Advertisement

Face Recognition by Cortical Multi-scale Line and Edge Representations

  • João Rodrigues
  • J. M. Hans du Buf
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4142)

Abstract

Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. Models of visual perception are based on image representations in cortical area V1 and beyond, which contain many cell layers for feature extraction. Simple, complex and end-stopped cells provide input for line, edge and keypoint detection. Detected events provide a rich, multi-scale object representation, and this representation can be stored in memory in order to identify objects. In this paper, the above context is applied to face recognition. The multi-scale line/edge representation is explored in conjunction with keypoint-based saliency maps for Focus-of-Attention. Recognition rates of up to 96% were achieved by combining frontal and 3/4 views, and recognition was quite robust against partial occlusions.

Keywords

Face Recognition Input Image Complex Cell Coarse Scale Simple Cell 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bar, M.: A cortical mechanism for triggering top-down facilitation in visual object recognition. Journal of Cognitive Neuroscience (15), 600–609 (2003)CrossRefGoogle Scholar
  2. 2.
    Berson, D.: Strange vision: ganglion cells as circadian photoreceptors. TRENDS in Neurosciences 26(6), 314–320 (2003)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Valentin, D., et al.: What represents a face? A computational approach for the integration of physiological and psychological data. Perception 26(10), 1271–1288 (1997)CrossRefGoogle Scholar
  4. 4.
    Deco, G., Rolls, E.T.: A neurodynamical cortical model of visual attention and invariant object recognition. Vision Res. (44), 621–642 (2004)CrossRefGoogle Scholar
  5. 5.
    du Buf, J.M.H.: Ramp edges, Mach bands, and the functional significance of simple cell assembly. Biol. Cybern. 70, 449–461 (1994)MATHCrossRefGoogle Scholar
  6. 6.
    du Buf, J.M.H., Fischer, S.: Modeling brightness perception and syntactical image coding. Optical Eng. 34(7), 1900–1911 (1995)CrossRefGoogle Scholar
  7. 7.
    Ekenel, H., Sankur, B.: Multiresolution face recognition. Image Vision Comp. 23(5), 469–477 (2005)CrossRefGoogle Scholar
  8. 8.
    Heitger, F., et al.: Simulation of neural contour mechanisms: from simple to end-stopped cells. Vision Res. 32(5), 963–981 (1992)CrossRefGoogle Scholar
  9. 9.
    Fleet, D.J., Jepson, A.D., Jenkin, M.R.M.: Phase-based disparity measurement. CVGIP: Image Understanding 53(2), 198–210 (1991)MATHCrossRefGoogle Scholar
  10. 10.
    Grigorescu, C., Petkov, N., Westenberg, M.A.: Contour detection based on nonclassical receptive field inhibition. IEEE Tr. IP 12(7), 729–739 (2003)Google Scholar
  11. 11.
    Hamker, F.: The reentry hypothesis: The putative interaction of the frontal eye field, ventrolateral prefrontal cortex, and areas V4, ITfor attention and eye movement. Cerebrel Cortex 15, 431–447 (2005)CrossRefGoogle Scholar
  12. 12.
    Hubel, D.H.: Eye, brain and vision. Scientific American Library (1995)Google Scholar
  13. 13.
    Hotta, K., et al.: Face matching through information theoretical attention points and its applications to face detection and classification. In: Proc. 4th IEEE Int. Conf. Automatic Face and Gesture Recogn., pp. 34–39 (2000)Google Scholar
  14. 14.
    Lindeberg, T.: Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, Dordrecht, Netherland (1994)Google Scholar
  15. 15.
    Pomplun, M., et al.: Augenbewegungen als kognitionswissenschaftlicher forschungsgegenstand. In: Kognitionswissenschaft: Strukturen und Prozesse intelligenter Systeme, Universitätsverlag, Deutscher, pp. 65–106 (1997)Google Scholar
  16. 16.
    Pessoa, L.: Mach bands: how many models are possible? Recent experimental findings and modeling attemps. Vision Res. 36, 3205–3227 (1996)CrossRefGoogle Scholar
  17. 17.
    Petkov, N., Kruizinga, P., Lourens, T.: Biologically motivated approach to face recognition. In: Proc. Int. Worksh. Artif. Neural Networks, pp. 68–77 (1993)Google Scholar
  18. 18.
    Riesenhuber, M., Poggio, T.: CBF: A new framework for object categorization in cortex. In: Proc. 1st IEEE Int. Worksh. Biol. Motivated Comp. Vision, pp. 1-9 (2000)Google Scholar
  19. 19.
    Riesenhuber, M., Poggio, T.: Models of object recognition. Nature Neuroscience 3, 1199–1204 (2000)CrossRefGoogle Scholar
  20. 20.
    Rodrigues, J., du Buf, J.M.H.: Visual cortex frontend: Integrating lines, edges, keypoints, and disparity. In: Campilho, A.C., Kamel, M.S. (eds.) ICIAR 2004. LNCS, vol. 3211, pp. 664–671. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  21. 21.
    Rodrigues, J., du Buf, J.M.H.: Multi-scale keypoints in V1 and face detection. In: De Gregorio, M., Di Maio, V., Frucci, M., Musio, C. (eds.) BVAI 2005. LNCS, vol. 3704, pp. 205–214. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  22. 22.
    Rodrigues, J., du Buf, J.M.H.: Cortical object segregation and categorization by multi-scale line and edge coding. In: Inter. Conf. Computer Vision Theory and Applications, Setúbal, Portugal, February 25-28 (accepted, 2006)Google Scholar
  23. 23.
    Yang, M.H., Kriegman, D.J., Ahuja, N.: Detecting faces in images: A survey. IEEE Tr. PAMI 24(1), 34–58 (2002)Google Scholar
  24. 24.
    Zhao, W., Chellappa, R., Rosenfeld, A., Phillips, P.: Face recognition: A literature survey. UMD CfAR Technical Report CAR-TR-948 (2000)Google Scholar
  25. 25.
    Zhaoping, L.: V1 mechanisms and some figure-ground and border effects. J. Physiology Paris 97, 503–515 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • João Rodrigues
    • 1
  • J. M. Hans du Buf
    • 2
  1. 1.Escola Superior de Tecnologia
  2. 2.Vision LaboratoryUniversity of AlgarveFaroPortugal

Personalised recommendations