Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Score-level fusion using generalized extreme value distribution and DSmT, for multi-biometric systems

  • Author(s): Renu Sharma 1, 2 ; Sukhendu Das 3 ; Padmaja Joshi 1
    • View affiliations
  • Source: Volume 7, Issue 5, September 2018, p. 474 – 481
    DOI:  10.1049/iet-bmt.2017.0076 , Print ISSN 2047-4938, Online ISSN 2047-4946
© The Institution of Engineering and Technology
Received 04/06/2017, Accepted 23/01/2018, Revised 13/01/2018, Published 12/02/2018

Human recognition in a multi-biometric system is performed by combining biometric clues from different sources (multiple sensors, units, algorithms, samples and modalities) at different levels (sensor, feature, score, rank and decision level). Low computational complexity and adequate data for fusion make the score-level fusion a preferable option over other levels of fusion. However, incompatibility issue prevails at this level as scores obtained from different uni-biometric systems are disparate in nature. This disparity can be resolved by using score normalisation before fusion. This study first analysed the effect of generalised extreme value distribution-based score normalisation technique on different fusion techniques and then proposes an efficient score fusion technique based on Dezert–Smarandache theory (DSmT). A unique blend of belief assignment and decision-making methods in the DSmT framework is proposed for score-level fusion. For evaluation of the proposed method, experiments are performed on multi-algorithm, multi-unit and multi-modal biometrics systems created from three publicly available datasets: (i) NIST BSSR1 multi-biometric score database, (ii) face recognition grand challenge (FRGC) V2.0 and (iii) LG4000 iris dataset. Comparative studies of performance analysis show the efficiency of the authors’ proposed method over other recently published state-of-the-art fusion methods.

Inspec keywords: sensor fusion; computational complexity; face recognition; iris recognition; biometrics (access control)

Other keywords: generalised extreme value distribution; extreme value distribution-based score normalisation technique; NIST BSSR1 multi-biometric score database; biometric clues; multibiometric systems; human recognition; computational complexity; LG4000 iris dataset; Dezert-Smarandache theory; DSmT; FRGC; uni-biometric systems; face recognition grand challenge; score-level fusion

Subjects: Image recognition; Computational complexity; Computer vision and image processing techniques; Sensor fusion; Data security

