基于序列图像融合的人脸图像增强方法分析-analysis of face image enhancement method based on sequence image fusion.docxVIP

Research of Face Image Enhancement Method Based on Sequence Image FusionAbstractAt present, the electronic video surveillance system is widely used in traffic monitoring and scheduling, security monitoring inside and outside of the building, security control of the banking system and so on. In the application of security monitoring, the face recognition based on sequence image is often dynamic images recognition , and its characteristic is that pose, glasses, accessories, illumination, imaging angle and the imaging distance is random and dynamic, which is affected the accuracy of face recognition. In order to solve this problem, seriously considering the interference of illumination and poses, this paper proposed a face image sequence enhancement algorithm based on dynamic image sequence information form face detection, normalization, image pretreatment and image fusion.First of all, the face detection method based on skin color model and geometric feature was used to make the face separated from the sequence image and get rid of the background, hair, clothes and other redundant information. Secondly, different methods were used to realize gray normalization according to the face image difference in the gray level resulted form different light conditions; and geometric normalization based on eyes location was completed according to the difference in the geometric location resulted from different poses and scale; then in order to evaluate the results after normalization, the correlation coefficient was adopted to make similarity detection on the sequence image after normalization; And then, the sequence of face image after normalization was fused by three different fusion rules based on wavelet transform. Finally, image quality evaluation for the result of image enhancement was made by the subjective and objective evaluation method.When it came to validating the method of this enhancement based on sequence image fusion, three kinds of face image and three fu