King's College London

Research portal

Gait recognition using linear time normalization

Research output: Contribution to journalArticlepeer-review

N V Boulgouris, K N Plataniotis, D Hatzinakos

Original languageEnglish
Pages (from-to)969 - 979
Number of pages11
JournalPATTERN RECOGNITION
Volume39
Issue number5
DOIs
PublishedMay 2006

King's Authors

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. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454