Facial paralysis detection system based on artificial intelligence and muscle model

Abstract

The invention relates to the technical field of computer vision, in particular to a facial paralysis detection system based on artificial intelligence and a muscle model, which comprises a face region division module, a symmetrical region detection module, a unilateral region association module and a facial paralysis detection module which are connected in sequence; the invention solves the problems that the existing facial paralysis detection technology ignores the motion relevance between adjacent areas on one side, and the face area cannot be accurately divided, so that a certain error exists in facial paralysis detection. According to the invention, facial paralysis detection is carried out by using the motion association characteristics between the single-side areas and the symmetrical area characteristics, the accuracy and reliability of facial paralysis detection are improved, weight distribution is realized through the obtained deviation angle vector of each face area, the operation is simple, and the complexity is relatively low; besides, according to the three-dimensional human face muscle model, human face areas are reasonably divided according to different human face muscle distributions, data errors are reduced, and the precision of detection data is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a facial paralysis detection system based on artificial intelligence and muscle models. Background technique [0002] Facial paralysis is a disease mainly characterized by motor dysfunction of facial expression muscles. The general symptoms are skewed mouth and eyes and uncoordinated facial expressions. Due to the lack of control of the facial muscles, people with facial paralysis are often inflexible in their facial movements and experience other symptoms, including drooling, speech difficulties, and nasal congestion. [0003] However, the existing facial paralysis detection methods usually determine facial paralysis based on facial asymmetry or differences, and only roughly divide the face area according to the positions of key points, which not only makes the movement information of facial muscles not reasonably utilized, but also ignores The motor correlation between...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a facial paralysis detection system based on artificial intelligence and muscle models. The technical problem to be solved is that the existing facial paralysis detection technology ignores the motion correlation between adjacent areas on one side, and cannot accurately divide human face areas. lead to certain errors in the detection of facial paralysis

Images