An artificial intelligence-based evaluation system for eyelid movement function

Abstract

The invention discloses an artificial intelligence-based eyelid movement abnormality evaluation system, which includes: a subject acquisition module: used to obtain a facial video containing only the subject from the input facial action video of the subject; eyes and Designated part positioning module: used to locate the eyes and designated parts of the facial video, and obtain eye movement video and designated part linkage video including only the subject under inspection; TSN model: used to process eye movement video and designated part linkage Video and output the action signals of eyes and designated parts; Probability output module: used to output the probability signal of each frame of the computer to judge the occurrence of abnormal eyelid movement; evaluation module, used to judge according to the probability signal of abnormal eyelid movement and the probability of abnormal eyelid movement Mechanisms gain anomalous levels. The invention has universal acceptability, convenience, accuracy, objectivity and repeatability, and has strong clinical applicability.

Description

technical field [0001] The present invention relates to the field of evaluation of abnormal degree of eyelid movement, and more particularly relates to an artificial intelligence-based eyelid movement function evaluation system. Background technique [0002] Existing techniques for observing eyelid movement abnormalities mainly include neuromuscular recorder technology, brainstem magnetic resonance angiography (MRA) examination, and wearing new glasses that record the frequency function of eyelid movement. The disadvantages of neuromuscular recorder technology are that the technical operation is complicated, time-consuming and labor-intensive, and the cooperation degree is low for the elderly and children; Therefore, the measurement results are easily affected by the subjective factors of the testers, the results lack repeatability and stability, and it is difficult to carry out early inspections on a large scale in the population. Brainstem magnetic resonance angiography (...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to solve the technical problems that the existing abnormal eyelid movement detection equipment has high requirements for the test environment, detection equipment and detection personnel, the cost of manpower and material resources is high, and the detection results are one-sided and not accurate enough; Acceptability, convenience, objectivity, accuracy and repeatability, clinically usable eyelid motor function assessment system based on artificial intelligence

Images