摘要
目的:建立基于计算机的抑郁症肝气郁证患者面部表情及眼神模式识别系统,初步探索抑郁面部表情及眼神与抑郁情绪内心体验关系,寻求直接、准确地测评抑郁情绪的方法。方法:构建抑郁症肝气郁证患者和正常人的基本表情库,采集基本表情和视频,人工标记面部特征点,获得针对特定人的主动外观模型。使用主动外观模型对视频进行处理,跟踪每帧的面部特征点位置。结果:抑郁症肝气郁证患者的偏度值主要集中在0.5~7之间,中位数3.4左右,正常人在1.2`15之间,中位数6.3左右。结论:抑郁症肝气郁证患者的瞳孔波动较弱(目光呆滞),瞳孔内眼角距的绝对值的偏度在3.9以下,有较大概率患有抑郁症肝气郁证,是抑郁面部表情及眼神的主要特征。
Objective:Establishing a recognition system based on the computer of depression of Liver-qi stagnation syndrome patients with facial expressions and eye pattern,preliminary exploration depression facial expression and eyesight and depressive emotion experience, seeking method of direct and accurate evaluation of depression. Method: Construction of basic facial expressions of depression of Liver-qi stagnation patients and normal persons, collecting basic facial expressions and video, manually labeled facial feature points, and obtaining the active appearance model for a specific person. Results: the skewness of value of depression of Liver-qi stagnation mainly concentrated in between 0. 5 -7, median 3.4%, and between 1.2 - 15 median 6. 3 normal people around. Conclusion : Patients with depression of Liver-qi stagnation pupil fluctuation is weak, ( dull eyes), from the inside comer of the eye pupil of absolute value of skewness in 3. 9 below, there is a greater probability of suffering from depression of Liver-qi stagnation is depression facial expressions and the eyes of the main features.
出处
《中国中医基础医学杂志》
CAS
CSCD
北大核心
2017年第2期230-233,共4页
JOURNAL OF BASIC CHINESE MEDICINE
基金
国家自然科学基金青年基金项目(81102738)-抑郁症肝气郁证抑郁眼神识别及其关键指标探索
国家自然科学基金面上项目(81573829)-抑郁症肝气郁证患者抑郁眼神
面部表情和姿态多模态识别及其脑区功能定位
关键词
抑郁症
肝气郁证
面部表情
眼神
Depression
Liver-qi stagnation
Facial expressions
Eye