access icon free Periocular biometrics: constraining the elastic graph matching algorithm to biologically plausible distortions

In biometrics research, the periocular region has been regarded as an interesting trade-off between the face and the iris, particularly in unconstrained data acquisition setups. As in other biometric traits, the current challenge is the development of more robust recognition algorithms. Having investigated the suitability of the ‘elastic graph matching’ (EGM) algorithm to handle non-linear distortions in the periocular region because of facial expressions, the authors observed that vertices locations often not correspond to displacements in the biological tissue. Hence, they propose a ‘globally coherent’ variant of EGM (GC-EGM) that avoids sudden local angular movements of vertices while maintains the ability to faithfully model non-linear distortions. Two main adaptations were carried out: (i) a new term for measuring vertices similarity and (ii) a new term in the edges-cost function penalises changes in orientation between the model and test graphs. Experiments were carried out both in synthetic and real data and point for the advantages of the proposed algorithm. Also, the recognition performance when using the EGM and GC-EGM was compared, and statistically significant improvements in the error rates were observed when using the GC-EGM variant.

.

Inspec keywords: biometrics (access control); image matching; statistical analysis; graph theory

Other keywords: synthetic data; facial expressions; unconstrained data acquisition; biometric recognition systems; edge-cost function; error rate improvement; globally-coherent EGM algorithm; nonlinear distortion modelling; vertex locations; real data; model graphs; vertex similarity measurement; recognition performance; local angular movement avoidance; periocular region; biologically plausible distortions; test graphs; statistical analysis; biological tissue; GC-EGM algorithm; elastic graph matching algorithm constraint; periocular biometrics

Subjects: Combinatorial mathematics; Other topics in statistics; Computer vision and image processing techniques; Combinatorial mathematics; Image recognition; Other topics in statistics

