Utilizing Graphics Processing Units for rapid facial recognition using video input

We propose a facial recognition method that is implemented utilizing a Graphics Processing Unit (GPU) to accelerate the processing time for a single frame of an input video sequence. When working with live streaming data, the processing speed that a particular frame is processed is a significant factor. A fast processing speed is necessary so that a recognition method can keep up with the frame rate of the video sequence. GPU computing is an ideal method to accelerate recognition processing. By implementing components of a facial recognition method on a Tesla C2050 GPU, we achieve a method that runs up to six times faster than a pure CPU implementation of the method. We evaluate these implementations using live streaming data and find that the GPU implementation achieves a greater accuracy and performance over the CPU implementation.