Robust Gait Recognition Based on Collaborative Representation with External Variant Dictionary

Existing methods for gait recognition mainly depend on the appearance of human. Their performances are greatly affected by variation outside of human body. To solve the problem, we proposed a collaborative representation classification (CRC) based approach by which gait under different condition is decomposed into normal gait ingredient and variant ingredient. An external variant dictionary is constructed to linear represent variant. The normal gait ingredient is directly classified by CRC. Experiments on CASIA gait database show that the proposed method achieves a satisfactory recognition result.