作者: Kap-Ho Seo , Won Kim , Changmok Oh , Ju-Jang Lee
DOI: 10.1109/ISIE.2002.1026332
关键词: Face (geometry) 、 Active contour model 、 Computer vision 、 Template matching 、 Pattern recognition 、 Feature extraction 、 Computer science 、 Face detection 、 Facial recognition system 、 Artificial intelligence 、 Image segmentation 、 Feature (computer vision)
摘要: Face detection and facial feature extraction is a necessary first-step in face recognition systems. These tasks are one of the visual tasks, which humans can do effortlessly. However, computer vision terms, this task not easy. This paper presents new active contour model using color information for extracting features. We describe algorithm detecting human faces features, such as location eyes, nose mouth. The composed three main parts: region estimation part, part part. In images segmented based on skin color. template matching method used. proposed called snake"" applied to extract points within estimated region.""