A hybrid system for locating and recognizing low level graphic items

  • F. Cesarini
  • M. Gori
  • S. Marinai
  • G. Soda
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1072)


This paper addresses the problem of locating and recognizing graphic items in document images. The proposed approach allows us to recognize such items also in the presence of high noise, scaling, and rotation. This is accomplished by a hybrid model which performs graphic item location by morphological operations and connected component analysis, and item recognition by a proper connectionist model. Some very promising experimental results are reported to support the proposed algorithms.


Word Recognition Document Image Hide Unit Morphological Operation Black Pixel 
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.
    M. Bianchini, P. Frasconi, and M. Gori. Learning in multilayered networks used as autoassociators. IEEE Transactions on Neural Networks, 6(2):pages 512–515, 1995.Google Scholar
  2. 2.
    M. Gori, L. Lastrucci, and G. Soda. Autoassociator-based models for speaker verification. Pattern Recognition Letters, To Appear.Google Scholar
  3. 3.
    J. Serra. Image Analysis and Mathematical Morphology. Academic Press, London, U.K., 1982.Google Scholar
  4. 4.
    D. H. Ballard and C. M. Brown. Computer Vision. Prentice Hall, Englewood Cliffs, N.J., 1982.Google Scholar
  5. 5.
    D. E. Rumelhart, G. E. Hinton, and R.J. Williams. Learning representation by error backpropagation. In Parallel Distributed Processing. MIT Press, 1990.Google Scholar
  6. 6.
    T. Kanungo, R.M. Haralick, and I. Phillips. Global and local document degradation models. In Proceedings of the International Conference on Document Analysis and Recognition, pages 730–734. IEEE Computer Society Press, 1993.Google Scholar
  7. 7.
    H.S. Baird. Document image defect models. In Structured Document Image Analysis, pages 547–555. Springer-Verlag, 1992.Google Scholar
  8. 8.
    H.S. Baird. Calibration of document image defect models. In Symposium on Document Analysis and Information Retrieval, pages 1–16, 1993.Google Scholar
  9. 9.
    F. Cesarini, M. Gori, S. Marinai, and G. Soda. A system for data extraction from forms of known class. In Proceedings of the International Conference on Document Analysis and Recognition, pages 1136–1140, 1995.Google Scholar
  10. 10.
    T.K. Ho, J.J. Hull, and S.N. Srihari. A computational model for recognition of multifont word images. Machine Vision and Applications, 6(6):157–168, 1993.Google Scholar
  11. 11.
    D.S. Doermann and A. Rosenfeld. The processing of form documents. In Proceedings of the International Conference on Document Analysis and Recognition, pages 497–501, 1993.Google Scholar
  12. 12.
    D. S. Doerman, E. Rivlin, and I. Weiss. Logo recognition. In Center for Automation Research, Technical Report 3145, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • F. Cesarini
    • 1
  • M. Gori
    • 1
  • S. Marinai
    • 1
  • G. Soda
    • 1
  1. 1.Dipartimento di Sistemi e InformaticaUniverstità di FirenzeFirenzeItalia

Personalised recommendations