The face detection system based on GPU+CPU desktop cluster

As an important research topic of the pattern recognition and machine vision, the face detection technology has been studied widely in the application area such as the face recognition, new human-computer interaction, information security etc. For these applications have the limitation of the real-time, how to accelerate the speed of the face detection has always been an important topic. In this paper, we developed a single GPU+CPU desktop face detection system which adopts the algorithm of Viola and Jones that is based on the Adaboost learning system, and uses the high data-parallel computing power and the high internal data bandwidth of GPU to achieve the thread-level parallelism. Our experimental results indicate that our system running on a NVIDIA Gefoce GTX260 graphics card could achieve the speed of 12 fps and the detection rate of 92%.