Abstract
Many modern pattern recognition methods depend on having an algorithm for direct pixelwise matching of two images, and such algorithms cannot be developed unless one knows the nature of imaged objects. To solve the problem of pixelwise matching of two impressions of one fingertip, we employ methods that derive from the theory of elastic deformations. The proposed approach is based on numerical solution of PDEs describing elastic body mechanics. The recognition statistics obtained on standard fingerprint datasets show roughly a twofold reduction of the false rejection rate for constant values of false acceptance rate, when the method of direct alignment is used.
Similar content being viewed by others
References
L. D. Landau and E. M. Lifshitz, Theory of Elasticity: Course of Theoretical Physics (Butterworth-Heinemann Edition, 1995).
A. M. Bazen and S. H. Gerez, “Thin-Plate Spline Modeling of Elastic Deformation in Fingerprints,” Proc. of 3rd IEEE Benelux Signal Processing Symposium, 2002.
F. L. Bookstein, “Principal Warps: Thin-Plate Splines and the Decomposition of Deformations,” IEEE Trans. PAMI 11(6), 567–585 (1989).
R. Cappelli, D. Maio, and D. Maltoni, “Modeling Plastic Distortion in Fingerprint Images,” ICAPR2001, pp. 369–376.
R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis (Wiley, New York, 1973).
M. Fornefett, K. Rohr, and H. S. Stiehl, “Radial Basis Functions with Compact Support for Elastic Registration of Medical Images,” Image Vis. Comput. 19(1–2), 87–96 (2001).
FVC2002, the Second International Competition for Fingerprint Verification Algorithms (FVC2000); bias.csr.unibo.it/fvc2002/.
H. C. Lee and R. E. Gaenssley, Advances in Fingerprint Technology (Elsevier, New York, 1991).
S. O. Novikov and G. N. Glushchenko, “Fingerprint Ridges Structure Generation Models,” 6th Int. Workshop on Digital Image Processing and Computer Graphics, Vienna, October 20–22, 1997, Proc. SPIE, Vol. 3346.
O. Ushmaev and S. Novikov, “Registration of Elastic Deformations of Fingerprint Images with Automatic Finding of Correspondences,” Proc. MMUA03, Santa Barbara, CA, 2003, pp. 196–201.
US Patent No. 6 282 304.
C. L. Wilson, C. I. Watson, M. D. Garris, and A. Hicklin, Studies of Fingerprint Matching Using the NIST Verification Test Bed (VTB); available at ftp://sequoyah.nist.gov/pub/nist_internal_reports/ir_7020.pdf.
Author information
Authors and Affiliations
Additional information
The methods for ED registration were developed under a contract with the Biolink Technologies Inc. The study of general models of identification via direct matching was supported by the Russian Foundation for Basic Research, project no. 04-01-00270.
Rights and permissions
About this article
Cite this article
Novikov, S.O., Ushmaev, O.S. Effect of elastic deformation registration in fingerprint identification. Pattern Recognit. Image Anal. 16, 15–18 (2006). https://doi.org/10.1134/S1054661806010056
Received:
Issue Date:
DOI: https://doi.org/10.1134/S1054661806010056