Line and Ligature Segmentation for Nastaliq Script

  • Mehvish YasinEmail author
  • Naveen Kumar Gondhi
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 35)


The accuracy rate of recognizing ligatures in Urdu Character Recognition mostly relies on the accuracy with which the segmentation has been performed to convert Urdu text into lines and ligatures. Generally, it has been seen that the ligature based segmentation yields better results rather than character based segmentation. In this paper, we present a technique for segmenting Urdu text images into lines and then to ligatures. A hybrid approach has been used, which employs top-down technique in order to perform line segmentation and bottom-up technique in order to segment lines into ligatures. The various issues like broken lines, diacritic association, overlapping has also been discussed.


Nastaliq Segmentation Ligatures Zones Overlapping 


  1. 1.
    Daud, A., Khan, W., Che, D.: Urdu language processing: a survey. Artif. Intell. Rev. 47, 1–33 (2016)Google Scholar
  2. 2.
    Pal, U., Sarkar, A.: In: International Conference on Document Analysis and Recognition, vol. 2, pp. 1183–1187 (2003)Google Scholar
  3. 3.
    Ul-Hasan, A., Ahmed, S.B., Rashid, F., Shafait, F., Breuel, T.M.: In: Document Analysis and Recognition (ICDAR), pp. 1061–1065. IEEE (2013)Google Scholar
  4. 4.
    Din, I.U., Malik, Z., Siddiqi, I., Khalid, S.: J. Appl. Environ. Biol. Sci 6, 114–120 (2016)Google Scholar
  5. 5.
    Amad, I., Wang, X., Li, R., Ahmed, M., Ullah, R.: Line and ligature segmentation of urdu nastaleeq text. IEEE access 5, 10924–10940 (2017)CrossRefGoogle Scholar
  6. 6.
    Malik, H., Fahiem, M.A.: Segmentation of printed urdu scripts using structural features. In: Second International Conference in Visualisation, 2009. VIZ 2009, pp. 191–195. IEEE (2009)Google Scholar
  7. 7.
    Kumar, K.S., Kumar, S., Jawahar, C.: In: Document Analysis and Recognition (2007)Google Scholar
  8. 8.
    Breuel, T.M.: In: International Workshop on Document Analysis Systems, pp. 188–199. Springer (2002)Google Scholar
  9. 9.
    Bukhari, S.S., Shafait, F., Breuel, T.M.: In: Document Analysis and Recognition (ICDAR), pp. 748–752. IEEE (2013)Google Scholar
  10. 10.
    Javed, S.T., Hussain, S.: In: Multitopic Conference INMIC, pp. 1–6. IEEE (2009)Google Scholar
  11. 11.
    Lehal, G.S.: In: Document Analysis and Recognition (ICDAR), pp. 1130–1134. IEEE (2013)Google Scholar
  12. 12.
    Hussain, S., Ali, S., et al.: Nastalique segmentation-based approach for Urdu OCR. Int. J. Doc. Anal. Recog. (IJDAR) 18(4), 357–374 (2015)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.SMVDUKatraIndia

Personalised recommendations