3D Fingerprint Identification System

Abstract

Human finger is a three-dimensional object. More real and more fingerprint features will be provided if 3D fingerprint images are available. This chapter thus explores 3D fingerprint features and their applications for personal identification. We define the 3D finger structural features, such as curve-skeleton, sectional curvatures as Level Zero Fingerprint Features in this chapter and investigate their distinctiveness for personal identification. These features are also used to assist fingerprint matching and make contribution to fingerprint recognition by combining with 2D fingerprint features. A series of experiments is conducted to evaluate 3D fingerprint recognition technique based on our established database with 541 fingers. Results show that an accuracy of 84.7 % can be achieved when using 3D curve-skeleton for recognition. The sectional curvatures can be used for human gender classification and an accuracy of 81 % is obtained in our database. An EER of 3.4 % is realized by including Level Zero Features into fingerprint recognition which demonstrates the effectiveness of 3D fingerprint recognition.