Journal of Intelligent and Robotic Systems

, Volume 40, Issue 1, pp 103–112 | Cite as

Fast Robust Fingerprint Feature Extraction and Classification

  • H. O. Nyongesa
  • S. Al-Khayatt
  • S. M. Mohamed
  • M. Mahmoud

Abstract

Automatic identification of humans based on their fingers is still one of the most reliable identification methods in criminal and forensic applications. Identification by fingerprint involves two processes: fingerprint feature extraction and feature classification. The basic idea of fingerprint feature extraction algorithms proposed is to locate the coarse features of fingerprints called singular-points using directional fields of the fingerprint image. The features are then classified by different types of neural networks. The “five-class” classification problem is addressed on the NIST-4 database of fingerprints. A maximum classification accuracy of 93.75% was achieved and the result shows a performance comparable to previous studies using either coarse features or the finer features called minutiae.

fingerprint classification directional fields fingerprint feature extraction neural network classifiers 

References

  1. Candela, G. T., Grother, P. J.,Watson, C. I.,Wilkinson, R. A., and Wilson, C. L.: 1995, A pattern-level classification automation system for fingerprints (PCASYS), NIST Technical Report NISTIR 5647, August 1995.Google Scholar
  2. Cappelli, R., Lumini, A., Maio, D., and Maltoni, D.: 1999, Fingerprint classification by directional image partitioning, IEEE Trans. Pattern Anal. Mach. Intell. 21(5), 402-421.Google Scholar
  3. Jain, A. K., Prabhakar, S., and Hong, L.: 1999, A multi-channel approach to fingerprint classification, IEEE Trans. Pattern Anal. Mach. Intell. 21(4), 348-358.Google Scholar
  4. Lam, L., Lee, S. W., and Suen, C. Y.: 1992, Thinning methodologies a comprehensive survey, IEEE Trans. Pattern Anal. Mach. Intell. 14(9), 869-885.Google Scholar
  5. Maio, D. and Maltoni, D.: 1996, A structural approach to fingerprint classification, in: Proc. of 13th ICPR, Vienna, pp. 578-585.Google Scholar
  6. Marcialis, G. L., Roli, F., and Frasconi, P.: 2001, Fingerprint classification by combination of flat and structural approaches, in: Lecture Notes in Computer Scince 2091, pp. 241-246.Google Scholar
  7. Merthe, B. M., Murthy, N. N., Kapoor, S., and Chatterjee, B.: 1998, Segmentation of fingerprint images using the directional image, Pattern Recognition 20(4), 429-435.Google Scholar
  8. NIST-National Institute of Standards and Technology, http://www.nist.gov/srd/nistsd.htm.Google Scholar
  9. Tojo, A. and Kawagoe, M.: 1984, Fingerprint pattern classification, Pattern Recognition 18(3), 201-210.Google Scholar
  10. Yao, Y., Frasconi, P., and Pontil, M.: 2001, Fingerprint classification with combinations of support vector machines, in: Lecture Notes in Computer Science 2091, pp. 253-258.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • H. O. Nyongesa
    • 1
  • S. Al-Khayatt
    • 2
  • S. M. Mohamed
    • 2
  • M. Mahmoud
    • 2
  1. 1.Department of Computer ScienceUniversity of BotswanaBotswana
  2. 2.School of Computing and Management SciencesSheffield Hallam UniversityBotswana

Personalised recommendations