A challenge to biometrics by sole pressure while walking

This paper describes a personal verification method based on fuzzy logic using dynamic sole pressure distribution while walking. The method employs a pair id sole pressure distribution change, and it is acquired by a mat type load distribution sensor. As a preliminary experiment for shoes, we take sole pressure data by bare foot and two kind of slippered foot. We extract thirty nine gait features from each sole pressure distribution change. We calculate a fuzzy degree of a feature from two fuzzy if-then rules and them fuzzy membership functions for a feature. These fuzzy membership functions are statistically determined by learning data. The fuzzy degree of acquisition sole pressure data is calculated by total of fuzzy degree of all features. The method verifies the walking person by using the fuzzy degree of the acquisition sole pressure data. When the fuzzy degree of acquisition data higher than a threshold, we verify the walking person as the target person. In our experiments, we employed 11 volunteers and took sole pressure data six times for each volunteer and foot situation. When the learning data included same kind of test data, we obtained low equal error rate. We obtained low false acceptance rate.