Advertisement

Image retrieval using scale-space matching

  • S. Ravela
  • R. Manmatha
  • E. M. Riseman
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1064)

Abstract

The retrieval of images from a large database of images is an important and emerging area of research. Here, a technique to retrieve images based on appearance that works effectively across large changes of scale is proposed. The database is initially filtered with derivatives of a Gaussian at several scales. A user defined template is then created from an image of an object similar to those being sought. The template is also filtered using Gaussian derivatives. The template is then matched with the filter outputs of the database images and the matches ranked according to the match score. Experiments demonstrate the technique on a number of images in a database. No prior segmentation of the images is required and the technique works with viewpoint changes up to 20 degrees and illumination changes.

Keywords

Image Retrieval Relative Scale Filter Output Steam Engine Image Retrieval System 
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.

References

  1. 1.
    Myron Flickner, Haxpreet Sawhney, Wayne Niblack, Jonathan Ashley, Qian Huang, Byron Dom, Monika Gorkani, Jim Hafner, Denis Lee, Dragutin Petkovix, David Steele, and Peter Yanker: Query By Image and Video Content: The QBIC System. IEEE Computer Magazine, September 1995, pp.23–30.Google Scholar
  2. 2.
    Gösta H. Granlund, and Hans Knutsson: Signal Processing in Computer Vision. Kluwer Academic Publishers, 1995, ISBN 0-7923-9530-1, Dordrecht, The Netherlands.Google Scholar
  3. 3.
    Venkat N. Gudivada, and Vijay V. Raghavan: Content-Based Image Retrieval Systems. IEEE Computer Magazine, September 1995, pp.18–21.Google Scholar
  4. 4.
    P. J. B. Hancock, R. J. Bradley and L. S. Smith: The Principal Components of Natural Images. Network, 1992, 3:61–70.Google Scholar
  5. 5.
    J. J. Koenderink, and A. J. van Doorn: Representation of Local Geometry in the Visual System. Biological Cybernetics, 1987, vol. 55, pp. 367–375.Google Scholar
  6. 6.
    Tony Lindeberg: Scale-Space Theory in Computer Vision. Kluwer Academic Publishers, 1994, ISBN 0-7923-9418-6, Dordrecht, The Netherlands.Google Scholar
  7. 7.
    R. Manmatha: Measuring Affine Transformations Using Gaussian Filters. Proc. European Conference on Computer Vision, 1994, vol II, pp. 159–164.Google Scholar
  8. 8.
    R. Manmatha and J. Oliensis: Measuring Affine Transform — I, Scale and Rotation. Proc. DARPA IUW, 1993, pp. 449–458, Washington D.C.Google Scholar
  9. 9.
    Rajiv Mehrotra and James E. Gary: Similar-Shape Retrieval In Shape Data Management.IEEE Computer Magazine, September 1995, pp. 57–62.Google Scholar
  10. 10.
    A. Pentland, R. W. Picard, and S. Sclaroff: Photobook: Tools for Content-Based Manipulation of Databases. Proc. Storage and Retrieval for Image and Video Databases II, 1994, Vol.2, 185, SPIE, pp. 34–47, Bellingham, Wash.Google Scholar
  11. 11.
    R. Rao, and D. Ballard: Object Indexing Using an Iconic Sparse Distributed Memory. Proc. International Conference on Computer Vision, 1995, pp. 24–31.Google Scholar
  12. 12.
    S. Ravela, R. Manmatha and E. M. Riseman: Retrieval from Image Databases Using Scale-Space Matching. Technical Report UM-CS-95-104, 1995, Dept. of Computer Science, Amherst, MA 01003.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • S. Ravela
    • 1
  • R. Manmatha
    • 2
  • E. M. Riseman
    • 1
  1. 1.Computer Vision Research LaboratoryUniversity of Massachusetts at AmherstUSA
  2. 2.Center for Intelligent Information RetrievalUniversity of Massachusetts at AmherstUSA

Personalised recommendations