Text Segmentation from Land Map Images

  • Samit Biswas
  • Amit Kumar Das
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8251)


Text segmentation from scanned map images is a challenging task as the texts in maps have wide variation in font, skew, spatial spread, touching components and a myriad background. We present a segmentation process by separating map components to three layers based on their areas. Further analysis, on spatial spread and node density from component graph leads to segmentation with encouraging performance.


Extremum Point Middle Layer Edge Weight Node Density Junction Point 
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.


  1. 1.
    Tofani, P., Kasturi, R.: Segmentation of text from color map images. In: Proceedings of the Fourteenth International Conference on Pattern Recognition, vol. 1, pp. 945–947 (August 1998)Google Scholar
  2. 2.
    Li, L., Nagy, G., Samal, A., Seth, S., Xu, Y.: Cooperative text and line-art extraction from a topographic map. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition, ICDAR 1999, pp. 467–470 (September 1999)Google Scholar
  3. 3.
    Cao, R., Tan, C.L.: Text/graphics separation in maps. In: Proceedings of the 4th International Workshop on Graphics Recognition Algorithms and Applications, pp. 245–254 (2001)Google Scholar
  4. 4.
    Roy, P.P., Vazquez, E., Lladós, J., Baldrich, R., Pal, U.: A system to segment text and symbols from color maps. In: Liu, W., Lladós, J., Ogier, J.-M. (eds.) GREC 2007. LNCS, vol. 5046, pp. 245–256. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Roy, P., Llados, J., Pal, U.: Text/graphics separation in color maps. In: International Conference on Computing: Theory and Applications, ICCTA 2007, pp. 545–551 (2007)Google Scholar
  6. 6.
    Pezeshk, A., Tutwiler, R.L.: Improved multi angled parallelism for separation of text from intersecting linear features in scanned topographic maps. In: ICASSP, pp. 1078–1081 (2010)Google Scholar
  7. 7.
    Pezeshk, A., Tutwiler, R.L.: Automatic feature extraction and text recognition from scanned topographic maps. IEEE T. Geoscience and Remote Sensing 49(12), 5047–5063 (2011)CrossRefGoogle Scholar
  8. 8.
    Biswas, S., Das, A.K.: Text segmentation from scanned land map images using radon transform based projection profile. In: 2011 International Conference of Soft Computing and Pattern Recognition (SoCPaR), pp. 413–418 (October 2011)Google Scholar
  9. 9.
    Biswas, S., Das, A.K.: Fuzzy graph modeling for text segmentation from land map images. In: Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012, pp. 75:1–75:7 (2012)Google Scholar
  10. 10.
    Biswas, S., Das, A.K.: Text extraction from scanned land map images. In: IEEE/OSA/IAPR International Conference on Informatics, Electronics & Vision, Dhaka, pp. 231–236 (May 2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Samit Biswas
    • 1
  • Amit Kumar Das
    • 1
  1. 1.CST DepartmentBESUShibpurIndia

Personalised recommendations