Face Recognition Based On Improved WPCA

The automatic human face recognition is a technology that using computer to analyze the human face images and extracting effective features from the human face images, then to recognize them. Compared with other biometric methods, such as fingerprint, palm, iris, and DNA, human face recognition is more friendly, direct, and imitate to humane. Therefore, in recent years, face recognition is getting more and more attention.Although in these years, many algorithms are developed in face recognition, there is no single model could work perfectly. Though reading and doing research in this field, I find that getting two or more algorithms together could work mor betterl. Therefore, in my research, I developed the improved WPC and based on it, using LDA into the algorithm and did some experiment.The total work of the paper research includes:1.I developed an improved WPCA algorithm. Based on the previous algorithm PCA, I developed a new core function to stress the key points of humane face and found the best parameters in the algorithm.2. I did the research. Based on the improved WPCA, I make it as the first step of the multi-algorithm, and then, I put LDA sorting roles to determine the results. The purpose of the experiment is to find whether this multi-algorithm can work better than a single model. The result proved that, under the same situation, it really gets better. Also, I did the improved WPCA and LDA in the multi-algorithm research.