Real-Time Face Tracking and Recognition Based on Particle Filtering and AdaBoosting Techniques

摘要

In this paper, a real-time face tracking and recognition system based on particle filtering and AdaBoosting techniques is presented. Regarding the face tracking, we develop an effective particle filter to locate faces in image sequences. Since we have considered the hair color information of a human head, the particle filter will keep tracking even if the person is back to the line of sight of a camera. We further adopt both the motion and color cues as the features to make the influence of the background as low as possible. A new fashion of classification architecture trained with an AdaBoost algorithm is also proposed to achieve face recognition rapidly. Compared to other machine learning schemes, the AdaBoost algorithm can update training samples to deal with comprehensive circumstances, but it need not spend much computational cost. Experimental results reveal that the face tracking rate is more than 97% in general situations and 89% when the face suffering from temporal occlusion. As for the face recognition, the accuracy rate is more than 90%; besides this, the efficiency of system execution is very satisfactory, which reaches 20 frames per second at least.