Two Geometric Algorithms for Layout Analysis

  • Thomas M. Breuel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2423)


This paper presents geometric algorithms for solving two key problems in layout analysis: finding a cover of the background whitespace of a document in terms of maximal empty rectangles, and finding constrained maximum likelihood matches of geometric text line models in the presence of geometric obstacles. The algorithms are considerably easier to implement than prior methods, they return globally optimal solutions, and they require no heuristics. The paper also introduces an evaluation function that reliably identifies maximal empty rectangles corresponding to column boundaries. Combining this evaluation function with the two geometric algorithms results in an easy-to-implement layout analysis system. Reliability of the system is demonstrated on documents from the UW3 database.


  1. 1.
    H. S. Baird. Background structure in document images. In H. Bunke, P. S. P. Wang, & H. S. Baird Eds., Document Image Analysis, World Scientific, Singapore, pages 17–34, 1994.Google Scholar
  2. 2.
    H. S. Baird, S. E. Jones, and S. J. Fortune. Image segmentation by shape-directed covers. In Proceedings of the Tenth International Conference on Pattern Recognition, Atlantic City, New Jersey, pages 820–825, 1990.Google Scholar
  3. 3.
    Thomas M. Breuel. Fast Recognition using Adaptive Subdivisions of Transformation Space. In Proceedings IEEE Conf. on Computer Vision and Pattern Recognition, pages 445–451, 1992.Google Scholar
  4. 4.
    Thomas M. Breuel. Finding Lines under Bounded Error. Pattern Recognition, 29(1):167–178, 1996.CrossRefGoogle Scholar
  5. 5.
    T.M. Breuel. Robust least square baseline finding using a branch and bound algorithm. In Proceedings of the SPIE-The International Society for Optical Engineering, page (in press), 2002.Google Scholar
  6. 6.
    R. Cattoni, T. Coianiz, S. Messelodi, and C. M. Modena. Geometric layout analysis techniques for document image understanding: a review. Technical report, IRST, Trento, Italy, 1998.Google Scholar
  7. 7.
    William Wells III. Statistical approaches to feature-based object recognition. International Journal of Computer Vision, 21(1/2):63–98, 1997.CrossRefGoogle Scholar
  8. 8.
    D. Ittner and H. Baird. Language-free layout analysis, 1993.Google Scholar
  9. 9.
    K. Kise, A. Sato, and M. Iwata. Segmentation of page images using the area voronoi diagram. Computer Vision and Image Understanding, 70(3):370–82, June 1998.CrossRefGoogle Scholar
  10. 10.
    J. Liang, I. T. Philips, and R. M. Haralick. An optimization methodology for document structure extraction on latin character documents. Pattern Analysis and Machine Intelligence, pages 719–734, 2001.Google Scholar
  11. 11.
    M. Orlowski. A new algorithm for the largest empty rectangle problem. Algorithmica, 5(1), 1990.Google Scholar
  12. 12.
    T. Pavlidis and J. Zhou. Page segementation by white streams. In 1st ICDAR, Saint-Malo, pages 945–953, 1991.Google Scholar
  13. 13.
    J. P. Trincklin. Conception d’un systéme d’analyse de documents. PhD thesis, Thêse de doctorat, Université de Franche-Compté, 1984.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Thomas M. Breuel
    • 1
  1. 1.Xerox Palo Alto Research CenterPalo Alto

Personalised recommendations