Line-Level Script Identification for Six Handwritten Scripts Using Texture Based Features

  • Pawan Kumar Singh
  • Ram Sarkar
  • Mita Nasipuri
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 340)


Script identification from a given document image has some important applicability in many computer applications such as automatic archiving of multilingual documents, searching online archives of document images and for the selection of script specific Optical Character Recognition (OCR) engine in any multilingual environment. In this paper, we propose a texture based approach for text line-level script identification of six handwritten scripts namely, Bangla, Devnagari, Malayalam, Tamil, Telugu and Roman. A set of 80 features based on Gray Level Co-occurrence Matrix (GLCM) has been designed for the present work. Multi Layer Perceptron (MLP) is found to be the best classifier among a set of popular multiple classifiers which is then extensively tested by tuning different parameters. Finally, an accuracy of 95.67 % has been achieved on a dataset of 600 text lines using 3-fold cross validation with epoch size 1,500 of MLP classifier.


Script identification Handwritten documents Texture based feature Gray level Co-occurrence matrix Multiple classifiers 


  1. 1.
    Pal, U., Chaudhuri, B.B.: Script line separation from indian multi-script documents. In: Proceedings of 5th International Conference on Document Analysis and Recognition (ICDAR), pp. 406–409. (1999)Google Scholar
  2. 2.
    Pal, U., Chaudhuri, B.B.: Identification of different script lines from multi-script documents. Image Vis. Comput. 20(13–14), 945–954 (2002)CrossRefGoogle Scholar
  3. 3.
    Pal, U., Sinha, S., Chaudhuri, B.B.: Multi-script line identification from indian documents. In: Proceedings of 7th International Conference on Document Analysis and Recognition (ICDAR), pp. 880–884. (2003)Google Scholar
  4. 4.
    Joshi, G.D., Garg, S., Sivaswamy, J.: Script identification from Indian documents. In: International Workshop Document Analysis Systems, Nelson. Lecture Notes in Computer Science, vol. 3872, pp. 255–267. (2006)Google Scholar
  5. 5.
    Padma, M.C., Vijaya, P.A.: Identification of Telugu, Devnagari and English scripts using discriminating features. Int. J. Comput. Sci. Inf. Technol. (IJCSIT) 1(2), 64–78 (2009)Google Scholar
  6. 6.
    Gopakumar, R., SubbaReddy, N.V., Makkithaya, K., Dinesh Acharya, U.: Script identification from multilingual indian documents using structural features. J. Comput. 2(7), 106–111 (2010)Google Scholar
  7. 7.
    Chaudhuri, B.B., Bera, S.: Handwritten text line identification in Indian scripts. In: Proceedings of 10th International Conference on Document Analysis and Recognition, pp. 636–640. (2009)Google Scholar
  8. 8.
    Hangarge, M., Dhandra, B.V.: Offline handwritten script identification in document images. Int. J. Comput. Appl. (IJCA) 4(6), 6–10 (2010)Google Scholar
  9. 9.
    Haralick, R.M., Shanmungam, K., Dinstein, I.: Textural features of image classification. IEEE Trans. Syst. Man, Cybern. 3, 610–621 (1973)CrossRefGoogle Scholar
  10. 10.
    Haralick, R.M., Watson, L.: A facet model for image data. Comput. Vision Graph. Image Process. 15, 113–129 (1981)CrossRefGoogle Scholar
  11. 11.
    Busch, A., Boles, W.W., Sridharan, S.: Texture for script identification. IEEE Trans. Pattern Anal. Mach. Intell. 27, 1720–1732 (2005)CrossRefGoogle Scholar
  12. 12.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, vol. I. PHI, New Delhi (1992)Google Scholar
  13. 13.
    Sarkar, R., Das, N., Basu, S., Kundu, M., Nasipuri, M.: Extraction of text lines from handwritten documents using piecewise water flow technique. J. Intell. Syst. 23(3), 245–260 (2014)Google Scholar
  14. 14.
    Ostu, N.: A thresholding selection method from gray-level histogram. IEEE Trans. Syst. Man Cybern. SMC-8, 62–66 (1978)Google Scholar
  15. 15.

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringJadavpur UniversityKolkataIndia

Personalised recommendations