Window based clothing invariant gait recognition

Appearance based gait recognition becomes more difficult due to changing the gait styles by different cofactors like as cloths, carrying objects, view angles, surfaces and shoes. Out of others clothes is the most challenging issues in this area. Different part based approaches have been defined several effective and redundant body parts which can influence for individual recognition. In this paper we have study the gait by splitting it into very small window chunks and define a random window subspace method (RWSM) for clothing invariant Human gait recognition. Experiments are conducted on large-scale clothing variations OUR TEADMILL dataset B and shows superb performance than others classical gait recognition approaches.