access icon free Efficient fingerprint matching using GPU

© The Institution of Engineering and Technology
Received 02/12/2016, Accepted 29/10/2017, Revised 15/09/2017, Published 30/10/2017

Graphical processing unit (GPU) has proven a beneficial tool in handling computationally intensive algorithms, by introducing massive parallelism in the calculations. In this study, an effective and low-cost fingerprint identification (FI) solution is proposed that can exploit the parallel computational power of GPU proficiently. It is achieved by mapping a generalised minutia neighbour-based novel encoding and matching algorithm on low-cost GPU technology. The proposed solution achieves high accuracy in comparison with two open source matchers and it is shown to be scalable by comparing matching performance on different GPUs. The proposed GPU implementation employs multithreading and loop unrolling, which minimises the use of nested loops and avoids sequential matching of encoded minutia features. After a thorough and careful designing of data structures, memory transfers and computations, a GPU-based fingerprint matching system is developed. It achieves on average 50,196 fingerprint matches per second on a single GPU. As compared to the sequential central processing unit implementation, the proposed system achieves a speed up of around 92 times, while maintaining the accuracy. The proposed system with matcher integrated on GPU can be considered as a good, low-cost, robust and efficient solution for large-scale applications of automated FI systems.

Inspec keywords: fingerprint identification; multi-threading; graphics processing units; image sequences; image matching; data structures; image coding

Other keywords: loop unrolling; computationally intensive algorithms; multithreading; automated FI system; graphical processing unit; fingerprint identification; open source matcher; minutia neighbour-based novel encoding algorithm; sequential central processing; fingerprint matching algorithm; nested loop minimisation; GPU technology; parallel computational power

Subjects: Image recognition; Image and video coding; Microprocessors and microcomputers; Microprocessor chips; Computer vision and image processing techniques

