Advertisement

Improved image classification using morphing

  • W. Brent Seales
  • Cheng Jiun Yuan
Poster Session II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1352)

Abstract

Principal component methods for classifying images have received broad attention and application. For objects with varying appearance, such as three-dimensional objects, increasing the number of object poses represented in the training set is the primary method for improving classification rate. In this paper we show how to improve the performance of this kind of an appearance-based image recognition system. The improvement is obtained by adding new views to the training set which have been generated from existing training data via a morphing algorithm. We show that adding morphed views to the training set increases recognition rate over the same data without morphed views.

Keywords

object recognition morphing principal components appearance models 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    E. Anderson, Z. Bai, and C. Bischof.LAPACK Users' Guide, Second Edition. Society for Industrial and Applied Mathematics (SIAM), Philadelphia, PA, 1995.Google Scholar
  2. 2.
    K. Fukunaga. Introduction to Statistical Recognition. Academic Press, 1990.Google Scholar
  3. 3.
    R.C. Gonzales and R.E. Woods. Digital Image Processing. Addison-Wesley, 1993.Google Scholar
  4. 4.
    J. Krumm. Object detection with vector quantizated binary features. In Proceedings CVPR '97, San Juan, Puerto Rico, pages 179–185. IEEE, June 1997.Google Scholar
  5. 5.
    Olivetti Research Laboratory. The ORL database of faces, April 1992. Images available at URL: http://www.cam-orl.co.uk/facedatabase.html. Google Scholar
  6. 6.
    H. Murase and S. Nayar. Visual learning and recognition of 3-D objects from appearance. International Journal of Computer Vision, 14:5–24, 1995.Google Scholar
  7. 7.
    A. Pentland, R.W. Picard, and S. Sclaroff. Photobook: Content-based manipulation of image databases. Int. Journal of Computer Vision, to appear, 1996.Google Scholar
  8. 8.
    W.B. Seales, M.D. Cutts, C.J. Yuan, and W. Hu. Content analysis of compressed video. Technical Report 265-96, Computer Science Dept., University of Kentucky, Lexington, Kentucky, 1996.Google Scholar
  9. 9.
    W.B. Seales, M.D. Cutts, C.J. Yuan, and W. Hu. Object recognition in compressed imagery. Image and Vision Computing, 1998.Google Scholar
  10. 10.
    S. Seitz and C. Dyer. View morphing. In Proc. SIGGRAPH, 1996.Google Scholar
  11. 11.
    M. Turk and A. Pentland. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3(1), 1991.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • W. Brent Seales
    • 1
  • Cheng Jiun Yuan
    • 1
  1. 1.Computer Science DepartmentUniversity of KentuckyLexingtonUSA

Personalised recommendations