Gait recognition and effect of noise on the recognition rate

Gait is defined to be the coordinated, cyclic combination of movements that result in human locomotion. Gait recognition refers to identify a human by the style/way, a person walks in image sequences. The objective of this paper is to implement the traditional gait recognition algorithm and to show the variation in gait recognition when subject is observed parallel to camera under three conditions- walking normal, carrying a bag and wearing a coat. In this work, we are devising a novel method for the purpose of similarity computation rather than the traditional recognition where 78.57% of overall recognition rate was obtained. Furthermore, noise is introduced to evaluate its effect on the recognition rate. Keywords—Human gait, biometrics, human identification, gait databases, silhouettes