The Research Of Color Face Images Recognition Based On Hamming Neural Network

Over the last several years, with the width spread of face recognition technology in economic field, face recognition (FR) arouses unprecedented attentions and become the hotspot in the area of image recognition and understanding. FR technology is within the research area of pattern recognition, computer vision and image understanding system, automatic face recognition is an identification technology that analyzes face image with computer to get effective recognition information, and is widely used in many field, including safety inspect of airport and other important place, financial business, intelligent Human-Computer-Interface, etc. Compared with other biometric techniques, face recognition has the advantages of being active, secret, continuous, cheap and readily acceptable by the public. Therefore, it's irreplaceable for many applications. Many face recognition methods have been proposed and some commercial products have been appeared.This paper elaborates main theory and technique applied in human face positive images recognition using neural network, compare these methods' excellence and defect, and describes function modules of images recognition . This paper put forward a method for face recognition based on statistical character. It's useful by experimentation. Firstly, in order to eliminate unrelated information in face images, some preprocessing methods are used. This paper elaborates several classical methods for threshold segmentation, and compare these methods' excellence and defect. When a face image is reading into workspace, take generalized binarization image , we adopt an improved neural network based on SOFM, Logistic Feature Map—Neural Network. It's used to resolve non-linear problem of high dimensionality logic space. The image we get has obvious effect. Secondly, extract pure face according to the role. Finally, we adopt an improved hamming network as a face classifier.This system adapt OOA and OOD technique. The experiments are complimented under the environment of Visual Studio.Net 2005 with a face recognition system.This experimentation indicates that the colorized human face images identification technique is effective.