Text line extraction in graphical documents using background and foreground information


In graphical documents (e.g., maps, engineering drawings), artistic documents etc., the text lines are annotated in multiple orientations or curvilinear way to illustrate different locations or symbols. For the optical character recognition of such documents, individual text lines from the documents need to be extracted. In this paper, we propose a novel method to segment such text lines and the method is based on the foreground and background information of the text components. To effectively utilize the background information, a water reservoir concept is used here. In the proposed scheme, at first, individual components are detected and grouped into character clusters in a hierarchical way using size and positional information. Next, the clusters are extended in two extreme sides to determine potential candidate regions. Finally, with the help of these candidate regions, individual lines are extracted. The experimental results are presented on different datasets of graphical documents, camera-based warped documents, noisy images containing seals, etc. The results demonstrate that our approach is robust and invariant to size and orientation of the text lines present in the document.

This is a preview of subscription content, access via your institution.


  1. 1

    Nagy G., Seth S., Viswanathan M.: A prototype document image analysis system for technical journals. Computer 25, 10–22 (1992)

    Article  Google Scholar 

  2. 2

    O’Gorman L.: The document spectrum for page layout analysis. Trans. Pattern Anal. Mach. Intell. 15, 1162–1173 (1993)

    Article  Google Scholar 

  3. 3

    Likforman, L., Zahour, A., Taconet, B.: Text line segmentation of historical documents: a Survey. Int. J. Doc. Anal. Recogn. (IJDAR), pp. 123–138 (2007)

  4. 4

    Li Y., Zheng Y., Doermann D., Jaeger S.: Script independent text line segmentation in freestyle handwritten documents. IEEE Trans. Pattern Anal. Mach. Intell. 30(8), 1313–1329 (2008)

    Article  Google Scholar 

  5. 5

    Goto H., Aso H.: Extracting curved lines using local linearity of the text line. Int. Conf. Doc. Anal. Recogn. (IJDAR) 2, 111–118 (1999)

    Article  Google Scholar 

  6. 6

    Hones F., Lichter J.: Layout extraction of mixed mode documents. Mach. Vis. Appl. 7, 237–246 (1994)

    Article  Google Scholar 

  7. 7

    Loo, P.K., Tan, C.L.: Word and sentence extraction using irregular pyramid. Workshop on Document Analysis System (DAS), pp. 307–318 (2002)

  8. 8

    Bukhari, S.S., Shafait, F., Breuel, T.M.: Segmentation of curled textlines using active contours. In: 8th IAPR Workshop on Document Analysis Systems (DAS), pp. 270–277 (2008)

  9. 9

    Gatos, B., Pratikakis, I., Ntirogiannis, K.: Segmentation based recovery of arbitrarily warped document images. In: Proceedings of International Conference on Document Analysis and Recognition (ICDAR) (2007)

  10. 10

    Bai, N.N., Nam, K., Song, Y.: Extracting curved text lines using the chain composition and the expanded grouping method. Document Recognition and Retrieval XV, USA (2008)

  11. 11

    Pal U., Roy P.P.: Multi-oriented and curved text lines extraction from Indian documents. IEEE Trans. SMC B 34, 1676–1684 (2004)

    Google Scholar 

  12. 12

    Pal, U., Sinha, S., Chaudhuri, B.B.: English multi-oriented text line extraction. Image analysis, Lecture Notes on Computer Science (LNCS-2749). Springer, pp. 1146–1153 (2003)

  13. 13

    Tombre, K., Tabbone, S., Peissier, L., Lamiroy, B., Dosch, P.: Text /graphics separation revisited. In: Workshop on Document Analysis System (DAS), LNCS. 2423, 200–211 (2002) Springer, London

  14. 14

    Fletcher L.A., Kasturi R.: A robust algorithm for text string separation from mixed text/graphics images. IEEE Trans. Pattern Anal. Mach. Intell. 10, 910–918 (1988)

    Article  Google Scholar 

  15. 15

    Pal U., Belaïd A., Choisy Ch.: Touching numeral segmentation using water reservoir concept. Pattern Recogn. Lett. 24, 261–272 (2003)

    Article  Google Scholar 

  16. 16

    Otsu N.: A threshold selection method from grey level histogram. IEEE Trans. SMC 9, 62–66 (1979)

    Google Scholar 

  17. 17

    Roy, K., Pal, U., Chaudhuri, B.B.: A system for joining and recognition of broken bangla numerals for Indian postal automation. In: Proceedings of 4th Indian Conference on Computer Vision, Graphics and Image Processing, pp 641–646 (2004)

  18. 18

    Shafait, F., Breuel, T.M.: Document image dewarping contest. In: 2nd International Workshop on Camera-Based Document Analysis and Recognition (CBDAR). Curitiba, Brazil (2007)

  19. 19

    Delalandre, M., Pridmore, T., Valveny, E., Trupin, E., Locteau, H.: Building synthetic graphical documents for performance evaluation. In: Workshop on Graphics Recognition (GREC), Lecture Note in Computer Science (LNCS), vol. 5046, pp. 288–298 (2008)

  20. 20

    Park H.C., Ok S.Y., Yu Y.J., Cho H.G.: Word extraction in text/graphic mixed image using 3-dimensional graph model. Int. J. Doc. Anal. Recogn. (IJDAR) 4, 115–130 (2001)

    Article  Google Scholar 

  21. 21

    Tan C.L., Ng P.O.: Text extraction using pyramid. Pattern Recogn. 31, 63–72 (1998)

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to Partha Pratim Roy.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Roy, P.P., Pal, U. & Lladós, J. Text line extraction in graphical documents using background and foreground information. IJDAR 15, 227–241 (2012). https://doi.org/10.1007/s10032-011-0167-3

Download citation


  • Multi-oriented text line segmentation
  • Artistic documents
  • Graphical document analysis
  • Foreground-background information