Research On Face Recognition Algorithm And Its Application

Biometrics is a kind of science and technology using individual physiological or behavioral characteristics to verify identity. It provides a highly reliable and robust approach to the identity recognition. Automatic face detection and recognition is one of the most attention branches of biometrics and it is also the one of the most active and challenging tasks for image processing, pattern recognition and computer vision. It is widely applied in commercial and law area, such as mug shots retrieval, real-time video surveillance in security system and cryptograp in bank and so on. Face recognition has direct, friendly characteristics and it is no psychological obstacle for users. This thesis mainly studies the approaches to face detection and recognition. The main research works and contributions are as the following:1. Face detection based on support vector machine.Face detection problem is firstly proposed as a key step of face recognition system. And with the extensive development of face recognition and advancement of developing practical system, face detect is developing into an independent research field. Up to now, the research of face detection algorithm is rather thorough; however, the multi-pose face detection in complex background is still a difficult problem. In addition, meeting the requirement of both speed and precision in a face detection system is another key issue. We propose a method for face detection based on support vector machine. We construct SVM classifiers to detect faces. The experimental results reveal that the proposed method has accurate detection results and high detection rate on video images.2. Face recognition based on Gabor and support vector machine.Automatic face recognition, though being a hard problem, has a wide variety of applications. Support vector machine (SVM), to which model selection plays a key role, is a powerful technique for pattern recognition problems. Recently lots of researches have been done on face recognition by SVMs and satisfying results have been reported. Firstly, Gabor transformation is used to compute features of an image. Then these features will be input for SVM classifiers. SVMs incorporate with a binary tree recognition strategy are proposed to tackle the multi-class face recognition problem. The FERET face databased is used to evluate the proposed method. Promising results reveal its effectiveness.