Difference depth feature-based facial expression recognition method and system

Abstract

The invention provides a difference depth feature-based facial expression recognition method and system and belongs to the pattern recognition technical field. The method includes the following stepsthat: face depth features are extracted from a sample face region frame sequence, and neutral expression frames and peak expression frames are extracted from the sample face region frame sequence according to the face depth features; and the face depth features of the neutral expression frames are subtracted from the face depth features of the peak expression frames of the sample image frame sequence, so that difference depth features can be obtained; and the difference depth features of the sample face region frame sequence and corresponding facial expressions are adopted as training input, so that a facial expression classifier can be obtained through training, and the facial expression classifier is adopted to achieve facial expression classification. According to the difference depth feature-based facial expression recognition method and system of the invention, the concept of difference is introduced into the depth features, and the difference depth features are used to representfacial expressions, and therefore, facial expression information can be preserved as much as possible, and at the same time, individual differences and environmental noises can be eliminated; and thedistinguishing capability of used features for the facial expressions is strong, so that the robustness of facial expression recognition can be improved.

Description

technical field [0001] The invention belongs to the technical field of image processing and pattern recognition, and in particular relates to a facial expression recognition method based on differential depth features. Background technique [0002] Facial expression recognition is a comprehensive subject involving pattern recognition, image processing, artificial intelligence and other disciplines. The so-called facial expression recognition refers to the process of allowing the computer to extract features from a given expression image, and combine the prior knowledge of humans to carry out learning, reasoning, and judgment, and then understand the process of human emotions. Facial expression recognition has application value in many fields, including robotics, human-computer interaction, intelligent transportation, intelligent education, animation production, etc., and is a current research hotspot. [0003] Deep learning is a new field in machine learning research. It or...

AI Technical Summary

Problems solved by technology

At present, a lot of research has been carried out in this field, but there are still problems such as low robustness, low precision, and susceptibility to noise interference in expression recognition.

Images