Advertisement

Cognitive Computation

, Volume 6, Issue 3, pp 446–461 | Cite as

Feature Component-Based Extreme Learning Machines for Finger Vein Recognition

  • Shan Juan Xie
  • Sook YoonEmail author
  • Jucheng Yang
  • Yu Lu
  • Dong Sun Park
  • Bin Zhou
Article

Abstract

This paper proposes an efficient finger vein recognition system, in which a variant of the original ensemble extreme learning machine (ELM) called the feature component-based ELMs (FC-ELMs) designed to utilize the characteristics of the features, is introduced to improve the recognition accuracy and stability and to substantially reduce the number of hidden nodes. For feature extraction, an explicit guided filter is proposed to extract the eight block-based directional features from the high-quality finger vein contours obtained from noisy, non-uniform, low-contrast finger vein images without introducing any segmentation process. An FC-ELMs consist of eight single ELMs, each trained with a block feature with a pre-defined direction to enhance the robustness against variation of the finger vein images, and an output layer to combine the outputs of the eight ELMs. For the structured training of the vein patterns, the FC-ELMs are designed to first train small differences between patterns with the same angle and then to aggregate the differences at the output layer. Each ELM can easily learn lower-complexity patterns with a smaller network and the matching accuracy can also be improved, due to the less complex boundaries required for each ELM. We also designed the ensemble FC-ELMs to provide the matching system with stability. For the dataset considered, the experimental results show that the proposed system is able to generate clearer vein contours and has good matching performance with an accuracy of 99.53 % and speed of 0.87 ms per image.

Keywords

Extreme learning machine Ensemble Feature component Finger vein recognition Guided directional filter 

Notes

Acknowledgments

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No. 2013R1A1A2013778), and by the National Natural Science Foundation of China (No. 61063035).

