Breaking the 99% barrier: optimisation of three-dimensional face recognition

Luuk Spreeuwers

Breaking the 99% barrier: optimisation of three-dimensional face recognition

View Fulltext

Author(s): Luuk Spreeuwers ¹
- Affiliations: 1: Chair of Biometrics Pattern Recognition, SCS Group, Department of EEMCS, University of Twente, P.O. Box 217, 7500 AE Enschede, The Netherlands
Source: Volume 4, Issue 3, September 2015, p. 169 – 178
DOI: 10.1049/iet-bmt.2014.0017 , Print ISSN 2047-4938, Online ISSN 2047-4946

Received 12/03/2014, Accepted 02/02/2015, Revised 19/12/2014, Published 28/04/2015

This study presents optimisations to a three-dimensional (3D) face recognition method the authors published in 2011. The optimisations concern handling and estimation of motion from a single 3D image using the symmetry of the face, fine registration by selection of the maximum score for small variations of the registration parameters and efficient training using automatic outlier removal where only part of the classifier is retrained. The optimisations lead to a staggering performance improvement: the verification rate on Face Recognition Grand Challenge (FRGC) v2 data at false accept rate = 0.1% increases from 94.6 to 99.3% and the identification rate increases from 99 to 99.4%. Both are, to the authors' knowledge, the best scores ever published on the FRGC data. In addition, the registration time was reduced from about 2.5 to 0.2–0.6 s and the number of comparisons has increased from about 11 000 to more than 50 000 per second. For slightly decreased performance, even millions of comparisons can be realised. The fast registration means near real-time recognition with 2–5 images is possible. The optimisations are not specific for this method, but can be beneficial for other 3D face recognition methods as well.

