A facial expression recognition method based on sparse representation based on double dictionary and multi-feature fusion decision

Abstract

The invention discloses a face expression recognition method based on sparse representation based on double dictionaries and multi-feature fusion decision-making. First, features are extracted from face image samples without expression and face images with specific expressions, and a nominal dictionary and a feature dictionary are constructed according to the features. ; For the image to be recognized, by extracting the corresponding features, use the nominal dictionary to perform sparse coding on it, and then combine the coding coefficient results with the nominal dictionary to obtain the reconstructed expressionless image features, and subtract the features before and after reconstruction The features containing only the information of expression characteristics are obtained, and the feature dictionary is used to sparsely encode the features to obtain the coding coefficient vector; based on the feature dictionary, an auxiliary decision-making fusion dictionary is trained for different types of features, and based on the sparse representation, the different types of features are calculated. The encoded coefficient vectors are classified and judged, and the judgment results of various features are obtained; the final recognition results are obtained by voting; this method can effectively overcome the influence of face, illumination, occlusion and other changes on expression recognition.

Description

technical field [0001] The invention belongs to the technical field of facial expression recognition, and more specifically relates to a method for recognizing facial expressions based on a sparse representation-based double dictionary and multi-feature fusion decision-making. Background technique [0002] Facial expression recognition technology has strong application prospects in human-computer interaction, online education, intelligent driving and other fields. In actual use, facial expression recognition is easily affected by illumination, noise, and occlusion. In order to overcome the influence of these factors, the recognition algorithm framework based on sparse representation theory has been widely used. [0003] At present, the most important feature that affects the accuracy of facial expression recognition based on sparse representation theory is intra-class variation. For facial expression recognition, the feature differences between different types of expressions...

AI Technical Summary

Problems solved by technology

[0004] Lee Seung Ho et al. published "Intra-Class Variation Reduction Using Training Expression Images for Sparse Representation Based Facial Expression Recognition" on IEEE Transactions on Affective computing (2014), aiming at the intra-class changes in the process of facial expression recognition, it is proposed to use training sample re- Construct an intra-class change feature map, and recognize facial expressions by extracting the difference information between it and different expression images; however, this technical solution does not distinguish between expressionless faces and specific expressions when extracting intra-class change features

[0005] "Modifiedclassification and regression tree for facial expression recognition with using difference expression images" published by Du Lingshuang et al. on Electronics letters (2017) proposes facial expression recognition based on the differential image information between a specific expression face and an expressionless face; However, the technical solution is to directly use image difference for recognition, which will lose a lot of information. Although the intra-class variation features are extracted, it is easy to lose some important information that can be used for recognition.

Images