Improved Fingerprint Enhancement Performance via GPU Programming

  • Raja Lehtihet
  • Wael El Oraiby
  • Mohammed Benmohammed
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 102)

Summary

This paper presents a fast GPU (Graphics Processing Unit) implementation to enhance fingerprint images by a Gabor filter-bank based algorithm. We apply a Gabor filter bank and compute image variances of the convolution responses. We then select parts of these responses and compose the final enhanced image. The algorithm presents a good mapping of data elements and partitions the processing steps into parallel threads to exploit GPU parallelism. The algorithm was implemented on the CPU as well. Both implementations were fed fingerprint images of different sizes and qualities from the FVC2004 DB2 database. We compare the execution speed between the CPU and GPU. This comparison shows that the algorithm is at least 2 times faster on a 112 cores GPU than the CPU.

Keywords

Graphic Processing Unit Gabor Wavelet Fingerprint Image Enhancement Algorithm Graphic Processing Unit Implementation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Maltoni, D., Maio, D., Jain, A.K., Prabhakar, S.: Handbook of Fingerprint Recognition (2003)Google Scholar
  2. 2.
    Rao, A.R.: A taxonomy for texture description and identification. Springer, New York, Inc (1990)MATHGoogle Scholar
  3. 3.
    Kamei, T., Mizoguchi, M.: Image filter design for fingerprint enhancement. In: International Symposium on Computer Vision, p. 109 (1995)Google Scholar
  4. 4.
    Hong, L., Wan, Y., Jain, A.: Fingerprint image enhancement: Algorithm and performance evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 777–789 (1998)CrossRefGoogle Scholar
  5. 5.
    Chikkerur, S., Wu, C., Govindaraju, V.: A systematic approach for feature extraction in fingerprint images. In: Zhang, D., Jain, A.K. (eds.) ICBA 2004. LNCS, vol. 3072, pp. 344–350. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Boukala, N., Rugna, J.D., Monnet, U.J.: Fast and accurate color image processing using 3d graphics cards. In: Proceedings Vision, Modeling and Visualization (2003)Google Scholar
  7. 7.
    Angel, E., Moreland, K.: Fourier Processing in the Graphics Pipeline. In: Integrated Image and Graphics Technologies, pp. 95–110. Kluwer Academic Publishers, Dordrecht (2004)CrossRefGoogle Scholar
  8. 8.
    Jargstorff, F.: A framework for image processing. In: Fernando, R. (ed.) GPU Gems: Programming Techniques, Tips and Tricks for Real-Time Graphics, pp. 445–467. Addison-Wesley, Reading (2004)Google Scholar
  9. 9.
    Fung, J., Mann, S.: Openvidia: parallel gpu computer vision. In: Proceedings of the 13th annual ACM international conference on Multimedia MULTIMEDIA 2005, pp. 849–852. ACM, New York (2005)CrossRefGoogle Scholar
  10. 10.
    Strzodka, R., Telea, A.: Generalized Distance Transforms and skeletons in graphics hardware. In: Proceedings of EG/IEEE TCVG Symposium on Visualization (VisSym 2004), pp. 221–230 (2004)Google Scholar
  11. 11.
    Strzodka, R., Garbe, C.: Real-time motion estimation and visualization on graphics cards. In: Proceedings of the conference on Visualization 2004. VIS 2004, pp. 545–552. IEEE Computer Society Press, Washington, DC, USA (2004)Google Scholar
  12. 12.
    Werlberger, M., Trobin, W., Pock, T., Wedel, A., Cremers, D., Bischof, H.: Anisotropic Huber-L1 optical flow. In: Proceedings of the British Machine Vision Conference (BMVC), London, UK (September 2009)Google Scholar
  13. 13.
    Werlberger, M., Pock, T., Bischof, H.: Motion estimation with non-local total variation regularization. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA (June 2010)Google Scholar
  14. 14.
    Nvidia, Cuda presentation (2004), http://www.nvidia.com/object/what_is_cuda_new.html
  15. 15.
  16. 16.
    group, K.: Opencl khronos group (2011), http://www.khronos.org/opencl/
  17. 17.
    Hong, L., Jain, A.K., Pankanti, S., Bolle, R.: Fingerprint enhancement. Tech. Rep. MSU-CPS-96-45, Department of Computer Science, Michigan State University, East Lansing, Michigan (1996)Google Scholar
  18. 18.
    Bernard, S., Boujemaa, N., Vitale, D., Bricot, C.: Fingerprint segmentation using the phase of multiscale gabor wavelets (2002)Google Scholar
  19. 19.
    FVC2004, Fingerprint database (2004), http://bias.csr.unibo.it/fvc2004/
  20. 20.
    Sumanaweera, T.: Medical image reconstruction with the fft. In: GPU Gems 2: Programming Techniques for High-Performance Graphics and General-Purpose Computation (Gpu Gems), Addison-Wesley, Reading (2005)Google Scholar
  21. 21.
    Bainville, E.: Opencl fast fourier transform (2010), http://www.bealto.com/gpu-fft_dft.html
  22. 22.
    Jain, A.K., Prabhakar, S., Hong, L., Pankanti, S.: Filterbank-based fingerprint matching. IEEE Transactions on Image Processing (9), 846–859 (2000)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Raja Lehtihet
    • 1
  • Wael El Oraiby
    • 2
  • Mohammed Benmohammed
    • 3
  1. 1.Computer Science DepartmentConstantineAlgeria
  2. 2.AIFU Ltd.MontrealCanada
  3. 3.LIRE LaboratoryConstantineAlgeria

Personalised recommendations