References

    1. 1)
    2. 2)
    3. 3)
    4. 4)
    5. 5)
    6. 6)
    7. 7)
      • 23. Ross, A., Nandakumar, K., Jain, A.K.: ‘Handbook of multibiometrics’ (Springer-Verlag, New York, 2006).
    8. 8)
    9. 9)
    10. 10)
    11. 11)
    12. 12)
    13. 13)
    14. 14)
    15. 15)
    16. 16)
      • 3. Woodard, D., Pundlik, S., Miller, P., Jillela, R., Ross, A.: ‘On the fusion of periocular and iris biometrics in non-ideal imagery’. Proc. 20th Int. Conf. Pattern Recognition (ICPR), 2010, pp. 201204.
    17. 17)
      • 2. Park, U., Jillela, R., Ross, A., Jain, A.K.: ‘Periocular biometrics in the visible spectrum’, IEEE Trans. Inf. Forensics Sec., 2011, 6, (1), pp. 96106 (doi: 10.1109/TIFS.2010.2096810).
    18. 18)
      • 4. Lades, M., Vorbruggen, J.C., Buhmann, J., et al: ‘Distortion invariant object recognition in the dynamic link architecture’, IEEE Trans. Comput., 1993, 42, (3), pp. 300311 (doi: 10.1109/12.210173).
    19. 19)
      • 7. Stamou, G., Nikolaidis, N., Pitas, I.: ‘Object tracking based on morphological elastic graph matching’. Proc. Int. Conf. Image Processing, 2005, vol. 1, pp. 709712.
    20. 20)
      • 6. Zhao, S., Gao, W., Shan, S., Yin, B.: ‘Enhance the alignment accuracy of active shape models using elastic graph matching’. Proc. First Int. Conf. Biometric Authentication, 2004, pp. 5258.
    21. 21)
      • 14. Kela, N., Rattani, A., Gupta, P.: ‘Illumination invariant elastic bunch graph matching for efficient face recognition’. Proc. Computer Vision and Pattern Recognition Workshop (CVPRW06), 2006, pp. 42.
    22. 22)
      • 24. Santos, G., Proença, H.: ‘A robust eye-corner detection method for real-world data’. Proc. IEEE Int. Joint Conf. Biometrics, 2011, pp. 16.
    23. 23)
      • 15. Shin, H., Kim, S.-D., Choi, H.-C.: ‘Generalized elastic graph matching for face recognition’, Pattern Recognit. Lett., 2007, 28, pp. 10771082 (doi: 10.1016/j.patrec.2007.01.003).
    24. 24)
      • 13. Zafeiriou, S., Pitas, I.: ‘Discriminant graph structures for facial expression recognition’, IEEE Trans. Multimed., 2008, 10, (8), pp. 15281540 (doi: 10.1109/TMM.2008.2007292).
    25. 25)
      • 11. Zafeiriou, S., Tefas, A., Pitas, I.: ‘Exploiting discriminant information in elastic graph matching’. Proc. Int. Conf. Image Processing (ICIP2005), 2005, vol. 3, pp. 768771.
    26. 26)
      • 10. Shin, H.-C., Park, J., Kim, S.-D.: ‘Combination of warping robust elastic graph matching and kernel-based projection discriminant analysis for face recognition’, IEEE Trans. Multimed., 2007, 9, (6), pp. 11251136 (doi: 10.1109/TMM.2007.898933).
    27. 27)
      • 1. Daugman, J.G.: ‘Probing the uniqueness and randomness of IrisCodes: results from 200 billion iris pair comparisons’, Proc. IEEE, 2006, 94, (11), pp. 19271935 (doi: 10.1109/JPROC.2006.884092).
    28. 28)
      • 18. Daugman, J.G.: ‘Complete discrete 2D gabor transform by neural networks for image analysis and compression’, IEEE Trans. Acoust. Speech Signal Process., 1988, 36, (1), pp. 169179.
    29. 29)
      • 9. Tefas, A., Kotropoulos, C., Pitas, I.: ‘Using support vector machines to enhance the performance of elastic graph matching for frontal face authentication’, IEEE Trans. Pattern Anal. Mach. Intell., 2001, 23, (7), pp. 735746 (doi: 10.1109/34.935847).
    30. 30)
      • 12. Zafeiriou, S., Tefas, A., Pitas, I.: ‘The discriminant elastic graph matching algorithm applied to frontal face verification’, Pattern Recognit., 2007, 40, pp. 27982810 (doi: 10.1016/j.patcog.2007.01.026).
    31. 31)
      • 20. Ojala, T., Pietikainen, M., Harwood, D.: ‘A comparative study of texture measures with classification based on feature distributions’, Pattern Recognit., 1996, 29, pp. 5159 (doi: 10.1016/0031-3203(95)00067-4).
    32. 32)
      • 21. Dalal, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. Proc. 2005 IEEE Computer Society Conf. Computer Vision and Pattern Recognition (CVPR05), 2005, vol. 1, pp. 886893.
    33. 33)
      • 16. Kotropoulos, C., Tefas, A., Pitas, I.: ‘Morphological elastic graph matching applied to frontal face authentication under well-controlled and real conditions’, Pattern Recognit., 2000, 33, pp. 19351947 (doi: 10.1016/S0031-3203(99)00185-5).
    34. 34)
      • 8. Gosling, J.A., Harris, P.F., Humpherson, J.R., Whitmore, I., Willan, P.: ‘Human anatomy: color atlas and textbook’, ed. Bentley, A.L. (Mosby Elsevier, Philadelphia, 2008, 5th edn.).
    35. 35)
      • 17. Serradell, E., Kybic, J., Noguer, F.M., Fua, P.: ‘Robust elastic 2D/3D geometric graph matching’, Proc. SPIE Med. Imaging, 2012, 8314, pp. 831408 (doi: 10.1117/12.910573).
    36. 36)
      • 19. Wiskott, L., Fellous, J.-M., Krüger, N., vd Malsburg, C.: ‘Face recognition by elastic bunch graph matching’, IEEE Trans. Pattern Anal. Mach. Intell., 1997, 19, (7), pp. 775779 (doi: 10.1109/34.598235).
    37. 37)
      • 5. Cao, Y., Zheng, W., Zhao, L., Zhou, C.: ‘Expression recognition using elastic graph matching’, Lect. Notes Comput. Sci., 2005, 3784, pp. 815 (doi: 10.1007/11573548_2).
    38. 38)
      • 23. Ross, A., Nandakumar, K., Jain, A.K.: ‘Handbook of multibiometrics’ (Springer-Verlag, New York, 2006).
    39. 39)
      • 22. Lowe, D.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, (2), pp. 91110 (doi: 10.1023/B:VISI.0000029664.99615.94).
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-bmt.2013.0039
Loading

Related content

content/journals/10.1049/iet-bmt.2013.0039
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading