Footprint-based personal recognition.

Abstract

This paper proposes a new method of personal recognition based on footprints. In this method, an input pair of raw footprints is normalized, both in direction and in position for robustness image-matching between the input pair of footprints and the pair of registered footprints. In addition to the Euclidean distance between them, the geometric information of the input footprint is used prior to the normalization, i.e., directional and positional information. In the experiment, the pressure distribution of the footprint was measured with a pressure-sensing mat. Ten volunteers contributed footprints for testing the proposed method. The recognition rate was 30.45% without any normalization (i.e., raw image), and 85.00% with our method.