Research On Face Recognition Algorithm

Face recognition is one of the key issues in computer vision, pattern recognition and biometrics fields, has very large academic and practical values. In daily life, people knowing each other use most of person's face. Face is the most familiar model in human vision. The visual information reflected by face has important meaning and impact between people's intercommunion and intercourse. Because of its extensive and applied realm, face recognition technique has got the extensive concern with study and become the most potential method of identity recognition. At the same time, it is difficult to implement face recognition using computers. First, human face is a deformable object composed of complex 3D curve surfaces, which is hard to be represented in form of mathematics. Secondly, faces of different persons have the similar structure, and the face images are greatly dependent on ages, illumination and environment.This paper mainly study face extraction and class method, which concept can be summarized as follows:Wavelet transform can fully demonstrate the characters of the target problem and it enjoys the outstanding capability of obtaining comparatively less traits and insensitive to the facial expressions in the face detection.In this paper, Independent Component Analysis (ICA) is presented as an efficient face feature extraction method. ICA is sensitive to high-order statistic in the data and finds not-necessarily orthogonal bases, so it has better identify and reconstruct high-dimensional face image data than Principle Component Analysis (PCA). Conventional ICA algorithms, such as informax algorithm, are time-consuming and sometimes converge difficultly. Informax algorithm need people adjust learning speed. In this paper, a modified Fast - ICA algorithm is developed, which computes faster in many iterations and achieves the corresponding recognition effect of ICA algorithm.Neural networks have been used successfully for face recognition problem. They are learned from the example images and relyed on the techniques from machine learning to find the relevant characteristics of face images. RBF neural networks have fast learning ability and best approximation property. Many researches have used RBF networks for face recognition in respect that they are faster to train than other neural networks and have better performance in verification task. So the RBF neural networks classifier is designed for recognition in this paper. At last, experimental results on the ORL database are shown and discussed.