Discrimination Analysis for Model-Based Gait Recognition
Gait has been evaluated as a new biometric through psychological experiments. However, most gait recognition approaches do not give their theoretical or experimental performance predictions. Therefore, the discriminating power of gait as a feature for human recognition cannot be evaluated. In this chapter, a Bayesian based statistical analysis is performed to evaluate the discriminating power of static gait features (body part dimensions). Through probabilistic simulation, we not only predict the probability of correct recognition (PCR) with regard to different within-class feature variance, but also obtain the upper bound on PCR with regard to different human silhouette resolution. In addition, the maximum number of people in a database is obtained given the allowable error rate. This is extremely important for gait recognition in large databases.
KeywordsFeature Vector Gait Recognition Average Recognition Rate Feature Extraction Algorithm Global Match
- 34.Cutting, J.E., Kozlowski, L.T.: Recognition of friends by their walk. Bull. Psychon. Soc. 9, 353–356 (1977) Google Scholar
- 54.Grimson, W.E.L.: Object Recognition by Computer: The Role of Geometric Constraints. MIT Press, Cambridge (1990) Google Scholar
- 90.Kothiyal, K., Tettey, S.: Anthropometry for design for the elderly. Int. J. Occup. Sagety Ergon. 7(1), 15–34 (2001) Google Scholar
- 136.Pheasant, S.: Bodyspace: Anthropometry, Ergonomics and Design. Taylor & Francis, London (1986) Google Scholar