Research On Method For NIR Face Recognition

Face Recognition as a very important identification technology in biological features identification field has very extensive application prospects in public security, bank system, military, custom etc. It comes down to many important fields such as computer vision, physiology, artificial intelligence, cognitive science, psychology and so on, which is also an extremely potential research subject in pattern recognition and image processing.So far, Face Recognition systems based on visible light get the greatest use, this kind of systems are only used in some particular conditions and easily affected by a series of external factors, such as illumination, pose etc.In recent years, in the light of existing faults of the visible face recognition, some scholars put forward a kind of new face recognition technology in which active near infrared is used. This method can effectively reduce the effects of light which is an unfavorable factor, which so far has become a hot topic in face recognition field in recent years.In the field of near infrared face recognition, there are a variety of algorithms, such as PCA, LBP, DBC etc, these algorithms have many advantages, but at the same time there are also some disadvantages, such as the aspect of the recognition rate etc, according to these situations, this thesis proposes a kind of new near infrared (NIR) face recognition algorithm based on Contourlet and SVM.The main research contents of this thesis are as follows:Firstly, this thesis lists some common biological features, briefly summarizes the application field and prospect of biological recognition technology and the general content of face recognition technology, analyzes the research background and current situation of the development of face recognition technology at home and abroad;and then makes a brief introduction of the advantages of face recognition systems, the research significance of face recognition systems and the application fields of face recognition systems. In order to reduce or eliminate some unfavorable factors to face recognition systems, we propose a kind of face recognition scheme which is based on near-infrared face images.Secondly, face recognition technology, the basic framework of face recognition systems, the typical commercial face recognition systems and products and the existing face recognition methods are briefly introduced. Face recognition technology as a kind of the most intuitive and most natural biological visual recognition technology is playing a more and more important rile in our life.Nextly, this thesis analyzes difficulties of the research of Face Recognition technology and makes a brief summary of the characteristics of infrared face images including thermal infrared and near-infrared face images. Some factors suchas illumination, expressions, postures and so on have become an obstacle which restricts the development of Face Recognition technology.This thesis also proves that Face Recognition technology based near-infrared light is a more practical and effective technology and also is an advanced technology which has a good adaptability to illumination and postures, and this thesis also lists some methods of near infrared face rocogn i t. i on.Finally, in response to the problem that the existing face recognition methods yield shortages, this thesis describes a new algorithm for near infrared(NIR) face recognition based on Contourlet transform and support vector machine (SVM). In thi s algori thm, firstly aNIR face image is decomposed into several sub-images via Contourlet transform to obtain characteristic datas, and then SVM is utilized to classify and distinguish.The algorithm effectively combines the feature extraction of Contourlet transform and the classification ability of SVM. The experimental results show the algorithm based on Contourlet transform and SVM is an efficient and accurate face recognition method.