Research On Face Detection And Recognition Method Based On Skin Color

Biometric identification technology is a kind of technology using individual biometric characteristics to verify identity. The biometric characteristics that we usually use are fingerprint, iris, face, sound, pace, hand, vein and so on. Competing with fingerprint recognition and iris recognition, face recognition is more direct and friendly. Face recognition technology has wide application aeras in identity verification, file management, video frequency searches and so on.Computer face recognition is a kind of technology using a computer to analyse face image and extract helpful information to identify identities. Face is an alterable form and structure composed of a set of complicated three-dimension curve surfaces. It is hard to be described by mathematics. And faces of different persons have the similar structure. Furthermore, the face images are greatly dependent on ages and photography conditions. This results that the difference between two face images of two different persons taken under the same photography condition is probably less than that between two images of the same person under different conditions. So face recognition is a very challenging problem.The thesis collects and studies lots of papers and reports on human face detection and recognition home and abroad of these years. It has deeply studied the arithmetics of human face detection and recognition technology. The research works main includes things as follows:(1)It has analysed and summarized the research condition of face detection and recognition technology at present. It has studied face detection technology based on skin color and face recognition technology based on singular value decomposition (SVD) and support vector machine (SVM). It has analysed some difficult problems of face detection and recognition technology which desideratly to be solved at present. It has discussed the development trend of face detection and recognition technology.(2) In the part of face detection, it has studied face detection technology based on skin color. First, it has studied the theory which connected to the face detection technology based on skin color, including face image preprocession, color-place translation, skin color modeling and so on. On the basis of these theories, it has studied the face detection system based on skin color. This system mainly includes light compensating, skin color modeling, dilation-and-erasion processing, deleting false area and getting face area. The results proved that this system can perform face detection function for 24 bit RGB images on complex background. And this system has good stability under diversification of light or face.(3)In the part of feature extraction, the thesis focuses on the the methods of independent component analysis (ICA) and singular value decomposition (SVD). And it has designed a feature extraction arithmetic based on the whole and local singular value decomposition.In the part of classification, it has studied the method based on the support vector machine (SVM) and designed a classifying arithmetic based on the support vector machine.