Novel features for silhouette based gait recognition systems

This paper proposes certain features for human gait cycle detection and recognition. The features cover both the categories of holistic and model-based approaches for human gait recognition. A unique feature vector is formed from the spatial-temporal silhouettes and Support Vector Machine (SVM) classifier is used for the identification of individuals through their gait. The present work is concerned with the efficiency of the extracted features. Experimentation on the silhouette samples of publicly available CASIA database has given furnishes promising results.