Gait recognition using linear time normalization

We present a novel system for gait recognition. Identity recognition and verification are based on the matching of linearly timenormalized gait walking cycles. A novel feature extraction process is also proposed for the transformation of human silhouettes into low-dimensional feature vectors consisting of average pixel distances from the center of the silhouette. By using the best-performing of the proposed methodologies, improvements of 8

• Type: Journal
• Year: 2006
• Where: PR
• Authors: Nikolaos V. Boulgouris, Konstantinos N. Plataniotis, Dimitrios Hatzinakos
• Keywords: Gait, Gait Recognition, Low-dimensional Feature Vectors, PR 2006