Illumination-adaptive face image enhancement method

Abstract

The invention discloses an illumination-adaptive face image enhancement method, and belongs to the field of image processing and face recognition. The method comprises the following steps: 1) calculating the average brightness of an input face image; 2) comparing the brightness interval with a brightness interval of a normal-illumination face image obtained through statistical learning, and judging the illumination level of the normal-illumination face image into low illumination, high illumination or normal illumination; 3) performing illumination enhancement processing on the face image judged to be low-illumination or high-illumination based on a camera response model and an exposure fusion method, and directly outputting the face image judged to be normal-illumination without processing; 4) calculating the average brightness of the face image enhanced in the previous step again, judging the illumination level, and iteratively executing the image enhancement operation until the faceimage with the normal illumination level is finally output. The enhanced face image can be seamlessly accessed to an existing face recognition algorithm to serve as input, and the performance of an existing face recognition system under complex illumination conditions is improved.

Description

technical field [0001] The invention belongs to the field of image processing and face recognition, and in particular relates to an illumination adaptive face image enhancement method. Background technique [0002] Face recognition technology has achieved good results under controllable conditions in recent years, and many mature face recognition algorithms and systems have emerged. However, in practical applications, due to the influence of uncontrollable factors such as illumination, expression, posture, etc., the image of the same face changes greatly in different environments, and the impact of illumination changes on the performance of face recognition is the most obvious, which greatly restricts human recognition. Applications of face recognition. Investigating methods to improve face recognition performance under complex lighting conditions is a challenging task. In recent years, scholars at home and abroad have done a lot of research work, and proposed different me...

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the situations of too dark, too bright and uneven lighting that may exist in face recognition occasions, and aims to solve the problem of poor imaging quality of face images under complex lighting conditions and affect the performance of face recognition, and proposes a lighting Adaptive Face Image Enhancement Method

Images