References

    1. 1)
      • 21. Liang, Y., Ding, X., Liu, C., et al: ‘Combining multiple biometric traits with an order-preserving score fusion algorithm’, Neurocomputing, 2016, 171, pp. 252–261.
    2. 2)
      • 45. Dempster, A.P.: ‘A generalization of Bayesian inference’ Journal of the Royal Statistical Society, 1968, vol. 30, pp. 73–104.
    3. 3)
      • 47. Dubois, D., Prade, H.: ‘On the unicity of Dempster rule of combination’, Int. J. Intell. Syst., 1986, 1, (2), pp. 133–142.
    4. 4)
      • 12. Chaa, M., Boukezzoula, N.-E., Attia, A.: ‘Score-level fusion of two-dimensional and three-dimensional palmprint for personal recognition systems’, J. Electron. Imaging, 2017, 26, p. 13018.
    5. 5)
      • 8. Ross, A., Jain, A., Nandakumar, K.: ‘Score normalization in multimodal biometric systems’, Pattern Recognit., 2005, 38, (12), pp. 2270–2285.
    6. 6)
      • 39. Abbas, N., Chibani, Y., Hadjadji, B.: ‘A DSmT based combination systems for handwritten signature verification’, in Smarandache, F., Dezert, J. (Eds.): ‘Advances and applications of DSmT for information fusion. Collected works’, (American Research Press, United States, 2015), vol. 4, pp. 423–440.
    7. 7)
      • 18. Marval, P.L.R., Aoyama, S., Ito, K., et al: ‘Score level fusion of multibiometrics using local phase array’. Advances in Multimedia Information Processing, 2015, vol. 9315.
    8. 8)
      • 25. Safavi, S., Mporas, I.: ‘Improving performance of speaker identification systems using score level fusion of two modes of operation’. International Conference on Speech and Computer, 2017 (LNCS, 10458), pp. 438–444.
    9. 9)
      • 24. Castrillón-Santana, M., Lorenzo-Navarro, J., Ramón-Balmaseda, E.: ‘Multiscale score level fusion of local descriptors for gender classification in the wild’, Multimedia Tools Appl.., 2017, 76, (4), pp. 4695–4711.
    10. 10)
      • 14. Zheng, L., Wang, S., Tian, L., et al: ‘Query-adaptive late fusion for image search and person re-identification’. IEEE Conf. Computer Vision and Pattern Recognition, June 2015.
    11. 11)
      • 34. Nguyen, K., Denman, S., Sridharan, S., et al: ‘Score-level multibiometric fusion based on Dempster–Shafer theory incorporating uncertainty factors’, IEEE Trans. Hum.-Mach. Syst., 2015, 45, (1), pp. 132–140.
    12. 12)
      • 15. Kabir, W., Ahmad, M.O., Swamy, M.N.S.: ‘Score reliability based weighting technique for score-level fusion in multi-biometric systems’. IEEE Winter Conf. Applications of Computer Vision, 2016, pp. 1–7.
    13. 13)
      • 38. Vatsa, M., Singh, R., Noore, A., et al: ‘On the dynamic selection of biometric fusion algorithms’, IEEE Trans. Inf. Forensics Sec., 2010, 5, (3), pp. 470–479.
    14. 14)
      • 40. Jasang, A., Munch-Maller, T.H.: ‘Biometric data fusion based on subjective logic’. Int. Conf. Information Fusion, 2014, pp. 1–8.
    15. 15)
      • 27. Artabaz, S., Sliman, L., Benatchba, K., et al: ‘Score level fusion scheme in hybrid multibiometric system’. Advances in Visual Informatics: Int. Visual Informatics Conf., 2015, pp. 166–177.
    16. 16)
      • 7. LG 4000 iris image database. Available at http://biometrics.idealtest.org/, 2002.
    17. 17)
      • 54. Duda, R.O., Hart, P.E., Stork, D.G.: ‘Pattern classification’ (Wiley, United States, 2000, 2nd edn.).
    18. 18)
      • 49. Smets, P.: ‘The combination of evidence in the transferable belief model’, IEEE Trans. Pattern Anal. Mach. Intell., 1990, 12, (5), pp. 447–458.
    19. 19)
      • 32. Kisku, D.R., Sing, J.K., Gupta, P.: ‘Multibiometrics belief fusion’. Int. Conf. Machine Vision, 2009, pp. 37–40.
    20. 20)
      • 50. Saaty, R.W.: ‘The analytic hierarchy process – what it is and how it is used’, Math. Model., 1987, 9, (3), pp. 161–176.
    21. 21)
      • 44. He, M., Horng, S.-J., Fan, P., et al: ‘Performance evaluation of score level fusion in multimodal biometric systems’, Pattern Recognit., 2010, 4, (5), pp. 1789–1800.
    22. 22)
      • 35. Smarandache, F., Dezert, J.: ‘Advances and applications of DSmT for information fusion’, vol. 3 (American Research Press, United States, 2009), pp. 760.
    23. 23)
      • 19. Nandakumar, K., Chen, Y., Dass, S.C., et al: ‘Likelihood ratio-based biometric score fusion’, IEEE Trans. Pattern Anal. Mach. Intell., 2008, 30, (2), pp. 342–347.
    24. 24)
      • 48. Voorbraak, F.: ‘On the justification of Dempster's rule of combination’, Artif. Intell., 1991, 48, (2), pp. 171–197.
    25. 25)
      • 42. Fakhar, K., Aroussi, M.E., Saidi, M.N., et al: ‘Fuzzy pattern recognition-based approach to biometric score fusion problem’, Fuzzy Sets Syst., 2016, 305, pp. 149–159.
    26. 26)
      • 41. Wasnik, P., Schafer, K., Ramachandra, R., et al: ‘Fusing biometric scores using subjective logic for gait recognition on smartphone’. Int. Conf. Biometrics Special Interest Group, 2017, pp. 1–5.
    27. 27)
      • 33. Mezai, L., Hachouf, F.: ‘Score-level fusion of face and voice using particle swarm optimization and belief functions’, IEEE Trans. Hum.-Mach. Syst., 2015, 45, (6), pp. 761–772.
    28. 28)
      • 31. Singh, R., Vatsa, A., Noore, M., et al: ‘Dempster–Shafer theory based classifier fusion for improved fingerprint verification performance’, Comput. Vis., Graph. Image Process., 2006, 4338, pp. 941–949.
    29. 29)
      • 53. Gutschoven, B., Verlinde, P.: ‘Multi-modal identity verification using support vector machines (SVM)’, Information Fusion, 2000, vol. 2, pp. 3–8.
