Advertisement

Multimedia Tools and Applications

, Volume 75, Issue 1, pp 365–380 | Cite as

Gappy wavelet neural network for 3D occluded faces: detection and recognition

  • Wajdi BellilEmail author
  • Hajer Brahim
  • Chokri Ben Amar
Article

Abstract

The first handicap in 3D faces recognizing under unconstrained problem is the largest variability of the visual aspect when we use various sources. This great variability complicates the task of identifying persons from their 3D facial scans and it is the most reason that bring to face detection and recognition of the major problems in pattern recognition fields, biometrics and computer vision. We propose a new 3D face identification and recognition method based on Gappy Wavelet Neural Network (GWNN) that is able to provide better accuracy in the presence of facial occlusions. The proposed approach consists of three steps: the first step is face detection. The second step is to identify and remove occlusions. Occluded regions detection is done by considering that occlusions can be defined as local face deformations. These deformations are detected by a comparison between the input facial test wavelet coefficients and wavelet coefficients of generic face model formed by the mean data base faces. They are beneficial for neighborhood relationships between pixels rotation, dilation and translation invariant. Then, occluded regions are refined by removing wavelet coefficient above a certain threshold. Finally, the last stage of processing and retrieving is made based on wavelet neural network to recognize and to restore 3D occluded regions that gathers the most. The experimental results on this challenging database demonstrate that the proposed approach improves recognition rate performance from 93.57 to 99.45 % which represents a competitive result compared to the state of the art.

Keywords

3D face recognition; Wavelets Wavelet neural network Gappy data Occlusion detection 

Notes

Acknowledgments

The authors would like to acknowledge the financial support of this work by grants from General Direction of Scientific Research (DGRST), Tunisia, under the ARUB program.

