Combining 2D and 3D hand geometry features for biometrie verification

Traditional hand geometry based personal verification systems offer limited performance and therefore suitable only for small scale applications. This paper investigates a new approach to achieve performance improvement for hand geometry systems by simultaneously acquiring three dimensional features from the presented hands. The proposed system utilizes a laser based 3D digitizer to acquire registered intensity and range images of the presented hands in a completely contact-free manner, without using any hand position restricting mechanism. Two new representations that characterize the local features on the finger surface are extracted from the acquired range images and are matched using the proposed matching metrics. The proposed approach is evaluated on a database of 177 users, with 10 hand images for each user acquired in two sessions. Our experimental results suggest that the proposed 3D hand geometry features have significant discriminatory information to reliably authenticate individuals. Our experimental results also demonstrate that the combination of 3D hand geometry features with 2D geometry features can be employed to significantly improve the performance from 2D hand geometry features alone.