Gait recognition using image self-similarity

TitleGait recognition using image self-similarity
Publication TypeJournal Articles
Year of Publication2004
AuthorsBenAbdelkader C, Cutler RG, Davis LS
JournalEURASIP J. Appl. Signal Process.
Volume2004
Pagination572 - 585
Date Published2004/01//
ISBN Number1110-8657
Keywordsbehavioral biometrics, gait recognition, human identification at a distance, human movement analysis, pattern recognition
Abstract

Gait is one of the few biometrics that can be measured at a distance, and is hence useful for passive surveillance as well as biometric applications. Gait recognition research is still at its infancy, however, and we have yet to solve the fundamental issue of finding gait features which at once have suffcient discrimination power and can be extracted robustly and accurately from low-resolution video. This paper describes a novel gait recognition technique based on the image self-similarity of a walking person. We contend that the similarity plot encodes a projection of gait dynamics. It is also correspondence-free, robust to segmentation noise, and works well with low-resolution video. The method is tested on multiple data sets of varying sizes and degrees of diffculty. Performance is best for fronto-parallel viewpoints, whereby a recognition rate of 98% is achieved for a data set of 6 people, and 70% for a data set of 54 people.

URLhttp://dx.doi.org/10.1155/S1110865704309236
DOI10.1155/S1110865704309236