detection and rectification of distorted fingerprints
V.Arul Prakash,G.Aswini Priya,S.Kumar
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:4 Issue:3 Year: 30 March,2016 Pages:584-592
Abstract
A major cause for false non-match of fingerprints is due to elastic distortion. This problem affects all fingerprint recognition applications, while it is especially dangerous in negative recognition applications, such as watchlist and deduplication applications. Malicious users may purposely distort their fingerprints to evade identification in such applications. To detect and rectify skin distortion, here a novel based approach over a single fingerprint image is used. A two-class classification problem for distortion detection includes, a feature vector for which the registered ridge orientation map and period map of a fingerprint and a SVM classifier is trained to perform the classification task. Distortion rectification (or equivalently called as distortion field estimation) is viewed as a regression problem, where the input is a distorted fingerprint and the output is the distortion field. A database (called reference database) of various distorted reference fingerprints and corresponding distortion fields is built in the offline stage, and then in the online stage, after which the nearest neighbor of the input fingerprint is found in the reference database and the corresponding distortion field is used to transform the input fingerprint into a normal one to overcome the regression problem. Promising results have been obtained on three sample databases containing many distorted fingerprints, namely the Fingerprint Verification Contest Database, Tsinghua Distorted Fingerprint database, and the National Institute of Standards and Technology latent fingerprint database.
Kewords
Fingerprint, distortion, registration, nearest neighbor regression, PCA.
Reference
[1] Alonso-Fernandez F., Big€un J. Fierrez-Aguilar J., Fronthaler H., Gonzalez-Rodriguez, Kollreider J. K., and, Ortega-Garcia J. “A comparative study of fingerprint image-quality estimation methods,” IEEE Trans. Inf. Forensics Security, vol. 2, no. 4, pp. 734–743, Dec. 2007. [2] Baveja M., and Wein L. M. “Using fingerprint image quality to improve the identification performance of the U.S. visitor and immigrant status indicator technology program,” Proc. Nat. Acad. Sci. USA, vol. 102, no. 21, pp. 7772–7775, 2005. [3] Bolle R. M., Dorai C., and Ratha N. K. “Dynamic behavior analysis in compressed fingerprint videos,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 1, pp. 58–73, Jan. 2004. [4] Bolle R. M., Germain R. S., Garwin R. L., Levine J. L., Pankanti S. U., Ratha N. K., and Schappert M. A. “System and method for distortion control in live-scan inkless fingerprint images,” U.S. Patent No. 6 064 753, May 16, 2000.
