Dynamic-footprint based person identification using mat-type pressure sensor

Many diverse methods have been developing in the field of biometric identification as human-friendliness has been emphasized in the intelligent system's area. And one of emerging method is to use human walking behavior. But, in the previous methods based on human gait, stable somewhat long-term walking data are an essential condition for person recognition. Therefore, these methods are difficult to cope with various change of walking velocity which may be generated frequently during real walking. In this paper, we suggest a new method which uses just one-step walking data from mat-type pressure sensor. When a human walk through the pressure sensor, we get quantized COP (center of pressure) trajectory and HMM (hidden Markov model) is used to make probability models for user's each foot. And then, HMMs for two feet are combined for better performance by Levenberg-Marquart learning method. Finally, we prove the usefulness of the suggested method using 8 people recognition experiments.