Advertisement

Machine Vision and Applications

, Volume 5, Issue 3, pp 169–184 | Cite as

Text segmentation using gabor filters for automatic document processing

  • Anil K. Jain
  • Sushil Bhattacharjee
Article

Abstract

There is a considerable interest in designing automatic systems that will scan a given paper document and store it on electronic media for easier storage, manipulation, and access. Most documents contain graphics and images in addition to text. Thus, the document image has to be segmented to identify the text regions, so that OCR techniques may be applied only to those regions. In this paper, we present a simple method for document image segmentation in which text regions in a given document image are automatically identified. The proposed segmentation method for document images is based on a multichannel filtering approach to texture segmentation. The text in the document is considered as a textured region. Nontext contents in the document, such as blank spaces, graphics, and pictures, are considered as regions with different textures. Thus, the problem of segmenting document images into text and nontext regions can be posed as a texture segmentation problem. Two-dimensional Gabor filters are used to extract texture features for each of these regions. These filters have been extensively used earlier for a variety of texture segmentation tasks. Here we apply the same filters to the document image segmentation problem. Our segmentation method does not assume any a priori knowledge about the content or font styles of the document, and is shown to work even for skewed images and handwritten text. Results of the proposed segmentation method are presented for several test images which demonstrate the robustness of this technique.

Keywords

Input Image Document Image Gabor Filter Text Region Texture Segmentation 
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. Becker RA, Chambers JM, Wilks AR (1988) The New S Language. Wadsworth & Brooks/Cole, Pacific Grove, CAzbMATHGoogle Scholar
  2. Chernoff H (1973) The use of faces to represent points in k-dimensional space graphically. J. Am. Stat. Assoc. 68:361–368CrossRefGoogle Scholar
  3. Clark M, Bovik AC (1989) Experiments in segmenting texton patterns using localized spatial filters. Pattern Recognition 22(6):707–717CrossRefGoogle Scholar
  4. Coggins JM, Jain AK (1985) A spatial filtering approach to texture analysis. Pattern Recognition Letters (3):195–203Google Scholar
  5. Farrokhnia F (1990) Multi-channel filtering techniques for texture segmentation and surface quality inspection. Ph.D. thesis. Dept. of Electrical Eng., Michigan State UniversityGoogle Scholar
  6. Farrokhnia F, Jain AK (1991) A multi-channel filtering approach to texture segmentation. Proc. IEEE Computer Vision and Pattern Recognition Conf. Maui, June, pp 364–370Google Scholar
  7. Fletcher LA, Kasturi R (1988) A robust algorithm for text string separation from mixed text/graphics images. IEEE Trans. Pattern Analysis and Machine Intelligence 10(6):910–918CrossRefGoogle Scholar
  8. Gabor D (1946) Theory of communication. J. Inst. Elect. Engr. 93:429–457Google Scholar
  9. Iwaki O, Kida H, Arakawa H (1987) A segmentation method based on office document hierarchical structure. Proc. IEEE Int. Conf. Sys. Man Cybern. Alexandria, VA, October, pp 759–763Google Scholar
  10. Jain AK, Chandrasekaran B (1982) Dimensionality and sample size considerations in pattern recognition practice. In: Krishnaiah PR, Kanal LN (eds), Handbook of Statistics 2, North Holland, pp 835–855Google Scholar
  11. Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice-Hall, New JerseyzbMATHGoogle Scholar
  12. Jain AK, Farrokhnia F (1991) Unsupervised texture segmentation using Gabor filters. Pattern Recognition 24(12):1167–1186CrossRefGoogle Scholar
  13. Malik J, Perona P (1990) Preattentive texture discrimination with early vision mechanisms. J. Opt. Soc. Amer. A. 7(5):923–932Google Scholar
  14. Nadler M (1984) A survey of document segmentation and coding techniques. Computer Vision, Graphics and Image Processing 28:240–262CrossRefGoogle Scholar
  15. Nagy G (1989) Document analysis and optical character recognition. Proc. Fifth Intl. Conf. on Image Analysis and Processing, Positano, Italy, Sept. 20–22, pp 511–529Google Scholar
  16. Ni LM, Jain AK (1985) A VLSI systolic architecture for pattern clustering. IEEE Trans. Pattern Analysis and Machine Intelligence 7:80–89CrossRefGoogle Scholar
  17. Pavlidis T, Swartz J. and Wang YP (1990) Fundamentals of bar code information theory. IEEE Computer 23(4):74–86Google Scholar
  18. Perry A and Lowe DG (1989) Segmentation of textured images. Proc. IEEE Computer Soc. Conf. on Computer Vision and Pattern Recognition San Diego, CA, pp 326–332Google Scholar
  19. Sríhari SN (1986) Document image understanding. Proc. IEEE Comput. Soc. Fall Joint Computer Conf. Dallas, Texas, Nov. 2–6Google Scholar
  20. Tan TN, Constantinides AG (1990) Texture analysis based on a human visual model. Proc. IEEE Int. Conf. on Acoust., Speech, Cignal Proc. Albuquerque, New Mexico, April, pp 2091–2110Google Scholar
  21. Turner MR (1986) Texture Discrimination by Gabor Functions. Biol Cybern. 55:71–82Google Scholar
  22. Wahl FM, Wong KY, Casey RG (1982) Block segmentation and text extraction in mixed text/image documents. Computer Graphics and Image Processing 20:375–390CrossRefGoogle Scholar
  23. Wang D, Srihari SN (1989) Classification of newspaper image blocks using texture analysis. Computer Vision, Graphics and Image Processing 47:327–352CrossRefGoogle Scholar
  24. Wong KY, Casey RG, Wahl FM (1982) Document analysis system. IBM Journal Res. Dev. 26(6):647–656CrossRefGoogle Scholar

Copyright information

© Springer-Verlag New York Inc. 1992

Authors and Affiliations

  • Anil K. Jain
    • 1
  • Sushil Bhattacharjee
    • 1
  1. 1.Pattern Recognition and Image Processing Processing LaboratoryMichigan State UniversityE. LansingUSA

Personalised recommendations