Gait recognition using linear time normalization

Nikolaos V. Boulgouris, Konstantinos N. Plataniotis, Dimitrios Hatzinakos

Abstract: We present a novel system for gait recognition. Identity recognition and verification are based on the matching of linearly time-normalized 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 8–20% in recognition and verification performance are seen in comparison to other known methodologies on the “Gait Challenge” database.