作者: Yingyu Ji , Shigang Wang , Yang Lu , Jian Wei , Yan Zhao
DOI: 10.1117/1.JEI.27.5.051205
关键词: Face (geometry) 、 Feature extraction 、 RGB color model 、 Cluster analysis 、 Segmentation 、 Human eye 、 Image segmentation 、 Iris recognition 、 Computer science 、 Algorithm
摘要: Eye and mouth state analysis is an important step in fatigue detection. An algorithm that analyzes the of eye by extracting contour features proposed. First, face area detected acquired image database. Then, eyes are located EyeMap through a clustering method to extract sclera-fitting calculate aspect ratio. In addition, effective proposed solve problem fitting when human affected strabismus. Meanwhile, value chromatism s defined RGB space, accurately lip segmentation. Based on color difference lip, skin, internal mouth, can be fitted analyze opening mouth; at same time, another unique yawning judgment mechanism considered determine whether driver tired. This paper based three different databases evaluate performance algorithm, it does not need training with high calculation efficiency.