References

  1. 1.
    Alyuz N, Gokberk B, Akarun L (2008) “A 3D face recognition system for expression and occlusion invariance”, 2nd IEEE international conference Biometrics: Theory, Applications and SystemsGoogle Scholar
  2. 2.
    Bellil W, Ben Amar C and Alimi MA, (2007) Multi Library Wavelet Neural Network for lossless image compression, International Review on Computers and Software, Vol. 2, N°. 5, ISSN 1828–6003, pp 520–526, SeptemberGoogle Scholar
  3. 3.
    Bellil W, Othmani M, Ben Amar C, and Alimim A (2008) A New Algorithm for Initialization and Training of Beta Multi-Library Wavelets Neural Network. “Advances in Robotics, Automation and Control”, I-Tech Education and Publishing, edited by Jesus Aramburo and Antonio Ramirez Trevino, October, pp. 199–220Google Scholar
  4. 4.
    Bowyer KW, Chang K, Flynn P (2006) “A survey of approaches and challenges in 3D and multi-modal 3D + 2D face recognition”, in. Comput Vis Image Underst 101:1–15CrossRefGoogle Scholar
  5. 5.
    Chang KI, Bowyer KW, Flynn PJ (2006) Multiple nose region matching for 3D face recognition under varying facial expression. IEEE Trans On PAMI 28:1695–1700CrossRefGoogle Scholar
  6. 6.
    Colombo A, Cusano C, and Schettini R (2006) “Detection and restoration of occlusions for 3D face recognition,” Proc. Of IEEE International Conference on Multimedia & Expo, pp. 1541–1544Google Scholar
  7. 7.
    Colombo A, Cusano C, Schettini R (2006) 3D face detection using curvature analysis”. Pattern Recogn 39(3):444–455CrossRefzbMATHGoogle Scholar
  8. 8.
    Colombo A, Cusano C, and Schettini R (2007) “Facê 3 a 2D+ 3D Robust Face Recognition System,” Image Analysis and Processing, 2007. ICIAP 2007. 14th International Conference on, pp. 393–398Google Scholar
  9. 9.
    Colombo A, Cusano C, Schettini R (2010) Three-Dimensional Occlusion Detection and Restoration of Partially Occluded Faces, Springer Science+Business Media, LLCGoogle Scholar
  10. 10.
    Colombo A, Cusanoet C, Schettini R (2009) Gappy PCA Classification for Occlusion Tolerant 3D Face Detection, Journal of Mathematical Imaging and Vision, vol. 35, no. 3Google Scholar
  11. 11.
    Colombo A, Cusanoet C, Schettini R (2011) UMB-DB: A database of partially occluded 3D faces. Univ. degli Studi di Milano-Bicocca, Milan, Italy Computer Vision Workshops (ICCV Workshops), 2011 I.E. International Conference on 6–13 NovGoogle Scholar
  12. 12.
    Drira1 H, Slama R, Ben Amor B, Daoudi M, Srivastava A (2012) Une nouvelle approche de reconnaissance de visages 3D partiellement occultés, RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Lyon : FranceGoogle Scholar
  13. 13.
    Faltemier T, Bowyer KW, and Flynn PJ (2006) “3D face recognition with region committee voting” in Proc. 3DPVT, 2006, pp. 318–325Google Scholar
  14. 14.
    Kakadiaris IA, Passalis G, Toderici G, Murtuza MN, Lu Y, Karampatziakis N, Theoharis T (2004) Three-dimensional face recognition in the presence of facial expressions: an annotated deformable model approach. IEEE Trans On PAMI 29(4):640–649CrossRefGoogle Scholar
  15. 15.
    Kim J, Choi J, Yi J, Turk M (2005) Effective representation using ICA for face recognition robust to local distortion and partial occlusion. IEEE Trans On PAMI 27(12):1977–1981CrossRefGoogle Scholar
  16. 16.
    Martínez AM (2002) Recognizing Imprecisely Localized, Partially Occluded, and Expression Variant Faces from a Single Sample per ClassGoogle Scholar
  17. 17.
    Mian AS, Bennamoun M, Owens R (2007) An efficient multimodal 2D-3D hybrid approach to automatic face recognition. IEEE Trans On PAMI 29(11):1927–1943CrossRefGoogle Scholar
  18. 18.
    Nesterov Y (1983) A method for unconstrained convex minimization problem with the rate of convergence O (1/k2). Doklady AN SSSR 269:543–547MathSciNetGoogle Scholar
  19. 19.
    Othmani M, Bellil W, Amar CB, ALimi MA (2010) A New structure and training procedure for multi-mother wavelet networks. Int J Wavelets, Multiresolution Inf Process, IJWMIP 8(1):149–175CrossRefzbMATHGoogle Scholar
  20. 20.
    Othmani M, Bellil W, Ben Amar C, and Alimi MA (2011) A novel approach for high dimension 3D object representation using Multi-Mother Wavelet Network, International Journal “MULTIMEDIA TOOLS AND APPLICATIONS”, MTAP, Springer Netherlands, ISSN 1380–7501, pp. 1–18Google Scholar
  21. 21.
    Phillips PJ, Flynn PJ, Scruggs WT, Bowyer KW, Chang J, Hoffman K, Marques J, Min J, Worek WJ (2005) Overview of the face recognition grand challenge. Proc IEEE Conf Comput Vision Patterns Recog 1:947–954Google Scholar
  22. 22.
    Phillips JP, Scruggs WT, O’Toole AJ, Flynn PJ, Bowyer KW, Schott CL, and Sharpe M (2007) FRVT 2006 and ICE 2006 Large-Scale Results (NISTIR 7408), March Google Scholar
  23. 23.
    Savran A, Alyüz N, Dibeklioglu H, Celiktutan O, Gökberk B, Sankur B, Akarun L (2008) Biometrics and identity management. Chapter bosphorus database for 3D face analysis. Springer-Verlag, Berlin, pp 47–56Google Scholar
  24. 24.
    Soatto S, Yezzi AJ, and Jin H (2003) Tales of shape and radiance in multiview stereo. In Intl. Conf. on Comp. Vision, pages 974–981, OctoberGoogle Scholar
  25. 25.
    Tarres F, and Rama A (2005) “A novel method for face recognition under partial occlusion or facial expression variations,” ELMAR, 2005. 47th International Symposium, pp. 163–166Google Scholar
  26. 26.
    Wang Z-m, Tao J-h (2010) Remove Unknown Face Occlusion by Fuzzy Principal: National Laboratory of Pattern Recognition, China, Journal of Computer Research and DevelopmentGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.REGIM: REsearch Groups on Intelligent MachinesUniversity of Sfax, National Engineering School of Sfax (ENIS)SfaxTunisia

Personalised recommendations