Image processing method and device, electronic device, and computer-readable storage medium

Abstract

The disclosure relates to an image processing method including: determining the edge of the structural area of a human face in an image; setting the filtering radius of pixels according to the shortest distance from the pixels in the image to the edge, wherein the filtering radius is in inverse correlation with the shortest distance; and edge-preserving filtering the pixels according to the filtering radius. According to the embodiment of the present disclosure, since the filtering radius of the pixels is in inverse correlation with the shortest distance between the pixels and the edge of thestructural area of the human face, the method can ensure the clearness of the edge of the structural area of the human face and can guarantee to filter flaws in the unstructured area of the human face.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular, to an image processing method, an image processing device, electronic equipment, and a computer-readable storage medium. Background technique [0002] At present, in the process of taking pictures, the microdermabrasion treatment of human faces is mainly realized through filtering algorithms. [0003] However, the size of the local sliding window used in the existing filtering algorithm is fixed, so the filtering effect for different areas of the face is the same, although this can realize the dermabrasion treatment of the non-structural areas of the face such as cheeks and forehead, However, the same effect of microdermabrasion will be performed on structural areas such as the nose and lips of the human face. [0004] As a result, the edges of the structural region of the human face become blurred after filtering, which affects the display effect of the proc...

AI Technical Summary

Problems solved by technology

[0003] However, the size of the local sliding window used in the existing filtering algorithm is fixed, so the filtering effect is the same for different areas of the face. Although this can achieve skin smoothing on the non-structural areas of the face such as cheeks and forehead, However, it will also perform the same effect of microdermabrasion on the structural areas such as the nose and lips of the human face.

[0004] As a result, the edges of the structural area of ​​the face will become blurred after filtering, which will affect the display effect of the processed image

Images