期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2012
卷号：2
期号：12
出版社：S.S. Mishra
摘要：C In today's scenario security is very important issue in real life. Security is very much related with the biometric term. Face is one o f the main features of biometric. So, this paper is related with the face detection only. In this paper, we address the problem of face detection in still images. We propose a fast algorithm for detecting human faces in colour images. The algorithm uses skin colour modelling in conjunction with half template matching to quickly locate faces in a given image. The proposed algorithm has been verified theoretically and is found to be quite satisfactory. This paper presents a new face detection method which combines the Skin Colour Detector and the Half Face Template Matching Method. First we can use the skin Colour Detector to find the faces. In the Skin Colour Detector, we can use the YCbCr model. The YCbCr model can be used to easily detect the Skin colour or Non-Skin colour in the images. But in the Skin Colour Detector, it can also detect the faces or some non-faces. Finally, we can use the Half Face Template Matching Method. This method is used to remove the non-faces and to detect the faces more accurately.
关键词：Skin Colour Modelling; Template Matching; Color Model; Normalization; Chrominannce
