Facial texture feature extraction method with uneven illumination

Abstract

The invention discloses a method for extracting facial textural features with uneven illumination. The method comprises the following steps: step (1), collecting an original image; step (2), performing uniform illumination condition correction processing on the image: step (1), obtaining a frequency domain of image brightness; step (2), disassembling the texture image; step (3) acquiring an illumination condition coefficient; step (4) obtaining quotient images under two different illumination conditions; and step (5) obtaining a quotient image based on the illumination condition of the given image and the reference uniform illumination, and obtaining a texture image under the uniform illumination condition. The problems of definition of texture features and continuity and smoothness of textures can be effectively solved, and face recognition performance is remarkably improved; the application prospect is wide, and the method can be applied to the fields of security check systems, identity recognition systems, video analysis systems and the like.

Description

technical field [0001] The invention relates to a face recognition and image processing method, in particular to a facial texture feature extraction method with uneven illumination. Background technique [0002] In recent years, face recognition systems such as expression, pose, and illumination invariance have been continuously developed. In the field of face recognition research, the illumination variation of facial images is still a difficult problem. When the illumination conditions are changed, the same face will appear in various ways. More specifically, partial shadows and full shadows are generated on the human face due to illumination changes. Therefore, the face recognition performance will be seriously reduced. In order to improve the accuracy and performance of face recognition, various methods have been proposed to solve this problem. For example, histogram equalization, gamma correction, logarithmic transformation, gradient method, self-quotient method and o...

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: In view of the shortcomings and deficiencies in the current existing facial texture feature enhancement methods, the purpose of the present invention is to provide a method for extracting facial texture features with uneven illumination, so as to solve the problem of texture clarity and texture features of facial image texture features. Continuity and smoothness issues

Images