Application Study On Feature Abstract Of Face In Complex Background

Face recognition is a new biologic technology of recognition, while the feature abstract of face is the most difficult and popular problem in these area. The feature abstract of face is the core technology of human face recognition. It consists of computer technology, image process technology and pattern recognition technology and so on. This biologic technology of recognition is developing quickly and widely .In this paper, it introduces a method of feature abstract of face in complex background. We create a YIQ Complexion Model to abstract face in complex background and discuss a morphological method of noise removal. It also proposes wavelet analysis process of face and the feature abstract of wavelet image .The technology innovation in this paper follows:Create a YIQ Complexion Model to abstract face in complex background and get a method of no infection of brightness. The experiment shows that it is better than the method of unitary RGB .Study a method of quick location of eyes in black and white imageStudy a method of pretreatment of unitary face image based onwavelet which is more effective .Design two classifier to check the effect of the feature of face. In this experiment, we get the correct result of 97 percent on the condition of ten swatch each person.It introduces the background and sense of feature abstract and tells current study status and method all over the world. It tells the basic theory of wavelet analysis and pattern recognition, the basic method of noise removal , image unitary method and the method of feature abstract of face.At last, it introduces the method of program design under the Visual Studio IDE and analyses the result of arithmetic. Then we reach a conclusion that the method proposed is effective and fast.