Session variability modelling for face authentication
- Author(s): Christopher McCool 1, 2 ; Roy Wallace 1 ; Mitchell McLaren 3 ; Laurent El Shafey 1 ; Sébastien Marcel 1
-
-
View affiliations
-
Affiliations:
1:
Idiap Research Institute, Centre du Parc, 1920-Martigny, Switzerland;
2: NICTA, GP.O. Box 2434, Brisbane, QLD 4001, Australia;
3: Radboud University Nijmegen, P.O. Box 9102, 6500HC, The Netherlands
-
Affiliations:
1:
Idiap Research Institute, Centre du Parc, 1920-Martigny, Switzerland;
- Source:
Volume 2, Issue 3,
September 2013,
p.
117 – 129
DOI: 10.1049/iet-bmt.2012.0059 , Print ISSN 2047-4938, Online ISSN 2047-4946
This study examines session variability modelling for face authentication using Gaussian mixture models. Session variability modelling aims to explicitly model and suppress detrimental within-class (inter-session) variation. The authors examine two techniques to do this, inter-session variability modelling (ISV) and joint factor analysis (JFA), which were initially developed for speaker authentication. We present a self-contained description of these two techniques and demonstrate that they can be successfully applied to face authentication. In particular, they show that using ISV leads to significant error rate reductions of, on average, 26% on the challenging and publicly available databases SCface, BANCA, MOBIO and multi-PIE. Finally, the authors show that a limitation of both ISV and JFA for face authentication is that the session variability model captures and suppresses a significant portion of between-class variation.
Inspec keywords: speaker recognition; visual databases; face recognition; Gaussian processes
Other keywords: speaker authentication; multiPIE; intersession variability modelling; JFA; detrimental within-class variation; joint factor analysis; face authentication; SCface; error rate reductions; publicly available databases; MOBIO; ISV; Gaussian mixture models; BANCA
Subjects: Other topics in statistics; Other topics in statistics; Image recognition; Computer vision and image processing techniques; Spatial and pictorial databases
References
-
-
1)
-
6. Kenny, P., Boulianne, G., Ouellet, P., Dumouchel, P.: ‘Joint factor analysis versus eigenchannels in speaker recognition’, IEEE Trans. Audio Speech Language Process., 2007, 15, (4), pp. 1435–1447 (doi: 10.1109/TASL.2006.881693).
-
-
2)
-
10. Günther, M., Wallace, R., Marcel, S.: ‘An open source framework for standardized comparisons of face recognition algorithms’. Proc. Second IEEE Int. Workshop on Benchmarking Facial Image Analysis Technologies, in conjunction with ECCV 2012, 2012, pp. 547–556.
-
-
3)
-
27. Grgic, M., Delac, K., Grgic, S.: ‘SCface-surveillance cameras face database’, Multimedia Tools Appl., 2011, 51, pp. 863–879 (doi: 10.1007/s11042-009-0417-2).
-
-
4)
-
26. Rodriguez, Y.: ‘Face detection and verification using local binary patterns’. PhD dissertation, Idiap Research Institute and École Polytechnique Fédérale de Lausanne, 2006.
-
-
5)
-
18. Tan, X., Triggs, B.: ‘Enhanced local texture feature sets for face recognition under difficult lighting conditions’, IEEE Trans. Image Process., 2010, 19, (6), pp. 1635–1650 (doi: 10.1109/TIP.2010.2042645).
-
-
6)
-
19. Glembek, O., Burget, L., Dehak, N., Brummer, N., Kenny, P.: ‘Comparison of scoring methods used in speaker recognition with joint factor analysis’. Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, April 2009, pp. 4057–4060.
-
-
7)
-
21. Kenny, P., Ouellet, P., Dehak, N., Gupta, V., Dumouchel, P.: ‘A study of inter-speaker variability in speaker verification’, IEEE Trans. Audio Speech Language Process., 2008, 16, pp. 980–988 (doi: 10.1109/TASL.2008.925147).
-
-
8)
-
5. Vogt, R., Sridharan, S.: ‘Explicit modelling of session variability for speaker verification’, Comput. Speech Language, 2008, 22, (1), pp. 17–38 (doi: 10.1016/j.csl.2007.05.003).
-
-
9)
-
12. Lucey, S., Chen, T.: ‘A GMM parts based face representation for improved verification through relevance adaptation’. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2004, vol. 2, pp. 855–861.
-
-
10)
-
28. Anjos, A., El Shafey, L., Wallace, R., Günther, M., McCool, C., Marcel, S.: ‘Bob: a free signal processing and machine learning toolbox for researchers’. Proc. ACM Multimedia Conf., 2012.
-
-
11)
-
23. Phillips, P., Flynn, P., Scruggs, T., et al: ‘Overview of the face recognition grand challenge’. Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2005, vol. 1, pp. 947–954.
