Advertisement

DCT-Domain Image Retrieval Via Block-Edge-Patterns

  • K. J. Qiu
  • J. Jiang
  • G. Xiao
  • S. Y. Irianto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4141)

Abstract

A new algorithm for compressed image retrieval is proposed in this paper based on DCT block edge patterns. This algorithm directly extract three edge patterns from compressed image data to construct an edge pattern histogram as an indexing key to retrieve images based on their content features. Three feature-based indexing keys are described, which include: (i) the first two features are represented by 3-D and 4-D histograms respectively; and (ii) the third feature is constructed by following the spirit of run-length coding, which is performed on consecutive horizontal and vertical edges. To test and evaluate the proposed algorithms, we carried out two-stage experiments. The results show that our proposed methods are robust to color changes and varied noise. In comparison with existing representative techniques, the proposed algorithms achieves superior performances in terms of retrieval precision and processing speed.

Keywords

Image Retrieval Query Image Vertical Edge Horizontal Edge Pixel Domain 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mandal, M.K., Idris, F., Panchanatha, S.: A critical evaluation of image and video indexing techniques in the compressed domain. Image and Vision Computing 17, 513–529 (1999)CrossRefGoogle Scholar
  2. 2.
    Shneier, M., Abdel-Mottaleb, M.: Exploiting the JPEG compression scheme for image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 18(8), 849–853 (1996)CrossRefGoogle Scholar
  3. 3.
    Shih-Fu, C.: Compressed domain techniques for image/video indexing and manipulation. In: IEEE International Conference on Image Processing, pp. 314–317 (1995) Google Scholar
  4. 4.
    Chong-Wah, N., Ting-chuen, P.: Exploiting image indexing techniques in DCT domain. Pattern Recongnition 34, 1841–1851 (2001)CrossRefMATHGoogle Scholar
  5. 5.
    Hsu, Y.S., Prum, S., Kagel, J.H., Andrews, H.C.: Pattern recognition experiments in the Man-dala/Cosine domain. IEEE Trans. Pattern Anal. Mach. Intell. 5(5), 512–520 (1983)CrossRefGoogle Scholar
  6. 6.
    Feng, G., Jiang, J.: JPEG compressed image retrieval via statistical features. Pattern Recognition 36, 977–985 (2003)CrossRefGoogle Scholar
  7. 7.
    Lay Jose, A., Guang, L.: Image retrieval based on energy histograms of the low frequency DCT coefficients. In: Proc of International Conference on Acoustics, Speech and Signal Processing, Phoenix, Arizona, USA, vol. 6, pp. 3009–3012 (1999)Google Scholar
  8. 8.
    Sim, D.G., Kim, H.K., Park, R.H.: Fast texture description and retrieval of DCT-based compressed image. Electronic Letters 37(1), 18–19 (2001)CrossRefGoogle Scholar
  9. 9.
    Liu, J., Gu, H.: Image retrieval in various domains. Computers & Graphics 27, 807–812 (2003)CrossRefGoogle Scholar
  10. 10.
    Zhong, D., Defee, I.: DCT histogrom optimization for image database retrieval. Pattern Recongnition Letters (2005)Google Scholar
  11. 11.
    Han, J.W., Guo, L.: A shape-based image retrieval method using salient edges. Signal processing: Image communication 18, 141–156 (2003)CrossRefGoogle Scholar
  12. 12.
    Banerjee, M., Kundu, M.K.: Edge based features for content based image retrieval. Pattern Recongnition 36, 2649–2661 (2003)CrossRefGoogle Scholar
  13. 13.
    Kim, D.S., Lee, S.U.: Image vector quantizer based on a classification in the DCT domain. IEEE Trans. Commun 39(4), 549–556 (1991)CrossRefGoogle Scholar
  14. 14.
    Soltane, S., Kerkeni, N., Angue, J.C.: The use of two dimensional discrete cosine transform for an adaptive approach to image segmentation. In: Proceedings of the SPIE Image and Video Processing IV, pp. 242–251 (1996)Google Scholar
  15. 15.
    Shen, B., Sethi, I.K.: Direct feature extraction from compressed images. In: Proc. SPIE: Storage and Retrieval for Still Image and Video Databases IV, March 1996, vol. 2670, pp. 404–414 (1996)Google Scholar
  16. 16.
    Lee, S.-W., Kim, Y.-M., Choi, S.W.: Fast scene change detection using direct feature extraction from MPEG compressed videos. IEEE Trans. Multimedia 2(4), 240–254 (2000)CrossRefMathSciNetGoogle Scholar
  17. 17.
    Li, H., Liu, G., Li, Y.: An effective approach to edge classification from DCT domain. In: Proc. IEEE Int. Conf. Image Processing, pp. 940–943 (September 2002)Google Scholar
  18. 18.
    Chang, H.S., Kang, K.: A compressed domain scheme for classifying block edge patterns. IEEE Transactions on image processing 14(2) (February 2005)Google Scholar
  19. 19.
    Won, C.S., Park, D.K., Park, S.-J.: Efficient use of MPEG-7 edge histogram descriptor. ETRI J. 24(1), 23–30 (2002)CrossRefGoogle Scholar
  20. 20.
    Bartsch, H.J.: Handbook of mathematical formulas. Academic Press, London (1974)MATHGoogle Scholar
  21. 21.
    MPEG Vancouver Meeting, ISO/IEC JTC1/SC29/WG11, Experimentation Model Ver.2.0, Doc. N2822 (July 1999)Google Scholar
  22. 22.
    Lee, H.Y., Lee, H.K., Ha, Y.H.: Spatial color descriptor for image retrieval and video segmentation. IEEE Transaction on Multimedia 5(3) (September 2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • K. J. Qiu
    • 1
  • J. Jiang
    • 1
    • 2
  • G. Xiao
    • 1
  • S. Y. Irianto
    • 2
  1. 1.Faculty of Informatics & ComputingSouthwest China UniversityChongqinChina
  2. 2.Department of EIMCUniversity of BradfordUK

Personalised recommendations