Abstract: Through the optimization of the two important part of face recognition system, we proposed a CUDA-based real-time face recognition system. In the face detection phase with Viola-Jones cascade classifier, we implemented and improved novel parallel methodologies of image integral, calculation scan window processing and the amplification and correction of classifiers. In the face recognition phase, we explored the parallelizing of the algorithm and parallelized some part of the testing phase.  In comparison with traditional CPU program, the proposed approach running on an NVIDIA GTX 570 graphics card could respectively achieve 22.42 times speedup in detection phase and 1668.56 times speedup in recognition phase. The recognition speed will increase until it reaches the hardware resource limit. The experimental results demonstrate that the system achieves a good real-time performance.

Key words: face recognition system, face detection, Compute Unified Device Architecture (CUDA), real-time