References

    1. 1)
      • 5. Ratha, N.K., Karu, K., Chen, S., et al: ‘A real-time matching system for large fingerprint databases’, IEEE Trans. Pattern Anal. Mach. Intell., 1996, 18, (8), pp. 799–813.
    2. 2)
      • 29. Rakvic, R., Broussard, R., Ngo, H.: ‘Energy efficient iris recognition with graphics processing units’, IEEE Access, 2016, 4, pp. 2831–2839.
    3. 3)
      • 40. Watson, C.I., Garris, M.D., Tabassi, E., et al: ‘User's guide to NIST biometric image software (NBIS)’. National Institute of Standards and Technology, January 2007.
    4. 4)
      • 33. Broussard, R.P., Rakvic, R.N., Ives, R.W.: ‘Accelerating iris template matching using commodity video graphics adapters’. IEEE Int. Conf. Biometrics: Theory, Applications and Systems, Crystal City, VA, September 2008, pp. 1–6.
    5. 5)
      • 16. Cappelli, R., Ferrara, M.: ‘A fingerprint retrieval system based on level-1 and level-2 features’, Expert Syst. Appl., 2012, 39, (12), pp. 10465–10478.
    6. 6)
      • 11. Tico, M., Kuosmanen, P.: ‘Fingerprint matching using an orientation-based minutia descriptor’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, (8), pp. 1009–1014.
    7. 7)
      • 38. Tico, M., Kuosmanen, P.: ‘An algorithm for fingerprint image post processing’. 34th Asilomar Conf. Signals, Systems, and Computers, 29 October 2000.
    8. 8)
      • 1. Maltoni, D., Maio, D., Jain, A.K., et al: ‘Handbook of fingerprint recognition’ (Springer, New York, 2009, 2nd edn.).
    9. 9)
      • 12. Feng, J.: ‘Combining minutiae descriptors for fingerprint matching’, Pattern Recognit., 2008, 41, (1), pp. 342–352.
    10. 10)
      • 19. Rakvic, R.N., Ngo, H., Broussard, R.P., et al: ‘Comparing an FPGA to a cell for an image processing application’, EURASIP J. Adv. Signal Process., 2010, 2010, (1), Article ID 764838, pp. 1–7.
    11. 11)
      • 15. Cappelli, R., Ferrara, M., Maltoni, D.: ‘Fingerprint indexing based on minutia cylinder code’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 33, (5), pp. 1051–1057.
    12. 12)
      • 14. Cappelli, R., Ferrara, M., Maltoni, D.: ‘Minutia cylinder-code: a new representation and matching technique for fingerprint recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (12), pp. 2128–2141.
    13. 13)
      • 2. Jain, A.K., Ross, A., Prabhakar, S.: ‘An introduction to biometric recognition’, IEEE Trans. Circuits Syst. Video Technol., 2004, 14, (1), pp. 4–20.
    14. 14)
      • 34. Gutiérrez, P.D., Lastra, M., Herrera, F., et al: ‘A high performance fingerprint matching system for large databases based on GPU’, IEEE Trans. Inf. Forensics Sec., 2014, 9, (1), pp. 62–71.
    15. 15)
      • 28. Crookes, D., Boyle, K., Miller, P., et al: ‘GPU implementation of the affine transform for 3D image registration’. 13th Int. Conf. Machine Vision and Image Processing, September 2009, pp. 151–155.
    16. 16)
      • 3. Henry, E.: ‘Classification and uses of fingerprints’ (Routledge, London, 1900).
    17. 17)
      • 4. Jain, A.K., Feng, J., Nagar, A., et al: ‘On matching latent fingerprints’. Proc. CVPR Workshop on Biometrics, June 2008, pp. 1–8.
    18. 18)
      • 25. ‘NVIDIA CUDA C programming guide’. Available at http://docs.nvidia.com/cuda/cuda-c-programming-guide.pdf, accessed January 2016.
    19. 19)
      • 21. Jiang, R.M., Crookes, D.: ‘FPGA-based minutia matching for biometric fingerprint image database retrieval’, J. Real-Time Image Proc., 2008, 3, (3), pp. 177–182.
    20. 20)
      • 9. Jea, T.Y., Govindaraju, V.: ‘A minutia-based partial fingerprint recognition system’, Pattern Recognit., 2005, 38, (10), pp. 1672–1684.
    21. 21)
      • 37. Ghafoor, M., Taj, I.A., Jafri, M.N.: ‘Fingerprint frequency normalisation and enhancement using two-dimensional short-time Fourier transform analysis’, IET Comput. Vis., 2016, 10, (8), pp. 806–816.
    22. 22)
      • 18. Yang, L., Chiu, S.C., Liao, W.K., et al: ‘High performance data clustering: a comparative analysis of performance for GPU, RASC, MPI, and OpenMP implementations’, J. Supercomput., 2014, 70, (1), pp. 284–300.
    23. 23)
      • 24. ‘NVIDIA CUDA’. Available at http://www.NVIDIA.com/object/cuda_home_new.htm, accessed January 2016.
    24. 24)
      • 27. Lastra, M., Mantas, J.M., Ureña, C., et al: ‘Simulation of shallow-water systems using graphics processing units’, Math. Comput. Simul., 2009, 80, (3), pp. 598–618.
    25. 25)
      • 31. Vandal, N.A., Savvides, M.: ‘CUDA accelerated iris template matching on graphics processing units (GPUs)’, Biometrics: Theory Appl. Syst. (BTAS), 2010, pp. 1–7.
    26. 26)
      • 36. Wang, W., Li, J.W., Huang, F.F., et al: ‘Design and implementation of log-Gabor filter in fingerprint image enhancement’, Pattern Recognit. Lett., 2008, 29, (3), pp. 301–308.
    27. 27)
      • 39. ‘Fingerprint Verification Competition 2002’. Available at http://bias.csr.unibo.it/fvc2002, accessed January 2016.
    28. 28)
      • 7. He, Z., Zhao, X., Zhang, S.: ‘Low-quality fingerprint recognition using a limited ellipse-band-based matching method’, J. Opt. Soc. Am. A, 2015, 32, (6), pp. 1171–1179.
    29. 29)
      • 6. Jie, Y., Fang, Y.Y., Renjie, Z., et al: ‘Fingerprint minutiae matching algorithm for real time system’, Pattern Recognit., 2006, 39, (1), pp. 143–146.
    30. 30)
      • 30. Chouchene, M., Sayadi, F.E., Bahri, H., et al: ‘Optimized parallel implementation of face detection based on GPU component’, Microprocess. Microsyst., 2015, 39, (6), pp. 393–404.
    31. 31)
      • 32. Gajdos, P., Platos, J., Moravec, P.: ‘Iris recognition on GPU with the usage of non-negative matrix factorization’. Tenth Int. Conf. Intelligent Systems Design and Applications (ISDA), November 2010, pp. 894–899.
    32. 32)
      • 23. ‘NVIDIA Corporation, Santa Clara, CA, USA’. Available at http://www.NVIDIA.com, accessed January 2016.
    33. 33)
      • 26. Friedrichs, M., Eastman, P., Vaidyanathan, V., et al: ‘Accelerating molecular dynamic simulation on graphics processing units’, J. Comput. Chem., 2009, 30, (6), pp. 864–872.
    34. 34)
      • 17. Peralta, D., Triguero, I., Sanchez-Reillo, R., et al: ‘Fast fingerprint identification for large databases’, Pattern Recognit., 2014, 47, (2), pp. 588–602.
    35. 35)
      • 22. Betkaoui, B., Thomas, D.B., Luk, W.: ‘Comparing performance and energy efficiency of FPGAs and GPUs for high productivity computing’. Int. Conf. Field-Programmable Technology (FPT), December 2010, pp. 94–101.
    36. 36)
      • 8. Jiang, X., Yau, W.Y.: ‘Fingerprint minutiae matching based on the local and global structures’. Proc. 15th Int. Conf. Pattern Recognition, 2000, vol. 2, pp. 1038–1041.
    37. 37)
      • 10. Ratha, N.K., Pandit, V.D., Bolle, R.M., et al: ‘Robust fingerprint authentication using local structural similarity’. Proc. Workshop on Applications of Computer Vision, 2000, pp. 29–34.
    38. 38)
      • 13. Chikkerur, S., Cartwright, A.N., Govindaraju, V.: ‘K-plet and CBFS: a graph based fingerprint representation and matching algorithm’. Proc. Int. Conf. Biometrics, Hong Kong, January 2006, pp. 309–315.
    39. 39)
      • 35. Ghafoor, M., Taj, I.A., Ahmed, W., et al: ‘Efficient 2-fold contextual filtering approach for fingerprint enhancement’, IET Image Process., 2014, 8, (7), pp. 417–425.
    40. 40)
      • 20. Lindoso, A., Entrena, L., Izquierdo, J.: ‘FPGA-based acceleration of fingerprint minutiae matching’. Proc. Third Southern Conf. Programmable Logic, Mar del Plata, Argentina, 2007, pp. 81–86.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.1021
Loading

Related content

content/journals/10.1049/iet-ipr.2016.1021
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading