Advertisement

Analysis on the Viewpoint Dependency in 3-D Object Recognition by Support Vector Machines

  • Taichi Hayasaka
  • Eiichi Ohnishi
  • Shigeki Nakauchi
  • Shiro Usui
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2085)

Abstract

In 3-D object recognition in human, the recognition performance across viewpoint changes is divided into 2 types: viewpoint-dependent and viewpoint-invariant. We analyzed the viewpoint dependency of objects under the theory of image-based onject representation in human brain (Poggio & Edelman 1990, Tarr 1995) using Support Vector Machines (Vapnik 1995). We suggest from such computational approach that the features of object images between different viewpoints are major factors for human performance in 3-D object recognition.

Keywords

Support Vector Machine Object Recognition Computational Approach Human Performance Recognition Performance 
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. Biederman, I.: Recognition-by-components: A theory of human image understanding. Psychological Review 94 (1987) 115–147CrossRefGoogle Scholar
  2. Biederman, I, Gierhardstein, P.C.: Recognition depth-rotated objects: Evidence and conditions for threc-dimensional vicwpoint invariance. J. Experimental Psychology: Human Perception and Performance 19 (1993) 1162–1182CrossRefGoogle Scholar
  3. Bülthoff, H.H., Edelman, S.: Psychophysical support for a two-dimensional view interpolation theory of objecl recognition. Proc. Natl. Acad. Sci. USA 89 (1992) 60–64CrossRefGoogle Scholar
  4. Hayward W.G., Tarr. M.S.: Testing conditions for viewpoint invariance in object recognition. J. Experimental Psychology: Human Perception and Performance 23 (1997) 1511–1521CrossRefGoogle Scholar
  5. Hummel, J.E., Biederman, I.: Dynamic binding in a neural network for shape recognition. Psychological Review 99 (1992) 480–517CrossRefGoogle Scholar
  6. Johnstone, M.B., Hayes, A,: An experimental comparison of viewpoint-specific and viewpoint-independent models of object representation. The Quarterly Journal of Experimental Psychology 53A (2000) 792–824Google Scholar
  7. Logothetis, N.K., Pauls, J., Bülthoff, H.H., Poggio, T.: View-dependent object recognition by monkeys. Current Biology 4 (1994) 401–414CrossRefGoogle Scholar
  8. Marr, D., Nishihara, H.K.: Representation and recognition of the spatial organization of three-dimensional shapes. Proc. R. Soc. Lond. B 200 (1978) 269–294CrossRefGoogle Scholar
  9. Poggio, T., Edelman, S.: A network that learns to recognize three-dimensional objects. Nature 343 (1990) 263–266CrossRefGoogle Scholar
  10. Saunders, C., Stitson, M.O., Weston, J., Bottou, L., Schoelkopf, B., Smola, A,: Support Vector Machine-Reference manual. Technical Report CSD-TR-98-03, Department of Computer Science, Royal Holloway, University of London, Egham, UK (1998)Google Scholar
  11. Tarr. M.J.: Rotating objects to recognize them: A case study on the role of viewpoint dependency in the recognition of three-dimensional objects. Psychonomic Bulletin & Review 2 (1995) 55–82Google Scholar
  12. Tarr, M.J., Bülthoff, H.H.: Image-based object recognition in man, monkey, and machine. Cognition 67 (1987) 1–20CrossRefGoogle Scholar
  13. Tarr, M.J., Bülthoff, H.H., Zabinski, M., Blanz, V.: To what extent do unique parts influence recognition across changes in viewpoint? Psychological Science 8 (1997) 282–289CrossRefGoogle Scholar
  14. Tjan, B.S., Legge, G.E.: The viewpoint complexity of an object recognition task. Vision Research 38 (1998) 2335–2350CrossRefGoogle Scholar
  15. Ullman, S., Barsi, R.: Recognition by linear combination of models. IEEE Trans. Pattern Analysis and Machine Intelligence 13 (1991) 992–1006CrossRefGoogle Scholar
  16. Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer-Verlag, New York (1995)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Taichi Hayasaka
    • 1
  • Eiichi Ohnishi
    • 1
  • Shigeki Nakauchi
    • 1
  • Shiro Usui
    • 1
  1. 1.Department of Information and Computer SciencesToyohashi University of TechnologyToyohashiJapan

Personalised recommendations