Fuzzy Segmentation of Characters in Web Images Based on Human Colour Perception

  • A. Antonacopoulos
  • D. Karatzas
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2423)


This paper describes a new approach for the segmentation of characters in images on Web pages. In common with the authors’ previous work in this subject, this approach attempts to emulate the ability of humans to differentiate between colours. In this case, pixels of similar colour are first grouped using a colour distance defined in a perceptually uniform colour space (as opposed to the commonly used RGB). The resulting colour connected components are then grouped to form larger (character-like) regions with the aid of a fuzzy propinquity measure. This measure expresses the likelihood for merging two components based on two features. The first feature is the colour distance in the L * a * b * colour space. The second feature expresses the topological relationship of two components. The results of the method indicate a better performance than the previous method devised by the authors and comparable (possibly better) performance to other existing methods.


Membership Function Colour Space Fuzzy Inference System Colour Distance Neighbouring Component 
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. 2.
    M.K. Brown, “Web Page Analysis for Voice Browsing”, Proceedings of the 1st International Workshop on Web Document Analysis (WDA’2001), Seattle, USA, September 2001, pp. 59–61.Google Scholar
  2. 3.
    G. Penn, J. Hu, H. Luo and R. McDonald, “Flexible Web Document Analysis for Delivery to Narrow-Bandwidth Devices”, Proceedings of the 6th International Conference on Document Analysis and Recognition (ICDAR’01), Seattle, USA, September 2001, pp. 1074–1078.Google Scholar
  3. 4.
    A. Antonacopoulos, D. Karatzas and J. Ortiz Lopez, “Accessing Textual Information Embedded in Internet Images”, Proceedings of SPIE Internet Imaging II, San Jose, USA, January 24–26, 2001, pp.198–205.Google Scholar
  4. 5.
    J. Zhou and D. Lopresti, “Extracting Text from WWW Images”, Proceedings of the 4th International Conference on Document Analysis and Recognition (ICDAR’97), Ulm, Germany, August, 1997Google Scholar
  5. 6.
    D. Lopresti and J. Zhou, “Document Analysis and the World Wide Web”, Proceedings of the 2nd IAPR Workshop on Document Analysis Systems (DAS’96), Marven, Pennsylvania, October 1996, pp. 417–424.Google Scholar
  6. 7.
    H. Li; D. Doermann and O. Kia, “Automatic text detection and tracking in digital video”, IEEE Transactions on Image Processing, vol. 9, issue 1, Jan. 2000, pp. 147–156.CrossRefGoogle Scholar
  7. 8.
    D. Lopresti and J. Zhou, “Locating and Recognizing Text in WWW Images”, Information Retrieval, 2 (2/3), May 2000, pp. 177–206.CrossRefGoogle Scholar
  8. 9.
    A.K. Jain and B. Yu, “Automatic Text Location in Images and Video Frames”, Pattern Recognition, vol 31, no. 12, 1998, pp.2055–2076.CrossRefGoogle Scholar
  9. 10.
    A. Antonacopoulos and F. Delporte, “Automated Interpretation of Visual Representations: Extracting textual Information from WWW Images”, Visual Representations and Interpretations, R. Paton and I Neilson eds., Springer, London, 1999.Google Scholar
  10. 11.
    A. Antonacopoulos and D. Karatzas “An Anthropocentric Approach to Text Extraction from WWW Images”, Proceedings of the 4 th IAPR Workshop on Document Analysis Systems (DAS’2000), Rio de Janeiro, Brazil, December 2000, pp. 515–526.Google Scholar
  11. 12.
    R. C. Carter and E. C. Carter, “CIE L*u*v* Color-Difference Equations for Self-Luminous Displays,” Color Research and Applications, vol. 8, 1983, pp. 252–253.CrossRefGoogle Scholar
  12. 13.
    K. McLaren, “The development of CIE 1976 (L*a*b*) Uniform Colour Space and Colourdiference Formlua,” Journal of the Society of Dyers and Colourists, vol. 92, 1976, pp. 338–341.Google Scholar
  13. 14.
    G. Wyszecki and W. S. Stiles, Color Science-Concepts and Methods, Quantitative Data Formulas. John Wiley, New York, 1967.Google Scholar
  14. 16.
    A. Antonacopoulos, “Page Segmentation Using the Description of the Background”, Computer Vision and Image Understanding, vol. 70, 1998, pp. 350–369.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • A. Antonacopoulos
    • 1
  • D. Karatzas
    • 1
  1. 1.PRImA Group, Department of Computer ScienceUniversity of LiverpoolLiverpoolUK

Personalised recommendations