Segmentation of Text and Graphics/Images Using the Gray-Level Histogram Fourier Transform

  • M. A. Patricio
  • D. Maravall
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)


One crucial issue in automatic document analysis is the discrimination between text and graphics/images. This paper presents a novel, robust method for the segmentation of text and graphics/images in digitized documents. This method is based on the representation of window-like portions of a document by means of their gray level histograms. Through empirical evidence it is shown that text and graphics/images regions have different gray level histograms. Unlike the usual approach for the characterization of histograms that is based on statistics parameters a novel approach is introduced. This approach works with the histogram Fourier transform since it possesses all the information contained in the histogram pattern. The next and logical step is to automatically select the most discriminant spectral components as far as the text and graphics/images segmentation goal is concerned. A fully automated procedure for the optimal selection of the discriminant features is also expounded. Finally, empirical results obtained for the text and graphics/images segmentation using a simple three-layer perceptron-like neural network are also discussed.


Feature extraction and selection Image analysis Applications: automatic document analysis 


  1. [1]
    H. Bunke, P.S.P. Wang, Handbook of Character Recognition and Document Image Analysis, World Scientific (1997).Google Scholar
  2. [2]
    Z. Jiang, J. Liu, J. Liu Jin“Char: a tool for automatic text/graphics segmentation of engineering drawing images”, Journal of Software Vol. 10 No. 6 (June 1999) 589–594.Google Scholar
  3. [3]
    Z. Jiang, J. Liu, “A shielding method for segmentation of graphics touching text in engineering drawings”, Porceedings of the SPIE. The International Society for Optical Engineering, Vol. 3305 (1998) 53–60.CrossRefGoogle Scholar
  4. [4]
    K. Tombre, C. Ah Soon, P. Dosch, A. Habed,, G. Masini, “Stable, robust and off-the-shelf methods for graphics recognition”, Proceedings. Fourteenth Conference on Pattern Recognition. IEEE Comput. Soc, Vol. 1 (1998) 406–408.CrossRefGoogle Scholar
  5. [5]
    E. Martí, “Análisis de elementos gráficos en documentos”, RECV-Revista Electrónica de Visión por Computador, Centro de Visión por Computador, No. 0, (Octubre 1999).
  6. [6]
    T. Ojala, M. Pietikäinen, and J. Nisula, “Determining composition of grain mixtures by texture classification based on feature distributions”, Int. Journal of Pattern Recognition and Artificial Intelligence Vol. 10 No. 1 (1996) 73–82.CrossRefGoogle Scholar
  7. [7]
    T. Ojala, M. Pietikäinen, and D. Harwood, “Performance evaluation of texture measures with classification based on Kullback discrimination of distributions” Proc. 12th. Int. Conf. On Pattern Recognition, vol. 1, Jerusalem, Israel, (1994) 582–585.CrossRefGoogle Scholar
  8. [8]
    M. Unser, “Sum and difference histograms for texture classification”, IEEE Trans. on Pattern Anal. and Machine Intell. 8 (1986) 118–125.Google Scholar
  9. [9]
    A. L. Vickers and J.W. Modestino, “A maximum likelihood aproach to texture classification”, IEEE Trans. on Pattern Anal. and Machine Intell. 4 (1982) 61–68.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • M. A. Patricio
    • 1
  • D. Maravall
    • 2
  1. 1.Centro de Cálculo ArtificialUniversidad Politécnica de MadridSpain
  2. 2.Departamento de Inteligencia ArtificialUniversidad Politécnica de MadridSpain

Personalised recommendations