent.