Fusion of Face and Gait for Human Recognition in Video Sequences

Focusing on the application of Intelligent Surveillance, this paper proposes a new approach in which fusion of face and gait is used for human recognition at a distance in video sequences. Hidden Markov Models and Fisherfaces method are primarily applied for gait and face classifier, respectively. And then, the results obtained from the two classifiers are utilized and integrated at match score level. The system is tested on video sequences of 31 individuals which are collected from different directions. The results showed that fusion of face and gait providing a more robust recognition strategy, and it has better recognition performance compared with face-only or gait-only method.