Coarse-to-Fine Textures Retrieval in the JPEG 2000 Compressed Domain for Fast Browsing of Large Image Databases

  • Antonin Descampe
  • Pierre Vandergheynst
  • Christophe De Vleeschouwer
  • Benoit Macq
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4105)


In many applications, the amount and resolution of digital images have significantly increased over the past few years. For this reason, there is a growing interest for techniques allowing to efficiently browse and seek information inside such huge data spaces. JPEG 2000, the latest compression standard from the JPEG committee, has several interesting features to handle very large images. In this paper, these features are used in a coarse-to-fine approach to retrieve specific information in a JPEG 2000 code-stream while minimizing the computational load required by such processing. Practically, a cascade of classifiers exploits the bit-depth and resolution scalability features intrinsically present in JPEG 2000 to progressively refine the classification process. Comparison with existing techniques is made in a texture-retrieval task and shows the efficiency of such approach.


Discrete Wavelet Transform Jpeg2000 Image Retrieval Rate Texture Retrieval Large Image Database 
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.
    Boliek, M., Christopoulos, C., Majani, E.: JPEG 2000 image core coding system (Part 1). Technical report, ISO/IEC JTC1/SC29 WG1 (2001)Google Scholar
  2. 2.
    Fleuret, F., Geman, D.: Coarse-to-fine face detection. International Journal of Computer Vision 41, 85 (2001)MATHCrossRefGoogle Scholar
  3. 3.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: IEEE Conference on CVPR, pp. 609–615 (2001)Google Scholar
  4. 4.
    Mandal, M.K., Liu, C.: Efficient image indexing techniques in the JPEG 2000 domain. Journal of Electronic Imaging 13, 179–187 (2004)CrossRefGoogle Scholar
  5. 5.
    Tabesh, A., Bilgin, A., Krishnan, K., Marcellin, M.W.: JPEG 2000 and motion jpeg 2000 content analysis using codestream length information. In: Proceedings of the Data Compression Conference (DCC 2005) (2005)Google Scholar
  6. 6.
    Neelamani, R., Berkner, K.: Adaptive representation of JPEG 2000 images using header-based processing. In: IEEE International Conference on Image Processing (ICIP), vol. 1, pp. I–381– I–384 (2002)Google Scholar
  7. 7.
    Xiong, Z., Huang, T.S.: Subband-based, memory-efficient JPEG 2000 images indexing in compressed-domain. In: SSIAI (ed.), pp. 290–294 (2002)Google Scholar
  8. 8.
    Jiang, J., Guo, B., Li, P.: Extracting shape features in JPEG 2000 compressed images. In: Yakhno, T. (ed.) ADVIS 2002. LNCS, vol. 2457, pp. 123–132. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  9. 9.
    MIT Vision and Modeling group: Vision texture (vistex) database (2002)Google Scholar
  10. 10.
    Do, M.N., Vetterli, M.: Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distance. IEEE Trans. Image Process 11 (2002)Google Scholar
  11. 11.
    Mallat, S.: A Wavelet Tour of Signal Processing, p. 577. Academic Press, London (1998)MATHGoogle Scholar
  12. 12.
    Descampe, A., DeVleeschouwer, C., Iregui, M., Macq, B., Marques, F.: Pre-fetching strategies for remote and interactive browsing of JPEG 2000 images. In: International Conference on Image Processing, ICIP 2006 ( to appear, 2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Antonin Descampe
    • 1
  • Pierre Vandergheynst
    • 2
  • Christophe De Vleeschouwer
    • 1
  • Benoit Macq
    • 1
  1. 1.Communications and Remote Sensing LaboratoryUniversité catholique de LouvainBelgium
  2. 2.Signal Processing Institute, Ecole Polytechnique Fédérale de LausanneSwitzerland

Personalised recommendations