Dynamic footprint-based person recognition method using a hidden markov model and a neural network

Abstract

Many diverse methods have been developed in the field of biometric identification as a greater emphasis is placed on human friendliness in the area of intelligent systems. One emerging method is the use of footprint shape. However, in previous research, there were some limitations resulting from the spatial resolution of sensors. One possible method to overcome this limitation is through the use of additional and independent information such as gait information during walking. In this study, we suggest a new person-recognition scheme based on the center of pressure (COP) trajectory in the dynamic footprint. To make an efficient and automated footprint-based person recognition method using the COP trajectory, we use a hidden Markov model and a neural network. Finally, we demonstrate the usefulness of the suggested method, obtaining an approximately 80% recognition rate using only the COP trajectory in our experiment with 11 people. © 2004 Wiley Periodicals, Inc. Int J Int Syst 19: 1127–1141, 2004.