Parametric Curve Based Human Gait Recognition

In this paper we institute a baseline technique for human identification based on their body structure and gait. This paper presents a unique human identification system based on self-extracted gait biometric features. Recurring gait analysis is done to deduce key frames from the gait sequence. The gait features extracted are height, hip, neck and knee trajectories of the human silhouette from the body structure Here, we propose two new parametric curves Beizer curve and hermite curve, based on gait pattern. The projected approach has been applied on the SOTON covariate database, which comprises eleven subjects. The testing samples are compared to training samples using normalized correlation, and subject classification is performed by nearest neighbor matching among correlation scores. From the conducted experimental results, it can be accomplished that the stated approach is successful in human identification.