On Reducing the Effect of Silhouette Quality on Individual Gait Recognition: A Feature Fusion Approach

The quality of the extracted gait silhouettes can hinder the performance and practicability of gait recognition algorithms. In this paper, we propose a framework that integrates a feature fusion approach to improve recognition rate under this situation. Specifically, we first generate a dataset containing gait silhouettes with various qualities based on the CASIA Dataset B. We then fuse gallery data with different qualities and project data into embedded subspaces. We perform classification based on the Euclidean distances between fused gallery features and probe features. Experimental results show that the proposed framework can provide important improvements on recognition rate.