References

1. 1)
  - 32. Bishop, C.M.: ‘Pattern recognition and machine learning (information science and statistics)’. (Springer-Verlag, New York, NY, 2006).
2. 2)
  - K.W. Bowyer , K. Chang , P. Flynn . A survey of approaches and challenges in 3d and multi-modal 3d+2d face recognition. Comput. Vis. Image Underst. , 1 , 1 - 15
3. 3)
  - 28. Conde, C., Serrano, A., Cabello, E.: ‘Multimodal 2D, 2.5D 3D face verification’. IEEE Int. Conf. on Image Processing, 2006, pp. 2061–2064.
4. 4)
  - 25. Yang, J., Zhang, D., Yang, J.-Y.: ‘Median LDA: a robust feature extraction method for face recognition’. IEEE Int. Conf. on Systems, Man and Cybernetics, 2006, vol. 5, pp. 4208–4213.
5. 5)
  - 33. Brown, L.D., Cai, T.T., Dasgupta, A.: ‘Interval estimation for a binomial proportion’, Stat. Sci., 2001, pp. 101–133.
6. 6)
  - 13. Bazen, A.M., Veldhuis, R.N.J.: ‘Likelihood ratio-based biometric verification’, IEEE Trans. Circuits Syst. Video Technol., 2004, 14, (1), pp. 86–94 (doi: 10.1109/TCSVT.2003.818356).
7. 7)
  - F. Al-Osaimi , M. Bennamoun , A. Mian . An expression deformation approach to non-rigid 3d face recognition. Int. J. Comput. Vis. , 3 , 302 - 316
8. 8)
  - 19. Savran, A., Alyüz, N., Dibeklioğlu, H., et al: ‘Bosphorus database for 3D face analysis’, in Schouten, B., Juul, N.C., Drygajlo, A., Tistarelli, M. (Eds.): ‘Biometrics and identity management’ (Springer Berlin Heidelberg, Berlin, Heidelberg, 2008), pp. 47–56.
9. 9)
  - 3. Yin, L., Wei, X., Sun, Y., Wang, J., Rosato, M.: ‘A 3D facial expression database for facial behavior research’. Seventh Int. Conf. on Automatic Face and Gesture Recognition, 2006, pp. 211–216.
10. 10)
  - 26. Hampel, F.R., Ronchetti, E.M., Rousseeuw, P.J., Stahel, W.A.: ‘Robust statistics. The approach based on influence functions’ (John Wiley & Sons, New York, NY, 1986).
11. 11)
  - 9. Alyüz, N., Gökberk, B., Akarun, L.: ‘Regional registration and curvature descriptors for expression resistant 3D face recognition’. Proc. of the IEEE 17th Signal Processing and Communications Applications Conf., 2009, pp. 544–547.
12. 12)
  - 29. Moreno, A.B., Sánchez, A.: ‘GavabDB: a 3D face database’. Workshop on Biometrics on the Internet, Vigo, 2004, pp. 77–85.
13. 13)
  - 18. Phillips, P.J., Flynn, P.J., Scruggs, T., et al: ‘Overview of the face recognition grand challenge’. Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2005, Washington, DC, USA, 2005, pp. 947–954.
14. 14)
  - Y. Wang , J. Liu , X. Tang . Robust 3d face recogniton by local shape difference boosting. IEEE Trans. Pattern Anal. Mach. Intell. , 10 , 1858 - 1870
15. 15)
  - 7. Scheenstra, A., Ruifrok, A., Veltkamp, R.C.: ‘A survey of 3D face recognition methods’ (Springer, Verlag, 2005), pp. 891–899.
16. 16)
  - 6. Papatheodorou, T., Rueckert, D.: ‘3D face recognition’ (I-Tech Education and Publishing, Austria, 2007).
17. 17)
  - 15. Veldhuis, R.N.J., Bazen, A.M.: ‘One-to-template and one-to-one verification in the single- and multi-user case’. Proc. of the 26th Symp. on Information Theory in the Benelux, 2005, Brussels, Belgium, pp. 39–46.
18. 18)
  - 20. 3DFace: 3D face project web page. Available at http://www.3dface.org/home/welcome.html, 2009.
19. 19)
  - 14. Beumer, G.M., Tao, Q., Bazen, A.M., Veldhuis, R.N.J.: ‘A landmark paper in face recognition’. Proc. of the Seventh Int. Conf. on Automatic Face and Gesture Recognition, April 2006, Los Alamitos, pp. 73–78.
20. 20)
  - 1. Spreeuwers, L.J.: ‘Fast and accurate 3D face recognition using registration to an intrinsic coordinate system and fusion of multiple region classifiers’, Int. J. Comput. Vis., 2011, 93, (3), pp. 389–414 (doi: 10.1007/s11263-011-0426-2).
21. 21)
  - 12. Tang, X., Chen, J., Moon, Y.: ‘Accurate 3D face registration based on the symmetry plane analysis on nose regions’. Proc. of the 16th European Signal Processing Conf., 2008, Lausanne, Switzerland, pp. 25–29.
22. 22)
  - I. Kakadiaris , G. Passalis , G. Toderici , N. Murtuza , Y. Lu , T. Theoharis . Three-dimensional face recognition in the presence of facial expressions: An annotated deformable model approach. IEEE Trans. Pattern Anal. Mach. Intell. , 4 , 640 - 649
23. 23)
  - 23. Fidler, S., Leonardis, A.: ‘Robust LDA classification by subsampling’. Computer Vision and Pattern Recognition Workshop, 2003, vol. 8, p. 97.
24. 24)
  - 8. Boehnen, C., Peters, T., Flynn, P.J.: ‘3D signatures for fast 3D face recognition’. Proc. of the Third Int. Conf. on Advances in Biometrics, 2009, pp. 12–21.
25. 25)
  - 11. Queirolo, C.C., Silva, L., Bellon, O.R., Segundo, M.P.: ‘3D face recognition using simulated annealing and the surface interpenetration measure’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, pp. 206–219 (doi: 10.1109/TPAMI.2009.14).
26. 26)
  - 4. Inan, T., Halici, U.: ‘3-D face recognition with local shape descriptors’, IEEE Trans. Inf. Forensics Sec., 2012, 7, (2), pp. 577–587 (doi: 10.1109/TIFS.2012.2186293).
27. 27)
  - 16. Maurer, T., Guigonis, D., Maslov, I., et al: ‘Performance of Geometrix ACTIVEID™ 3D face recognition engine on the FRGC data’. Proc. of the IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, 2005, Washington, DC, USA, p. 154.
28. 28)
  - 27. Hoaglin, D.C., Mosteller, F., Tukey, J.W.: ‘Understanding robust and exploratory data analysis’ (John Wiley & Sons, New York, NY, 1983).
29. 29)
  - 17. Spreeuwers, L.J., Boom, B.J., Veldhuis, R.N.J.: ‘Better than best: matching score based face registration’. Proc. of the 28th Symp. on Information Theory in the Benelux, 2007, Enschede, The Netherlands, pp. 125–132.
30. 30)
  - 9. TerHaar, F.B., Veltkamp, R.C.: ‘Expression modeling for expression-invariant face recognition’, Comput. Graph., 2010, 34, pp. 231–241 (doi: 10.1016/j.cag.2010.03.010).
31. 31)
  - T.C. Faltemier , K.W. Bowyer , P.J. Flynn . A region ensemble for 3d face recognition. IEEE Trans. Inf. Forensics Sec. , 1 , 62 - 73
32. 32)
  - 7. Hodge, V.J.: ‘A survey of outlier detection methodologies’, Artif. Intell. Rev., 2004, 22, (2), pp. 85–126 (doi: 10.1023/B:AIRE.0000045502.10941.a9).
33. 33)
  - 31. Drira, H., Amor, B.B., Srivastava, A., Daoudi, M., Slama, R.: ‘3D face recognition under expressions, occlusions, and pose variations’, IEEE Trans. Pattern Anal. Mach. Intell., 2013, 35, (9), pp. 2270–2283 (doi: 10.1109/TPAMI.2013.48).
34. 34)
  - E. Candes , X. Li , Y. Ma , J. Wright . Robust principal component analysis. J. ACM , 2861 - 2873
35. 35)
  - 21. ‘CASIA-3D Facev1’. Available at http://www.biometrics.idealtest.org/, 2004.

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Breaking the 99% barrier: optimisation of three-dimensional face recognition

References

Related content