A Delaunay Quadrangle-Based Fingerprint Authentication System With Template Protection Using Topology Code for Local Registration and Security Enhancement

• Published in: IEEE transactions on information forensics and security Vol. 9; no. 7; pp. 1179 - 1192
• Main Authors: Yang, Wencheng, Hu, Jiankun, Wang, Song
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.07.2014; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Artificial intelligence; Authentication; Computer information security; Computer science; control theory; systems; Cryptography; Distortion; Exact sciences and technology; Feature extraction; Fingerprint recognition; Fingerprinting; Fingerprints; Memory and file management (including protection and security); Memory organisation. Data processing; Nonlinear distortion; Nonlinearity; Pattern recognition. Digital image processing. Computational geometry; Security; Similarity; Software; Topology; template protection; Fingerprint; Delaunay quadrangle; topology code; Delaunay triangle; Biometrics; Image registration; Similarity; Delaunay triangulation; Topology; Risk analysis; Alignment; Experimental result; Protection system; Security of data; Metric; Level; Non linear distortion; Computer security; Pattern extraction
• ISSN: 1556-6013; 1556-6021
• DOI: 10.1109/TIFS.2014.2328095

Although some nice properties of the Delaunay triangle-based structure have been exploited in many fingerprint authentication systems and satisfactory outcomes have been reported, most of these systems operate without template protection. In addition, the feature sets and similarity measures utilized in these systems are not suitable for existing template protection techniques. Moreover, local structural change caused by nonlinear distortion is often not considered adequately in these systems. In this paper, we propose a Delaunay quadrangle-based fingerprint authentication system to deal with nonlinear distortion-induced local structural change that the Delaunay triangle-based structure suffers. Fixed-length and alignment-free feature vectors extracted from Delaunay quadrangles are less sensitive to nonlinear distortion and more discriminative than those from Delaunay triangles and can be applied to existing template protection directly. Furthermore, we propose to construct a unique topology code from each Delaunay quadrangle. Not only can this unique topology code help to carry out accurate local registration under distortion, but it also enhances the security of template data. Experimental results on public databases and security analysis show that the Delaunay quadrangle-based system with topology code can achieve better performance and higher security level than the Delaunay triangle-based system, the Delaunay quadrangle-based system without topology code, and some other similar systems.