    30. 30)
      • 6. Phillips, P.J., Flynn, P.J., Scruggs, T., et al: ‘Overview of the face recognition grand challenge’. Computer Vision and Pattern Recognition, 2005, vol. 1, pp. 947–954.
    31. 31)
      • 5. NIST: ‘Biometric scores set (BSSR1)’. Available at https://www.nist.gov/itl/iad/image-group/nist-biometric-scores-set-bssr1, 2004.
    32. 32)
      • 29. Al-Ani, A., Mohamed, D.: ‘A new technique for combining multiple classifiers using the Dempster–Shafer theory of evidence’, J. Artif. Intell. Res., 2002, 17, pp. 333–361.
    33. 33)
      • 22. Ben-Yacoub, S., Abdeljaoued, Y., Mayoraz, E.: ‘Fusion of face and speech data for person identity verification’, IEEE Trans. Neural Netw., 1999, 10, (5), pp. 1065–1074.
    34. 34)
      • 37. Vatsa, M., Singh, R., Noore, A.: ‘Unification of evidence-theoretic fusion algorithms: a case study in level-2 and level-3 fingerprint features’, IEEE Trans. Syst., Man Cybern. A, Syst. Hum., 2009, 39, (1), pp. 47–56.
    35. 35)
      • 1. Scheirer, W., Rocha, A., Micheals, R., et al: ‘Robust fusion: extreme value theory for recognition score normalization’. European Conf. Computer Vision, 2010, pp. 481–495.
    36. 36)
      • 17. Dass, S.C., Nandakumar, K., Jain, A.K.: ‘A principled approach to score level fusion in multimodal biometric systems’. Audio and Video-Based Biometric Person Authentication, 2005 (LNCS, 3546), pp. 1049–1058.
    37. 37)
      • 46. Zadeh, L.A.: ‘A simple view of the Dempster–Shafer theory of evidence and its implication for the rule of combination’, AI Mag., 1986, 7, (2), pp. 85–90.
    38. 38)
      • 16. Artabaz, S., Sliman, L., Dellys, H.N., et al: ‘Multibiometrics enhancement using quality measurement in score level fusion’, in Janusz, K. (Ed.): ‘Advances in intelligent systems and computing’, vol. 557 (Springer, 2017), pp. 1287–1297.
    39. 39)
      • 3. Fragoso, V., Sen, P., Rodriguez, S., et al: ‘EVSAC: accelerating hypotheses generation by modeling matching scores with extreme value theory’. IEEE Int. Conf. Computer Vision, 2013, pp. 2472–2479.
    40. 40)
      • 20. Mukherjee, S., Pal, K., Majumder, B.P., et al: Differential evolution based score level fusion for multi-modal biometric systems, Computational Intelligence in Biometrics and Identity Management (CIBIM), 2014, pp. 38–44.
    41. 41)
      • 23. Ross, A.A., Nandakumar, K., Jain, A.K.: ‘Handbook of multibiometrics (international series on biometrics’ (Springer-Verlag, New York, Inc., Secaucus, NJ, USA, 2006).
    42. 42)
      • 4. Gibert, X., Patel, V.M., Chellappa, R.: ‘Sequential score adaptation with extreme value theory for robust railway track inspection’. IEEE Int. Conf. Computer Vision Workshops, 2015, pp. 131–138.
    43. 43)
      • 43. Sharma, R., Das, S., Joshi, P.: ‘Score normalization in multimodal systems using generalized extreme value distribution’. British Machine Vision Conf. (BMVC), 2015, vol. 1, pp. 131.1–131.12.
    44. 44)
      • 52. Bergamini, C., Oliveira, L.S., Koerich, A.L., et al: ‘Combining different biometric traits with one-class classification’, Signal Process., 2009, 89, (11), pp. 2117–2127.
    45. 45)
      • 10. Ross, A., Jain, A.: ‘Information fusion in biometrics’, Pattern Recognit. Lett., 2003, 24, (13), pp. 2115–2125.
    46. 46)
      • 36. Singh, R., Vatsa, M., Noore, A.: ‘Integrated multilevel image fusion and match score fusion of visible and infrared face images for robust face recognition’, Pattern Recognit., 2008, 41, (3), pp. 880–893.
    47. 47)
      • 2. Li, Z., Vinyals, O., Baker, H., et al: ‘Feature learning using generalized extreme value distribution based k-means clustering’. Int. Conf. Pattern Recognition, 2012, pp. 1538–1541.
    48. 48)
      • 9. Snelick, R., Uludag, U., Mink, A., et al: ‘Large-scale evaluation of multimodal biometric authentication using state-of-the-art systems’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (3), pp. 450–455.
    49. 49)
      • 28. Shafer, G.: ‘A mathematical theory of evidence’ (Princeton University Press, Princeton, 1976).
    50. 50)
      • 13. Eisenbach, M., Kolarow, A., Vorndran, A.: ‘Evaluation of multi feature fusion at score-level for appearance-based person re-identification’. Int. Joint Conf. Neural Networks, 2015, pp. 469–476.
    51. 51)
      • 26. Zheng, Y., Blasch, E.: ‘An exploration of the impacts of three factors in multimodal biometric score fusion: score modality, recognition method, and fusion process’, J. Adv. Inf. Fusion, 2014, 9, (2), pp. 124–137.
    52. 52)
      • 11. Connaughton, R., Bowyer, K.W., Flynn, P.J.: ‘Fusion of face and iris biometrics’ (Handbook of Iris Recognition, Springer London, 2016), pp. 397–415.
    53. 53)
      • 30. Mezai, L., Hachouf, F., Bengherabi, M.: ‘Score fusion of face and voice using Dempster–Shafer theory for person authentication’. Intelligent Systems Design and Applications (ISDA), 2011, pp. 894–899.
    54. 54)
      • 51. Brunelli, M.: ‘Introduction to the analytic hierarchy process’, in (Eds.): ‘Springer briefs in operations research’ (Springer International Publishing, United States, 2015), p. 83.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2017.0076
Loading

Related content

content/journals/10.1049/iet-bmt.2017.0076
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address