A Noise Robust Facial Expression Recognition Method

Abstract

The invention discloses a noise-robust facial expression recognition method, including the improvement of the preprocessing filter and the feature extraction operator, wherein the anisotropic diffusion filter model based on the relative brightness difference adjustment factor compensates for the original The anisotropic diffusion filtering method smoothes out the lack of details while filtering out noise, distinguishes facial noise and weak detail expression information, and ensures the integrity of expression image information. dimension, reduce the interference of redundant information, shorten the running time of the algorithm, improve the classification accuracy and robustness to noise, and have good application prospects.

Description

technical field [0001] The invention relates to a noise-robust human facial expression recognition method, which belongs to the technical field of human face recognition. Background technique [0002] Facial expression is one of the important body languages ​​of human beings, which can accurately reflect changes in emotional, mental, and psychological states. In recent years, the use of computers to analyze and understand facial expressions to complete related work has important application prospects in human-computer interaction. Facial expression recognition technology has gradually become a research hotspot. The facial expression recognition system mainly includes image preprocessing, face detection and area Segmentation, expression feature extraction and classification are four parts. Considering that the recognition effect of the classifier largely depends on the accuracy of the feature description, the expression feature extraction is an important part of the facial ex...

AI Technical Summary

Problems solved by technology

[0011] The purpose of the present invention is to overcome the problem of traditional facial expression recognition. The noise-robust human facial expression recognition method provided by the present invention is based on the anisotropic diffusion filter model of the relative brightness difference adjustment factor, which compensates for the original anisotropic The heterogeneous diffusion filtering method can smooth out the lack of details while filtering out noise, distinguish facial noise and weak detail expression information, and ensure the integrity of expression image information. At the same time, the improved HOG operator is used to extract expression features and reduce the dimension of feature vectors. Reduce the interference of redundant information, shorten the running time of the algorithm, improve the classification accuracy and robustness to noise, and have good application prospects

Images