A new approach to unwrap a 3-D fingerprint to a 2-D rolled equivalent fingerprint

  • Authors:
  • Sara Shafaei;Tamer Inanc;Laurence G. Hassebrook

  • Affiliations:
  • Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY;Faculty of Electrical and Computer Engineering Department, University of Louisville, Louisville, KY;Faculty of Electrical and Computer Engineering Department, University of Kentucky, Lexington, KY

  • Venue:
  • BTAS'09 Proceedings of the 3rd IEEE international conference on Biometrics: Theory, applications and systems
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

For many years, fingerprints have been captured by pressing a finger against a paper or hard surface. This touch-based fingerprint acquisition introduces some problems such as distortions and deformations in the acquired images, which arise due to the contact of the fingerprint surface with the sensor platen, and degrades the recognition performance. A new touchless fingerprint technology has been recently introduced to the market, which can address the problems with the contact-based fingerprint systems. In this paper, we propose a new algorithm for unwrapping the acquired 3-D scan of the subject's finger into a 2-D rolled equivalent image. Therefore, The resulting image can be matched with the conventional 2-D scans; it also can be used for matching unwrapped 3-D fingerprints among themselves with the 2-D fingerprint matching algorithms. The algorithm is based on curvature analysis of the 3-D surface. The quality of the resulting image is evaluated and analyzed using NIST fingerprint image software.