Facial expression identification method based on Gabor wavelet and gray-level co-occurrence matrix

Abstract

A facial expression identification method based on a Gabor wavelet and a gray-level co-occurrence matrix. According to the method, firstly, a pure face region in an expression image is extracted by a manual partitioning method and color image gray processing, histogram equalization and scale normalization processing are carried out; then data redundancies of conventional Gabor features are greatly reduced by a method for carrying out block extraction on a Gabor feature statistic, and the gray-level co-occurrence matrix which reflects the image texture features is introduced into the field of expression identification for the first time so as to make up the defect of deficiency of pixel spatial relativity, which is caused by Gabor feature block processing; and finally, a set of low-dimension feature vectors for feature expression are generated and on the premise of ensuring a high expression identification rate, the expression identification rate is greatly improved.

Description

technical field [0001] The invention relates to the field of human facial expression recognition, and designs and implements a human facial expression recognition algorithm based on Gabor wavelet and gray level co-occurrence matrix. Background technique [0002] Facial expressions contain rich personal emotional information and are an important way for humans to express emotions. By recognizing facial expressions, computers can understand the corresponding psychological state of humans, so as to better serve all aspects of human life, such as human-computer interaction, intelligent security, medical monitoring, psychological analysis, etc. At present, most expression recognition algorithms are mainly tested on facial expression images with no occlusion in front, and the complete expression information is preserved to a certain extent. However, in real life, facial expressions are often blocked. Coverage by hair, sunglasses, masks, gestures, etc. will cause the loss of facia...

AI Technical Summary

Problems solved by technology

[0005] However, since the expression features extracted by Gabor wavelets often have high dimensions, various feature extraction algorithms combined with Gabor wavelets have the disadvantages of large amount of calculation and high complexity, resulting in a long time-consuming process of the entire expression recognition process. It is not conducive to expression recognition from experimental simulation to practical application

Images