Computing Eigen Space from Limited Number of Views for Recognition

  • Paresh K. Jain
  • P. Kartik Rao
  • C. V. Jawahar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4338)


This paper presents a novel approach to construct an eigen space representation from limited number of views, which is equivalent to the one obtained from large number of images captured from multiple view points. This procedure implicitly incorporates a novel view synthesis algorithm in the eigen space construction process. Inherent information in an appearance representation is enhanced using geometric computations. We experimentally verify the performance for orthographic, affine and projective camera models. Recognition results on the COIL and SOIL image database are promising.


Appearance Model Kernel Principal Component Analysis View Synthesis Interpolation Vector View Cone 
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. 1.
    Wang, Y., Chua, C.S.: Face Recognition Across Views From 2D and 3D Images. Asian Conference on Computer Vision 2, 730–735 (2004)Google Scholar
  2. 2.
    Mori, G., Malik, J.: Recognizing Objects in Adversial Clutter: Breaking a visual CAPTCHA. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 134–144 (2003)Google Scholar
  3. 3.
    Liu, X., Srivastava, A., Gallivan, K.: Optimal Linear Representation of Images for Object Recognition. IEEE Conference on Computer Vision and Pattern Recognition 1, 229–234 (2003)Google Scholar
  4. 4.
    Pentland, A., Moghaddam, B., Starner, T.: View-based and modular eigenspaces for face recognition. IEEE Conference on Computer Vision and Pattern Recognition, 84–91 (1994)Google Scholar
  5. 5.
    Nayar, S.K., Nene, S.A., Murase, H.: Real Time 100 Object Recognition System. In: IEEE Int’l Conference on Robotics and Automation, vol. 3, pp. 2321–2325 (1996)Google Scholar
  6. 6.
    Turk, M.A., Pentland, A.P.: Face Recognition Using Eigenfaces. IEEE Conference on Computer Vision and Pattern Recognition, 586–591 (1991)Google Scholar
  7. 7.
    Cootes, T., Wheeler, G., Walker, K., Taylor, C.: Coupled View Active Appearance Models. In: British Machine Vision Conference, vol. 1, pp. 52–61 (2000)Google Scholar
  8. 8.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)MATHGoogle Scholar
  9. 9.
    Nene, S.A., Nayar, S.K., Murase, H.: Columbia Object Image Library(COIL-20). Technical Report CUCS-005-96 (1996)Google Scholar
  10. 10.
    Burianek, J., Ahmadyfard, A., Kittler, J.: SOIL-47, The Surrey Object Image Library, Centre for Vision, Speach and Signal processing, Univerisity of Surrey,
  11. 11.
    Chatterjee, S., Banerjee, S., Biswas, K.K.: Reconstruction of Local Features for Facial Video Compression. In: Int’l Conf. on Image Processing, vol. 2, pp. 211–214 (2000)Google Scholar
  12. 12.
    Ulmann, S., Basri, R.: Recognition by Linear Combination of Models. IEEE Trans. Pattern Anal. Machine Intell. 13(10), 992–1006 (1991)CrossRefGoogle Scholar
  13. 13.
    Avidan, S., Shashua, A.: Novel view synthesis by cascading trilinear tensors. IEEE Transactions on Visualization and Computer Graphics 4, 293–306 (1998)CrossRefGoogle Scholar
  14. 14.
    de Verdiere, V.C., Crowley, J.L.: Visual Recognition Using Local Appearance. In: European Conference on Computer Vision, vol. 1, pp. 640–654 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Paresh K. Jain
    • 1
  • P. Kartik Rao
    • 1
  • C. V. Jawahar
    • 1
  1. 1.Centre for Visual Information TechnologyInternational Institute of Information TechnologyHyderabadIndia

Personalised recommendations