Hmm-based Gait Identity Recognition

Human identification at a distance has recently gained more and more interests from computer vision researchers. Gait recognition aims essentially to address this problem by identifying people based on the way they walk.In this paper, the frame of gait recognition system and the various methods about gait recognition have been introduced firstly. Then principle and the recognition feature about HMM (Hidden Markov Model) have been detailed introduced. From this foundation, the designed scheme of gait recognition is proposed and simulated by the computer. The research experiments have been done in image preprocessing, training the HMM parameters and identifying from a test sequence. From the results of the experiments, we got a lot of significant conclusions. The real recognition is based on gait database of CASIA. The experimental result show that proposed approach is excellent in accuracy.