Image retrieval by color regions

  • A. Del Bimbo
  • M. Mugnaini
  • P. Pala
  • F. Turco
  • L. Verzucoli
Poster Session C: Compression, Hardware & Software, Image Databases, Neural Networks, Object Recognition & Reconstruction
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1311)


The minor expressiveness of text with respect to visual features doesn't allow to fully exploit capabilities of human memory. For this reason retrieval based on visual contents has been identified as the means to provide an effective retrieval. The relative relevance of visual elements depends on user's subjectivity (which is not known in advance) and on the context of application. To cope with this problem, the description of image visual contents should exploit different levels of detail in image representation. In the following we present the PICASSO system, which supports image indexing and retrieval based on shapes, colors, and spatial relationships. The system exploits a pyramidal representation of the images which are analyzed at different levels of resolution. Multiple descriptions of image properties are created at different levels of resolution thus allowing effective retrieval through specific queries as well as imprecise ones. Retrieval results for a sample database of pictorial images are reported, with efficiency and effectiveness measures.


Image Retrieval Color Region Effective Retrieval Image Energy Query Region 
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.


  1. 1.
    T. Uchiyama and M.A. Arbib. Color image segmentation using competitive learning. IEEE Trans. on Pattern Analysis and Machine Intelligence, (16)12:1197–1206, Dec. 1994.CrossRefGoogle Scholar
  2. 2.
    R. K. Srihari. Automatic indexing and content-based retrieval of captioned images. IEEE Computer, 28(9):49–56, Sept. 1995.Google Scholar
  3. 3.
    W. Cody. Querying multimedia data for multiple repositories by content: The GARLIC project. In Proc. on Visual Data Base Systems III, Lausanne, 1995.Google Scholar
  4. 4.
    A. Del Bimbo and P. Pala. Visual image retrieval by elastic matching of user sketches. Accepted for publication in IEEE Trans. on Pattern Analysis and Machine Intelligence.Google Scholar
  5. 5.
    A. Del Bimbo, P. Pala. Image Indexing Using Shape Based Visual Features International Conference on Pattern Recognition, Wien, August 1996.Google Scholar
  6. 6.
    C.L. Huang, T.Y. Cheng and C.C. Chen. Color images' segmentation using scale space filter and Markov random field. Pattern Recognition, (25)10:1217–1229, 1992.Google Scholar
  7. 7.
    A. K. Jain and A. Vailaya. Image retrieval using color and shape. Pattern Recognition, 29(8):1233–1244, Aug. 1996.CrossRefGoogle Scholar
  8. 8.
    Y.W. Lim and S.U. Lee. On the color image segmentation algorithm based on the thresholding and the fuzzy c-means techniques. Pattern Recognition (23)9:935–952, 1990.Google Scholar
  9. 9.
    J. Liu and Y.H. Yang. Multiresolution color image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence, (16)7:689–700, 1994.Google Scholar
  10. 10.
    A. Nagasaka and Y. Tanaka. Automatic video indexing and full video search for object appearances. In IFIP Trans., Visual Database Systems II, pages 113–127, Knuth, Wegner (Eds.), 1992. Elsevier.Google Scholar
  11. 11.
    W.Niblack et alii, “The QBIC Project: Querying Images by Content Using Color, Texture and Shape”. Res.Report 9203, IBM Res.Div. Almaden Res.Center, Feb. 1993.Google Scholar
  12. 12.
    M.J.Swain, D.H.Gallard, “Color Indexing”. Int.Journal of Computer Vision, Vol.7, No. 1, 1991.Google Scholar
  13. 13.
    V. Vinod, H. Murase, “Focussed Retrieval of Color Images”. To appear on Pattern Recognition Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • A. Del Bimbo
    • 1
  • M. Mugnaini
    • 1
  • P. Pala
    • 1
  • F. Turco
    • 1
  • L. Verzucoli
    • 1
  1. 1.Dipartimento di Sistemi e InformaticaUniversith di FirenzeFirenzeItaly

Personalised recommendations