The study on fuzzy face recognition of low-quality images

In this paper, an in-depth study is made on the fuzzy face recognition technology based on the shape features. In view of the defects and deficiency of the traditional Active Shape Model (ASM) method in the process of feature extraction, several improved methods are put forward. In the improved algorithm, the initial position is initialized by using the method of pupil localization; in the extraction of the gray scale information of the feature points, a method is designed by forming a circular area centered on the feature points and extracting meaningful pixel information from this area. All of these methods have effectively improved the performance of the ASM method. An experimental analysis is made on the algorithm, and the experimental results show that the modified ASM method has been improved both in the accuracy and in the robustness of fuzzy face recognition.