Optical flow gradient amplitude characteristic-based subtle facial expression detection method

Abstract

The invention discloses an optical flow gradient amplitude characteristic-based subtle facial expression detection method and relates to processing for identifying a graphic recording carrier. According to the method, face edges are obtained by means of fitting according to face key points, and a face region of interest is extracted; an optical flow field between face image frames in a video sequence is extracted by using a FlowNet2 network; the optical flow gradient amplitude characteristics of the face region of interest are extracted; characteristic distances are calculated and processed, and noise elimination is carried out; and therefore, subtle facial expression detection based on the optical flow gradient amplitude characteristics is completed. According to subtle facial expressiondetection in the prior art, subtle facial expression motion cannot be captured in extracted face image motion features; the features contain excessive interference information, and as a result, the subtle facial expression detection is susceptible to the influence of head deviation, blinking motion, accumulated noise and single-frame noise in feature distance analysis. However, with the method adopted, the above defects in the prior art can be eliminated.

Description

technical field [0001] The technical solution of the present invention relates to the processing for identifying graphic record carriers, in particular to the detection method of human face micro-expression based on the characteristic of optical flow gradient amplitude. Background technique [0002] Facial micro-expression detection is widely used in many fields of national security, clinical medicine and judicial system, such as identifying dangerous persons such as terrorists through facial micro-expression detection, and using facial micro-expression detection training software to treat patients with schizophrenia. Adjuvant treatment, analysis of the criminal's criminal psychology through facial micro-expression detection to help the investigation and interrogation, etc. At present, most of the research work on facial micro-expressions focuses on the recognition of facial micro-expressions. However, the video sequence frames used to recognize facial micro-expressions need...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a face micro-expression detection method based on the optical flow gradient amplitude feature. At first, the method extracts the region of interest of the face by fitting the edge of the face according to the key points of the face, and extracts the video using the FlowNet2 network. The optical flow field between the frames of the face image in the sequence, and then extract the optical flow gradient amplitude feature of the region of interest in the face, and then calculate and process the feature distance and perform noise elimination, and complete the face micro-scale based on the optical flow gradient amplitude feature. Expression detection overcomes the problem that in the prior art of face micro-expression detection, tiny facial micro-expression movements cannot be captured in the extracted face image motion features, and the features contain too much interference information, which is susceptible to head deviation , Eyeblink motion and cumulative noise effects and flaws of single frame noise effects in feature distance analysis

Images