Real-Time Face Recognition Method Based on the Threshold Determination of the Positive Face Sequence
Xin Ling Shi, Jian Wu, Xin Ling, Qiaoli Zheng, Xuan-qi Pan, Zhiqiang Zhao · Atlantis Press eBooks · 2016
Most of the current face recognition methods are not able to ensure the accuracy and real-time performance at the same time. In this paper, a real-time face recognition method based on the threshold determination of the positive face sequence is proposed. The procedure of the proposed method is as following. Firstly, the faces with different angles are detected and tracked. At the same time, the angle and position information of the faces is recorded. Secondly, the faces in different frames are matched. Then the positive faces which are matched as the same person are recognized. Finally, the final results are obtained by using the threshold determination method. The experimental results indicate that this algorithm has good recognition rates in the case of the moderate flow density and is able to satisfy the requirement of the real-time system.