Human Face Recognition Method Based On Artificial Neural Network

An accurate automatic personal identification is critical to a wide range of application domains such as access control, electronic commerce, and welfare benefits disbursement. Traditional personal identification methods (e .g., passwords, PIN) suffer from a number of drawbacks and are unable to satisfy the security requirement of our highly inter-connected information society. Biometrics refer to automatic identification technology of an individual based on their physiological traits such as fingerprint, face and iris or behavioral traits such as signature, speech and gait. Currently, there are many biometric techniques that are widely used. A biometric system is essentially a pattern recognition system, which makes a personal identification by establishing the authenticity of a specific physiological or behavioral characteristic of the user.As one of the most successful applications of image analysis and understanding, Facere cognition has recently received significant atention, especially during the few Years. Presently, the research about face recognition is mainly in two ways. One is based on the method of transcendent knowledge including template matching and face rules, the other is based on the method of learning and training. Hard to extract characters and accessible to light and accouterment are the main difficulties of face recognition technology.Presently, the research about face recognition is mainly in two ways. One is based on the method of transcendent knowledge including template matching and face rules, the other is based on the method of learning and training. Hard to extract characters and accessible to light and accouterment are the main difficulties of face recognition technology.Face recognition is to detect human faces and provide the exact coordinate of each face in still images or video sequences, regardless of diferent location, orientation, size, pose, lighting condition. As a key technology in human face processing, face recognition is of great importance in the field of security protection, ROI-based coding, content-based image retrieval, automatic video surveillance, human computer interface, etc. Now, face recognition is one of the most active research fields of patern recognition and computer vision.With the great efforts taken by researchers all over the world, face recognition can now achieve a usable recognition rate and speed. However, human face is a nature structure with highly complicated variations in detail, which bring great challenges to the performance of detection algorithm. These kinds of variations lie in pose, facial expression, partial occlusion, lighting condition, rotation, etc. Besides, human faces are always compounded with a complex background. Due to all of these dificulties, there is no such an algorithm that can handle all these variations without any kind of limitation at present.The research of face recognition advanced from simple image process to complex real-time video process. However, face recognition is a most challenging task because of the complicated patern and the frangibility of human face, most methods have the weakness of large computation, low eficiency and many false reports among the detection result; but Viola present a fast face recognition method based on AdaBoost learning algorithm in 2001, which made PC can see human face via camera.We can use integral image to quickly calculate the feature, and construct weak classifier by the feature; then weak classifiers are combined to a strong classifier in a linear way. The final classifier is built in a cascade structure, which could reject most non-face samples in the early layer. But as a new method, AdaBoost also need deeply development.Human skin color has been proven to be an effective feature and widely used in face recognition in resent years. The results of experiment show that this recognition approach features a rapid inspecting speed and is insensitive to the face posture. But how to improve the performance of the skin detector is a challenging problem.Face is a nonrigid object with complex modes. Although a human can easily recognition of a human face, the automatic human recognition for a machine is very difticult. After a survey for human patern features and all kinds of human recognition algorithms, a conclusion can be drawn that an efficient and robust algorithm must be one method which has been combined with muti-cues and facial features. Moreover, Human detection automatically is the first important step in a fully automatic human face recognition system.Generally, face recognition consists of three parts: preprocessing of the face images, feature extraction and selection from face, and classification.In this paper, we present a new system based on artificial neural network for face recognition. Clustering is a major tool used in a number of applications, such as analyzing gene expression data, data mining, image processing, web mining, hypothesis generation, hypothesis testing, prediction based on groups and so on. Competitive learning neural network is the main method for clustering analysis. To solve the problems in the competitive layer, an added and deleted competitive neural network is proposed in this paper. Its unsupervised learning method is based on the Hebbian postulate and a new competitive learning method is adopted. The main idea of learning is that the similarity level decides the rewarded and penalized rate. To overcome the dead units problems it adds new neuron when it is necessary to constitute a new cluster. After learning, another important task of it is detecting whether there are wrong clusters, if it finds one, it will delete the cluster and combine its elements with the cluster which is the most similar cluster to the wrong cluster, and thus the result of clustering is more accurate.