-
-
12)
-
20. Thyes, O., Kuhn, R., Nguyen, P., Junqua, J.: ‘Speaker identification and verification using eigenvoices’. Proc. Int. Conf. Spoken Language Processing, 2000, vol. 2, pp. 242–245.
-
-
13)
-
29. Wallace, R., McLaren, M., McCool, C., Marcel, S.: ‘Cross-pollination of normalisation techniques from speaker to face authentication using Gaussian mixture models’, IEEE Trans. Inf. Forens. Security, 2012, 7, pp. 553–562 (doi: 10.1109/TIFS.2012.2184095).
-
-
14)
-
30. Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., Ouellet, P.: ‘Front-end factor analysis for speaker verification’, IEEE Trans. Audio Speech Language Process., 2011, 19, pp. 788–798 (doi: 10.1109/TASL.2010.2064307).
-
-
15)
-
1. Rúa, E., Castro, J., Mateo, C.: ‘Quality-based score normalization for audiovisual person authentication’. Image Analysis and Recognition, ser. (LNCS, 5112), 2008, pp. 1003–1012 (doi: 10.1007/978-3-540-69812-8_100).
-
-
16)
-
24. Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: ‘Labeled faces in the wild: a database for studying face recognition in unconstrained environments’. University of Massachusetts, Amherst, Technical Report 07-49, 2007.
-
-
17)
-
11. Sanderson, C., Paliwal, K.: ‘Fast features for face authentication under illumination direction changes’, Pattern Recogn. Lett., 2003, 24, pp. 2409–2419 (doi: 10.1016/S0167-8655(03)00070-9).
-
-
18)
-
13. Cardinaux, F., Sanderson, C., Bengio, S.: ‘User authentication via adapted statistical models of face images’, IEEE Trans. Signal Process., 2006, 54, (1), pp. 361–373 (doi: 10.1109/TSP.2005.861075).
-
-
19)
-
15. Sanderson, C., Lovell, B.C.: ‘Multi-region probabilistic histograms for robust and scalable identity inference’. Proc. Third Int. Conf. Advances in Biometrics, 2009.
-
-
20)
-
8. Yang, J., Frangi, A., Yang, J., Zhang, D., Jin, Z.: ‘KPCA plus LDA: a complete kernel fisher discriminant framework for feature extraction and recognition’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (2), pp. 230–244 (doi: 10.1109/TPAMI.2005.33).
-
-
21)
-
7. Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: ‘Speaker verification using adapted Gaussian mixture models’, Digital Signal Process., 2000, 10, (1–3), pp. 19–41 (doi: 10.1006/dspr.1999.0361).
-
-
22)
-
14. McCool, C., Marcel, S.: ‘Parts-based face verification using local frequency bands’. Proc. Third Int. Conf. Advances in Biometrics, 2009.
-
-
23)
-
16. Wallace, R., McLaren, M., McCool, C., Marcel, S.: ‘Inter-session variability modelling and joint factor analysis for face authentication’. Proc. Int. Joint Conf. Biometrics, 2011, pp. 1–8.
-
-
24)
-
3. McCool, C., Marcel, S., Hadid, C., et al: ‘Bi-modal person recognition on a mobile phone: using mobile phone data’. IEEE International Conf. on Multimedia and Expo Workshop on Hot Topics in Mobile Multimedia, 2012.
-
-
25)
-
9. Phillips, P., Beveridge, J., Draper, B., et al: ‘An introduction to the good, the bad, & the ugly face recognition challenge problem’. Proc. IEEE Int. Conf. Face Gesture, 2011, pp. 346–353.
-
-
26)
-
22. Burget, L., Fapšo, M., Hubeika, V., et al: ‘BUT system description: NIST SRE 2008’. Proc. 2008 NIST Speaker Recognition Evaluation Workshop, 2008, pp. 1–4.
-
-
27)
-
25. Bailly-Baillière, E., Bengio, S., Bimbot, F., et al.: ‘The BANCA database and evaluation protocol’. Audio- and Video-Based Biometric Person Authentication, ser. (LNCS2688), 2003, pp. 1057–1071.
-
-
28)
-
2. Ahonen, T., Pietikäinen, M.: ‘Pixelwise local binary pattern models of faces using Kernel density estimation’. Advances in Biometrics, ser. (LNCS5558), 2009, pp. 52–61 (doi: 10.1007/978-3-642-01793-3_6).
-
-
29)
-
17. Cardinaux, F., Sanderson, C., Marcel, S.: ‘Comparison of MLP and GMM classifiers for face verification on XM2VTS’. Audio- and Video-Based Biometric Person Authentication, ser. (LNCS2688), 2003, pp. 1058–1059.
-
-
30)
-
4. Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: ‘Multi-PIE’, Image Vis. Comput., 2010, 28, pp. 807–813 (doi: 10.1016/j.imavis.2009.08.002).
-
-
1)