基于Adaboost算法的人脸疲劳检测  

Face Fatigue Detection Based on Adaboost Algorithm

作　　者：李维维[1] 胡桂明[1] 何龙玲 李铭[1] 

机构地区：[1]广西大学电气工程学院,广西南宁530004

出　　处：《自动化技术与应用》2014年第2期46-48,53,共4页Techniques of Automation and Applications

摘　　要：眼睛状态是人体疲劳最主要和最明显的特征。本文采用肤色和Adaboost方法相结合来进行人脸检测,并在此基础上结合人脸结构的边缘特征及Adaboost方法对眼睛进行精确定位,运用自适应二值化和数学形态学的方法对检测出的图像进行处理提取眼睛状态特征,结合PERCLOS规则及点头率来进行疲劳状态的判定,实验表明,该方法鲁棒性强,速度快,满足人脸疲劳检测的实时性要求。The eyes state is the most important and obvious characteristics of the body fatigue.This paper combine color with Adaboost to detect face,on this basis, combine the edge of the face structure characteristics and Adaboost method to position eyes precisely. Then using adaptive threshold and mathematical morphology method to extract the eye feature. At last, integrating PERCLOS rules and nod to judge the fatigue state. Experiments show that this method is robust, fast speed, and meet the real-time demands.

关 键 词：ADABOOST 人脸检测 人眼检测 PERCLOS 疲劳判别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]