Fusion of gait and fingerprint for user authentication on mobile devices

Abstract

A new multi-modal biometric authentication approach using gait signals and fingerprint images as biometric traits is proposed. The individual comparison scores derived from the gait and fingers are normalized using four methods (min-max, z-score, median absolute deviation, tangent hyperbolic) and then four fusion approaches (simple sum, user-weighting, maximum score and minimum core) are applied. Gait samples are obtained by using a dedicated accelerometer sensor attached to the hip. The proposed method is evaluated using 7200 fingerprint images and gait samples. Fingerprints are collected by a capacitive line sensor, an optical sensor with total internal reflection and a touch-less optical sensor. The fusion results of these two biometrics show an improved performance and a large step closer for user authentication on mobile devices.