A MULTI-SCALE LAYOUT DESCRIPTOR BASED ON DELAUNAY TRIANGULATION FOR IMAGE RETRIEVAL

Agnés Borràs Angosto, Josep Lladós Canet

Abstract

Working with large collections of videos and images has need of effective and flexible techniques of retrieval and browsing. Beyond the classical color histogram approaches, the layout information has proven to be a very descriptive cue for image description. We have developed a descriptor that encodes the layout of an image using a histogram-based representation. The descriptor uses a multi-layer representation that captures the saliency of the image parts. Furthermore it encodes their relative positions using the properties of a Delaunay triangulation. The descriptor is a compact feature vector which content is normalized. Their properties make it suitable for image retrieval and indexing applications. Finally, have applied it to a video browsing application that detects characteristic scenes of a news program.

References

  1. Delaunay, B. (1934). Sur la sphère vide. Bulletin of Academy of Sciences of the USSR, (7):793-800.
  2. Gagaudakis, G. and Rosin, P. L. (2003). Shape measures for image retrieval. Pattern Recogn. Letters, 24(15):2711-2721.
  3. Huang, J., Kumar, S., Mitra, M., Zhu, W., and Zabih, R. (1997). Image indexing using color correlograms. In Proc. IEEE Comp. Soc. Conf. Comp. Vis. and Patt. Rec., pages 762-768.
  4. Koenderink, J. (1984). The structure of images. In Biological Cybernetics, volume 50, pages 363-370, Egmond aan Zee, The Netherlands.
  5. Lindeberg, T. (1996). Scale-space: A framework for handling image structures at multiple scales. In Proceedings of CERN School of Computing, pages 8-21, Egmond aan Zee, The Netherlands.
  6. Lipson, P., Grimson, E., and Sinha, P. (1997). Configuration based scene classification and image indexing. Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR 7897), pages 1007- 1013.
  7. Pass, G. and Zabih, R. (1996). Histogram refinement for content based image retrieval. IEEE Workshop on Applications of Computer Vision, pages 96-102.
  8. Rosenfeld, A. and Pfaltz, J. (1968). Distance functions in digital pictures. Pattern Recognition, 1:33-61.
  9. Swain, M. and Ballard, D. (1991). Color indexing. International Journal of Computer Vision, 7(1):11-32.
  10. Tao, Y. and Grosky, W. (1999). Delaunay triangulation for image object indexing: A novel method for shape representation. In IST SPIE's Symposium on Storage and Retrieval for Image and Video Databases VII, San Jose, California.
  11. Veltkamp, R. and Tanase, M. (2000). Content-based image retrieval systems: A survey. Technical report, Department of Computer Science, Utrecht University.
  12. Witkin, A. P. (1987). Scale-space filtering. In Fischler, M. A. and Firschein, O., editors, Readings in Computer Vision: Issues, Problems, Principles, and Paradigms. Kaufmann.
Download


Paper Citation


in Harvard Style

Borràs Angosto A. and Lladós Canet J. (2008). A MULTI-SCALE LAYOUT DESCRIPTOR BASED ON DELAUNAY TRIANGULATION FOR IMAGE RETRIEVAL . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 139-144. DOI: 10.5220/0001077501390144


in Bibtex Style

@conference{visapp08,
author={Agnés Borràs Angosto and Josep Lladós Canet},
title={A MULTI-SCALE LAYOUT DESCRIPTOR BASED ON DELAUNAY TRIANGULATION FOR IMAGE RETRIEVAL},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={139-144},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001077501390144},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - A MULTI-SCALE LAYOUT DESCRIPTOR BASED ON DELAUNAY TRIANGULATION FOR IMAGE RETRIEVAL
SN - 978-989-8111-21-0
AU - Borràs Angosto A.
AU - Lladós Canet J.
PY - 2008
SP - 139
EP - 144
DO - 10.5220/0001077501390144