Facial expression recognition method and system based on deep privileged network

Abstract

The invention discloses a facial expression recognition method based on a deep privileged network. The method comprises the following steps: inputting a facial expression picture through a main network, and carrying out the preprocessing of the facial expression picture, thereby obtaining a preprocessed facial expression picture; the main network learns facial expression features to obtain facial expression feature information, and then performs emotion classification on facial expression emotions to obtain emotion classification information; obtaining privilege information through the privilege network, performing privilege learning on the loss function, optimizing parameters of the main network, and obtaining an optimized deep privilege network; inputting a tested facial expression picture into the main network, and preprocessing the tested facial expression picture; the deep privileged network after privileged learning is adopted to extract expression features, emotion classification is achieved, and a facial expression recognition result is obtained; according to the method, the face movement unit is used as privilege information, and a traditional deep network is trained to extract expression features beneficial to recognition, so that the accuracy of face emotion recognition is improved.

Description

technical field [0001] The invention relates to the research field of facial expression recognition, in particular to a method and system for facial expression recognition based on a deep privileged network. Background technique [0002] Existing Facial Expression Recognition Algorithms [0003] Facial expression refers to the expression of various emotional states through the transformation of facial muscles, eye muscles and oral muscles. The six main human emotions: anger, joy, sadness, surprise, disgust, fear, contempt can be reflected by the corresponding facial expressions. Facial expression recognition is the most direct and effective emotion recognition mode. Facial expression recognition (FER), as an important means for computers to identify human emotional states, has a wide range of application scenarios, such as human-computer interaction and game experience. [0004] The task of facial expression recognition is to select the expression state from static face pi...

AI Technical Summary

Problems solved by technology

[0014] At present, the facial expression recognition technology rarely uses the method of privileged information learning, so some methods that can be obtained in the training stage but difficult to obtain in the test stage or require a lot of manpower and material resources, and the cost is extremely high. The problem of obtaining features still needs to be improved

[0015] Existing methods of learning using privileged information only use privileged information in the training process, without considering the impact of different stages of integrating privileged information

[0016] The existing learning using privileged information usually supervises the network through similarity constraints and inequality regularization loss during integration, and fine-tunes it, but does not take into account the different effects of different loss functions on parameter adjustment

Images