Recognizing Objects by Their Appearance Using Eigenimages

  • Horst Bischof
  • Aleš Leonardis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1963)


The appearance-based approaches to vision problems have recently received a renewed attention in the vision community due to their ability to deal with combined effects of shape, reflectance properties, pose in the scene, and illumination conditions. Besides, appearancebased representations can be acquired through an automatic learning phase which is not the case with traditional shape representations. The approach has led to a variety of successful applications, e. g., visual positioning and tracking of robot manipulators, visual inspection, and human face recognition.

In this paper we will review the basic methods for appearance-based object recognition. We will also identify the major limitations of the standard approach and present algorithms how these limitations can be alleviated leading to an object recognition system which is applicable in real world situations.


Object Recognition Training Image Independent Component Analysis Minimum Description Length Pepper Noise 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 2.
    T. W. Anderson. An Introduction to Multivariate Statistical Analysis. New York: Wiley, 1958. 248zbMATHGoogle Scholar
  2. 3.
    A. Bab-Hadiashar and D. Suter. Optic flow calculation using robust statistics. In Proc. CVPR’97, pages 988–993, 1997. 255Google Scholar
  3. 4.
    P. Baldi and K. Hornik. Learning in linear neural networks: A survey. IEEE Transactions on Neural Networks, 6(4):837–858, 1995. 250CrossRefGoogle Scholar
  4. 5.
    P. Belhumeuer, J. Hespanha, and D. Kriegman. Eigenfaces vs. fischerfaces: Recognition using class specific projection. In Proc. ECCV, pages 45–58. Springer, 1996. 262Google Scholar
  5. 6.
    D. Beymer and T. Poggio. Face recognition from one example view. In Proceedings of 5th ICCV’95, pages 500–507. IEEE Computer Society Press, 1995. 246Google Scholar
  6. 7.
    I. Biederman. Recognition by components: A theory of human image understanding. Psychological Review, 94:115–147, 1987. 246CrossRefGoogle Scholar
  7. 8.
    H. Bischof and A. Leonardis. Recovery of eigenimages from responses of local filter banks. In R. Sablatnig, editor, Applications of 3D-Imaging and Graph-based Modelling 2000, volume 142 of OCG Schriftenreihe, pages 121–128. Österreichische Computer Gesellschaft, 2000. 259, 263Google Scholar
  8. 9.
    Horst Bischof and Aleš Leonardis. Robust recognition of scaled eigenimages through a hierarchical approach. In Proc. of CVPR98, pages 664–670. IEEE Compter Society Press, 1998. 259, 261Google Scholar
  9. 10.
    M. Black and A. Jepson. Eigentracking: Robust matching and tracking of articulated objects using a view-based representation. International Journal of Computer Vision, 26(1):63–84, 1998. 253CrossRefGoogle Scholar
  10. 11.
    H. Bourlard and Y. Kamp. Auto-association by multilayer perceptrons and singular value decomposition. Biological Cybernetics, 59:291–294, 1988. 251zbMATHCrossRefMathSciNetGoogle Scholar
  11. 12.
    H. H. Bülthosf, S. Y. Edelman, and M. Tarr. How are three-dimensional objects represented in the brain? Technical Report A. I. Memo No. 1479, C. B. C. L. Paper No. 9, Massachusetts Institute of Technology, 1994. 263Google Scholar
  12. 13.
    J. Edwards and H. Murase. Appearance matching of occluded objects using coarseto-fine adaptive masks. In Proc. CVPR’97, pages 533–539, 1997. 253Google Scholar
  13. 14.
    H. Farid and E. H. Adelson. Separating reflections and lighting using independent components analysis. In CVPR99, pages I:262–267, 1999. 263Google Scholar
  14. 15.
    M. A. Fischler and R. C. Bolles. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications ACM, 24(6):381–395, June 1981. 254, 255CrossRefMathSciNetGoogle Scholar
  15. 16.
    B. J. Frey, A. Colmenarez, and T. S. Huang. Mixtures of local linear subspaces for face recognition. In Proc. CVPR98, pages 32–37. IEEE Computer Society, 1998. 262Google Scholar
  16. 17.
    P. M. Hall, D. Marshall, and R.R. Martin. Incremental eigenanalysis for classification. TR 98001, Dept. of Computer Science, Univ. of Cardi., 1998. 251Google Scholar
  17. 18.
    Geoffrey E Hinton, Michael Revow, and Peter Dayan. Recognizing handwritten digits using mixtures of linear models. In G. Tesauro, D. Touretzky, and T. Leen, eds, NIPS, volume 7, pages 1015–1022. The MIT Press, 1995. 262Google Scholar
