Method of micro facial expression detection based on facial action coding system (FACS)

Abstract

The invention provides a method of micro facial expression detection based on a facial action coding system (FACS). The method has a main content of a visual CNN filter, network architecture and training, migration learning and micro facial expression detection. The method comprises steps: firstly, a robust emotion classification framework is built; the provided network learning model is analyzed; the provided network training filter is visualized in different emotion classification tasks; and the model is applied to micro facial expression detection. The recognition rate of the existing method in micro facial expression detection is improved, the strong correlation between features generated by an unsupervised learning process and action units for a facial expression analysis method is presented, the FACS-based function generalization ability in aspects of providing high-precision score cross data and cross mission is verified, the micro facial expression detection recognition rate is improved, the facial expression can be recognized more accurately, the emotion state is deduced, the effectiveness and the accuracy of application in various fields are improved, and development of artificial intelligence is pushed.

Description

technical field [0001] The invention relates to the field of expression recognition, in particular to a method for micro-expression detection based on a facial action coding system. Background technique [0002] Expression recognition is often used in human-computer interaction, social games, psychological research, assisted driving and other fields to automatically recognize facial expressions and infer emotional states. Specifically, advanced applications such as detection of the smiling face of the subject to start automatic shooting, automatic expression replacement of game players, analysis of user viewing effects of multimedia advertisements, detection of pain and misfortune of patients, and detection of driver drowsiness. Facial expressions play an important role in interpersonal communication and behavior. Although existing methods have met certain accuracy in observing object characteristics and analysis, most current methods only consider local information and igno...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem of insufficient recognition rate of the existing method, the present invention improves the recognition rate of the existing method on micro-expression detection, and demonstrates the strong relationship between the features generated by the unsupervised learning process and the action units used in the facial expression analysis method. Correlation, the generalization ability of FACS-based functions is verified in terms of cross-data and cross-tasks providing high-precision scores, and the recognition rate of micro-expression detection is improved, facial expressions are more accurately recognized and emotional states are inferred, improving its performance in The effectiveness and accuracy of applications in various fields promote the development of artificial intelligence

Images