Research On Parallel Algorithms Of Face Recognition Based On GPU

Face Recognition is one of the most toughest problems in Pattern Recognition and Image Processing field, but its wide range of applications in law, customs, security, and so on, so face recognition attracts more and more research groups and companies.On the other time, as graphics processing unit(GPU) has been developing rapidly recently, various applications about computer graphics have grown greatly. At the same time, the highly processing power, parallelism and programmability available nowadays on the current GPU make the general purpose computation available.This paper proposes a novel approach named Gabor feature based two-pass classifier of face recognition: for the feature extraction part, Gabor feature are used; for the classifier design part, Two-pass Classification method with Biomimetic Pattern Recognition and Error Correcting SVMs is used. The HENN is used for the first classification to get the intermediate result, and the SVM with error correction method is used to solve the intermediate result and all the training samples for the second classification. It has the advantages of both biomimetic pattern recognition method and the SVM method with error correction ability, the first is that it can avoid the high false recognition rate, and the second is that it has the error correction ability, so it outperforms either of the two methods and reaches a higher recognition rate. But the time consuming on Gabor feature extraction, training of HENN and SVM is very long both for ORL and AR databases.Because of those problems in Two-pass Classification method, this paper raised a fine-grained parallel algorism making the best use of GPU's parallel processing, which converts the process of working-out into the process of texture-rendering based on GPU, making Gabor feature extraction, the training and tesing of HENN and SVM greatly accelerated in it without effecting the recognition rate.