Unsupervised feature selection method for improved human gait recognition

Abstract

Gait recognition is an emerging biometric technology which aims to identify people purely through the analysis of the way they walk. The technology has attracted interest as a method of identification because it is non-invasiveness since it does not require the subject's cooperation. However, 'covariates' which include clothing, carrying conditions, and other intra-class variations affect the recognition performances. This paper proposes an unsupervised feature selection method which is able to select most relevant discriminative features for human recognition to alleviate the impact of covariates so as to improve the recognition performances. The proposed method has been evaluated using CASIA Gait Database (Dataset B) and the experimental results demonstrate that the proposed technique achieves 85.43 % of correct recognition.