Computer vision-based facial nerve disease rehabilitation condition static detection system

Abstract

The invention provides a computer vision-based facial nerve disease rehabilitation condition static detection system, which comprises a face detection segmentation module for processing a front-view face image to obtain an eye image and a mouth image, an eye anomaly detection module for obtaining an eye anomaly degree based on an eye white area and a pupil area, a mouth anomaly detection module which is used for obtaining the mouth overall offset, the mouth deformation degree and the mouth corner depth difference, and a rehabilitation effect judgment module which is used for obtaining a plurality of illness state description change curves based on the eye anomaly degree, the mouth overall offset, the mouth deformation degree and the mouth corner depth difference and analyzing the rehabilitation situation of a patient according to the curves. According to the invention, abnormity judgment is carried out on the eyes and the mouth of the patient based on the single-frame image, and interference of asymmetry of the eyes of the normal human face on disease judgment can be avoided, so that the disease of the patient can be judged more accurately, and errors are small.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a computer vision-based static detection system for rehabilitation of facial nerve diseases. Background technique [0002] The most direct external manifestation of facial nerve paralysis is that the eyes and mouth are crooked, that is, facial nerve diseases mostly occur in the eyes and mouth. In the prior art, after the symmetry axis of the face is found, the disease is judged based on the difference in coordinates of the feature points on the left and right sides of the face. However, the overall position of the eyes of the normal human face itself is not symmetrical, and the eyes are not ideally equal in size. This method is easily affected by the asymmetry of the faces of different patients, and the more indicators or feature points are used, the greater the error accumulation will be, which will easily lead to misjudgment. Contents of the invention [0003] In order to sol...

AI Technical Summary

Problems solved by technology

Using this method is easy to be affected by the asymmetry of the face of different patients, and the more indicators or feature points are used, the greater the error accumulation will be, and it is easy to cause misjudgment in the end.

Images