Lightweight unconstrained facial expression recognition method and system embedded with high-order information

Abstract

The invention relates to the field of unconstrained facial expression recognition, in particular to a lightweight unconstrained facial expression recognition method and system embedded with high-order information, and the method comprises the steps: carrying out the preprocessing and image enhancement of input data, inputting the data into a lightweight feature extraction network, and extracting a deep feature map of a facial expression image; inputting the deep feature map into the input of a second-order effective channel attention module, counting the second-order information of the deep expression features and capturing the interdependence relationship between the cross-channel features; using cross entropy loss and center loss to jointly optimize the network model; inputting a to-be-detected facial expression image into the trained network model, and outputting a final predicted expression category by the classifier according to facial expression features; the network model provided by the invention has less parameter quantity, lower video memory requirement and calculation amount, does not use additional data pre-training models, is higher in precision, and is higher in applicability of related products.

Description

technical field [0001] The invention relates to the field of unconstrained facial expression recognition, in particular to a lightweight unconstrained facial expression recognition method and system embedded with high-level information. Background technique [0002] Facial expression refers to various emotions expressed through changes in eye muscles, cheek muscles and mouth muscles. Among them, the muscle groups near the eyes and mouth are the most expressive parts of the human face, and they are one of the most powerful, natural and common signals for humans to convey emotions. Facial expression recognition has been extensively studied due to its importance in psychology, medicine, public safety, and business. Since unconstrained facial expression images have many uncertain factors (illumination changes, head poses, identity deviations, and occlusions), the inter-class differences are small, while the intra-class differences are large, which makes unconstrained facial exp...

AI Technical Summary

Problems solved by technology

However, the existing unconstrained facial expression recognition method based on convolutional neural network focuses more on the design of the network structure, ignoring the study of the deep feature correlation between the channels learned by the network, which hinders the strong expressiveness of the neural network extraction. Moreover, the existing methods have the problem of excessive calculation and parameters, and an overly large network model is not conducive to the deployment of mobile terminals and is difficult to meet the needs of the market.

Images