References

  1. 1.
    Miura N, Nagasaka A, Miyatake T. Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification. Mach Vis Appl. 2004;15(4):194–203.CrossRefGoogle Scholar
  2. 2.
    Miura N, Nagasaka A, Miyatake T. Extraction of finger vein patterns using maximum curvature points in image profiles. IEICE-Trans Inf Syst. 2007;90(8):1185–94.CrossRefGoogle Scholar
  3. 3.
    Song WS, Kim TJ, Kim HC. A finger-vein verification system using mean curvature. Pattern Recogn Lett. 2011;32(11):1541–7.CrossRefGoogle Scholar
  4. 4.
    Hoover A, Kouznetsova V, Goldbaum M. Locating blood vessels in retinal images by piece-wise threshold probing of a matched filter response. IEEE Trans Med Imaging. 2000;19(3):203–10.PubMedCrossRefGoogle Scholar
  5. 5.
    Chaudhuri S, Chatterjee S, Katz N, Nelson M, Goldbaum M. Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE Trans Med Imaging. 1989;8:263–9.PubMedCrossRefGoogle Scholar
  6. 6.
    Gang L, Chutatape O, Krishnan SM. Detection and measurement of retinal vessels in fundus images using amplitude modified second-order gaussian filter. IEEE Trans Biomed Eng. 2000;49:168–72.CrossRefGoogle Scholar
  7. 7.
    Yang WM, Rao Q, Liao QM. Personal identification for single sample using finger vein location and direction coding. In: International conference on hand-based biometrics; 2011. p. 1–6.Google Scholar
  8. 8.
    Wang YD, Li KF, Cui JL, Shark LK, Varley M. Study of hand-dorsa vein recognition. Adv Intell Comput Theor Appl. 2010;6215:490–8.Google Scholar
  9. 9.
    Grassi M, Cambria E, Hussain A, Piazza F. Sentic web: a new paradigm for managing social media affective information. Cogn Comput. 2011;3(3):480–9.CrossRefGoogle Scholar
  10. 10.
    Cambria E, Hussain A. Sentic album: content-, concept-, and context-based online personal photo management system. Cogn Comput. 2012;4(4):477–96.CrossRefGoogle Scholar
  11. 11.
    Cambria E, Hussain A. Sentic computing: techniques, tools, and applications. In: Springer briefs in cognitive computation; 2012.Google Scholar
  12. 12.
    Wang QF, Cambria E, Liu CL, Hussain A. Common sense knowledge for handwritten Chinese recognition. Cogn Comput. 2013;5(2):234–42.CrossRefGoogle Scholar
  13. 13.
    Wu JD, Liu CT. Driver identification using finger-vein patterns with radon transform and neural network. Expert Syst Appl. 2009;36(3):5793–9.CrossRefGoogle Scholar
  14. 14.
    Cao FL, Zhang YQ, He ZR. Interpolation and rate of convergence for a class of neural networks. Appl Math Model. 2009;33(3):1441–56.CrossRefGoogle Scholar
  15. 15.
    Cao FL, Xie TF, Xu ZB. The estimate for approximation error of neural networks: a constructive approach. Neurocomputing. 2009;71(4):626–30.Google Scholar
  16. 16.
    Wu JD, Liu CT. Finger-vein pattern identification using svm and neural network technique. Expert Syst Appl. 2011;38(11):14284–9.Google Scholar
  17. 17.
    Huang G-B, Zhou H, Ding X, Zhang R. Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern Part B Cybern. 2012;42(2):513–29.CrossRefGoogle Scholar
  18. 18.
    Yang JC, Xie SJ, Yoon S, Park DS, Fang Z. Fingerprint matching based on extreme learning machine. Neural Comput Appl. 2012;1:1–11.Google Scholar
  19. 19.
    Xie SJ, Yang JC, Yoon S, Park DS. Intelligent fingerprint quality analysis using online sequential extreme learning machine. Soft Comput. 2012;16(9):1555–68.CrossRefGoogle Scholar
  20. 20.
    Chacko BP, Vimal KVR, Raju G, Babu AP. Handwritten character recognition using wavelet energy and extreme learning machine. Int J Mach Learn Cybern. 2011;3(2):149–61.CrossRefGoogle Scholar
  21. 21.
    Huang GB, Zhu QY, Siew CK. Extreme learning machine: theory and applications. Neurocomputing. 2006;70:489–501.CrossRefGoogle Scholar
  22. 22.
    Huang GB, Ding X, Zhou HM. Optimization method based extreme learning machine for classification. Neurocomputing. 2010;74(12):155–63.CrossRefGoogle Scholar
  23. 23.
    Wang XZ, Dong LC, Yan JH. Maximum ambiguity based sample selection in fuzzy decision tree induction. IEEE Trans Knowl Data Eng. 2011;24(8):1491–505.CrossRefGoogle Scholar
  24. 24.
    Wang XZ, Chen A, Feng HM. Upper integral network with extreme learning mechanism. Neurocomputing. 2011;74(16):2520–5.CrossRefGoogle Scholar
  25. 25.
    Huang GB, Wang D, Lan Y. Extreme learning machines: a survey. Int J Mach Learn Cybern. 2011;2(2):107–22.CrossRefGoogle Scholar
  26. 26.
    Hansen LK, Salamon P. Neural network ensemble. IEEE Trans Pattern Anal Mach Intell. 1990;12:993–1001.CrossRefGoogle Scholar
  27. 27.
    Lan Y, Soh Y, Huang G-B. Ensemble of online sequential extreme learning machine. Neurocomputing. 2009;72:3391–5.CrossRefGoogle Scholar
  28. 28.
    Heeswijk M, Miche Y, Lindh-Knuutila T, Hilbers P, Honkela T, Oja E, Lendasse A. Adaptive ensemble models of extreme learning machines for time series prediction. Lect Notes Comput Sci. 2009;5769:305–14.CrossRefGoogle Scholar
  29. 29.
    Heeswijk M, Miche Y, Oja E, Lendasse A. Gpu accelerated and parallelized elm ensembles for large-scale regression. Neurocomputing. 2011;74:2430–7.CrossRefGoogle Scholar
  30. 30.
    Sun ZL, Choi TM, Au KF, Yu Y. Sales forecasting using extreme learning machine with applications in fashion retailing. Decis Support Syst. 2008;46:411–9.CrossRefGoogle Scholar
  31. 31.
    Duda RO, Hart PE. Use of the hough transform to detect lines and curves in pictures. Commun Assoc Comput Mach. 1972;15(1):11–5.Google Scholar
  32. 32.
    Lee T. Image representation using 2d gabor wavelets. IEEE Trans Pattern Anal Mach Intell. 1996;18(10):959–71.Google Scholar
  33. 33.
    He K, Sun J, Tang X. Guided image filtering. Eur Conf Comput Vis. 2010;1:1–14.Google Scholar
  34. 34.
    Maltoni D, Maio D, Jain AK, Prabhakar S. Handbook of fingerprint recognition. 2nd ed. Berlin: Springer; 2009.CrossRefGoogle Scholar
  35. 35.
    Heisele B, Ho P, Wu J, Poggio T. Face recognition: component-based versus global approaches. Comput Vis Image Underst. 2003;91(12):6–21.CrossRefGoogle Scholar
  36. 36.
  37. 37.
    Wang LY, Leedham G, Cho DSY. Minutiae feature analysis for infrared hand vein pattern biometrics. Pattern Recogn. 2008;41(3):920–9.CrossRefGoogle Scholar
  38. 38.
    Yang GP, Xi XM, Yin YL. Finger-vein recognition based on (2d) 2pca and metric learning. J Biomed Biotechnol. 2012;2012:1–9.Google Scholar
  39. 39.
    Yang GP, Xi XM, Yin YL. Finger vein recognition based on a personalized best bit map. Sensors. 2012;12(2):1738–57.PubMedCentralPubMedCrossRefGoogle Scholar
  40. 40.
    Toh K-A. Deterministic neural classifications. Neural Comput. 2008;20(6):1565–95.PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  • Shan Juan Xie
    • 1
    • 2
  • Sook Yoon
    • 3
    Email author
  • Jucheng Yang
    • 4
  • Yu Lu
    • 2
  • Dong Sun Park
    • 2
    • 5
  • Bin Zhou
    • 1
  1. 1.Institute of Remote Sensing and Earth ScienceHangzhou Normal UniversityHangzhouChina
  2. 2.Division of Electronic and Information EngineeringChonbuk National UniversityJeonjuSouth Korea
  3. 3.Department of Multimedia EngineeringMokpo National UniversityJeonnamSouth Korea
  4. 4.College of Computer Science and Information EngineeringTianjin University of Science and TechnologyTianjinChina
  5. 5.IT Convergence Research CenterChonbuk National UniversityJeonjuSouth Korea

Personalised recommendations