  18. 19.
    A. Hyvärinen and E. Oja. Independent component analysis: algorithms and applications. Neural Networks, 13(4–5):411–431, 2000. 263CrossRefGoogle Scholar
  19. 20.
    Ales Leonardis and Horst Bischof. Multiple Eigenspaces by MDL (in press). In Proceedings of ICPR2000. IEEE Computer Society, 2000. 262Google Scholar
  20. 21.
    Aleš Leonardis and Horst Bischof. Robust recognition using eigenimages. Computer Vision and Image Understanding, 78(1):99–118, 2000. 253, 255, 256, 257CrossRefGoogle Scholar
  21. 22.
    David Marr. Vision. New York: Freeman, 1982. 246Google Scholar
  22. 23.
    B. Moghaddam and A. Pentland. Probabilistic visual learning for object representation. IEEE Trans. PAMI, 19(7):696, 1997. 250Google Scholar
  23. 24.
    H. Murase and S. K. Nayar. Image spotting of 3D objects using parametric eigenspace representation. In G. Borgefors, editor, The 9th Scandinavian Conference on Image Analysis, volume 1, pages 323–332, Uppsala, Sweden, June 1995. 246, 253Google Scholar
  24. 25.
    H. Murase and S. K. Nayar. Visual learning and recognition of 3-D objects from appearance. International Journal of Computer Vision, 14:5–24, 1995. 246, 250, 251CrossRefGoogle Scholar
  25. 26.
    H. Murase and S.K. Nayar. Illumination planning for object recognition using parametric eigenspaces. IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(12):1219–1227, 1994. 246, 248CrossRefGoogle Scholar
  26. 27.
    S. K. Nayar, H. Murase, and S. A. Nene. Learning, positioning, and tracking visual appearance. In IEEE International Conference on Robotics and Automation, San Diego, May 1994. 246Google Scholar
  27. 28.
    S. A. Nene, S. K. Nayar, and H. Murase. Columbia object image library (COIL-20). Technical Report CUCS-005-96, Columbia University, New York, 1996. 249, 257Google Scholar
  28. 29.
    K. Ohba and K. Ikeuchi. Detectability, uniqueness, and reliability of eigen windows for stable verification of partially occluded objects. PAMI, 9:1043–1047, 1997. 253Google Scholar
  29. 30.
    A. Pentland, B. Moghaddam, and T. Straner. View-based and modular eigenspaces for face recognition. Technical Report 245, MIT Media Laboratory, 1994. 253Google Scholar
  30. 31.
    T. Poggio and S. Edelman. A network that learns to recognize three-dimensional objects. Nature, 343:263–266, 1990. 248, 263CrossRefGoogle Scholar
  31. 32.
    R. Rao. Dynamic appearance-based recognition. In CVPR’97, pages 540–546. IEEE Computer Society, 1997. 253Google Scholar
  32. 33.
    J. Rissanen. Stochastic Complexity in Statistical Inquiry, volume 15 of Series in Computer Science. World Scientific, 1989. 256Google Scholar
  33. 34.
    P. J. Rousseuw and A. M. Leroy. Robust Regression and Outlier Detection. Wiley, New York, 1987. 254CrossRefGoogle Scholar
  34. 35.
    S. Chandrasekaran, B. S. Manjunath, Y. F. Wang, J. Winkler, and H. Zhang. An eigenspace update algorithm for image analysis. Technical Report TR CS 96-04, Dept. of Computer Science, Univ. of California, Santa Barbara, 1996. 251Google Scholar
  35. 36.
    B. Schölkopf, A. Smola, and K. R. Müller. Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 10(5):1299–1319, 1998. 262CrossRefGoogle Scholar
  36. 37.
    E. Simoncelli and H. Farid. Steerable wedge filters for local orientation analysis. IEEE Trans. on Image Processing, pages 1–15, 1996. 261Google Scholar
  37. 38.
    M. Stricker and A. Leonardis. ExSel++: A general framework to extract parametric models. In V. Hlavac and R. Sara, editors, 6th CAIP’95, number 970 in Lecture Notes in Computer Science, pages 90–97, Prague, Czech Republic, September 1995. Springer. 262Google Scholar
  38. 39.
    M. Turk and A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1):71–86, 1991. 246, 248, 250CrossRefGoogle Scholar
  39. 40.
    Shimon Ullman. High-level Vision. MIT Press, 1996. 248Google Scholar
  40. 41.
    V. N. Vapnik. The Nature of Statistical Learning Theory. Springer, 1995. 262Google Scholar
  41. 42.
    S. Yoshimura and T. Kanade. Fast template matching based on the normalized correlation by using multiresolution eigenimages. In Proceedings of IROS’94, pages 2086–2093, 1994. 246, 248Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Horst Bischof
    • 1
  • Aleš Leonardis
    • 2
  1. 1.Pattern Recognition and Image Processing GroupUniversity of TechnologyViennaAustria
  2. 2.Faculty of Computer and Information ScienceUniversity of LjubljanaSlovenia

Personalised recommendations