Biometric personal authentication by one step foot pressure distribution change by fuzzy artificial immune system

This paper proposes a biometric personal authentication method based on one step foot pressure distribution change. We acquire the foot pressure distribution change by mat type load distribution sensor and use it as a personal authentication. We employ twelve features based on shape of footprint, and twenty seven features based on movement of weight while walking. A classifier for each feature is developed on the basis of fuzzy inference. The classifier is trained by a clonal selection algorithm in artificial immune system. A personal authentication system for one step is made every classifier for all features. We employed 10 volunteers, and we took the step data five times. We evaluated our method by five-fold cross validation method. We obtained low false rejection and acceptance rates in identification and verification.