Advertisement

Primitive Feature-Based Optical Character Recognition of the Devanagari Script

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 714)

Abstract

The Devanagari script forms the backbone of the writing system of several Indian languages including Sanskrit and Hindi. This paper proposes a method to recognize a Devanagari character from a digital image using primitive feature information. The procedure involves representing each character in terms of the presence and location of primitive features like vertical lines, the frequency, and location of the intersections and the frequency of intersections of character body with Shirorekha (the top horizontal line of a Devanagari character). The classification of the character is done on the basis of the existence and (if present) the location of these features in the glyph (test character). The proposed method gave 93.33% accuracy with 21 fonts used for Hindi, Sanskrit, and Marathi and 72.72% accuracy for the handwritten character samples taken from 22 different people from varied age groups for the Ka-Varga—the first five consonants of the Devanagari script. The method worked better for handwritten samples of younger people (aged 20–25 years) than the older ones (aged 40–50 years).

Keywords

Optical character recognition (OCR) Devanagari Hindi OCR Primitive feature-based OCR 

References

  1. 1.
    Cardona, G.: Devanagari. (Encyclopædia Britannica, inc.), https://www.britannica.com/topic/Devanagari, last accessed 2017/05/17.
  2. 2.
    Hanmandlu, M., Murthy, O. R.: Fuzzy model based recognition of handwritten numerals. The journal of the pattern recognition society, 1840–1854 (2007).Google Scholar
  3. 3.
    Sethi, K., Chatterjee, B.: Machine Recognition of constrained handprinted Devanagari. Pattern Recognition 9, 69–75 (1977).Google Scholar
  4. 4.
    Bansal, V., Sinha, R.: A Complete OCR for Printed Hindi Text in Devanagari Script. Proceedings 6th conference on document analysis and recognition, 800–804 (2001).Google Scholar
  5. 5.
    Aggarwal, A., Rani, R., RenuDhir.: Handwritten Devanagari Character Recognition Using Gradient Features. International Journal of Advanced Research in Computer Science and Software Engineering 2, 85–90 (2012).Google Scholar
  6. 6.
    Sarkar, R., Sen, B., Das, N., Basu, S.: Handwritten Devanagari Script Segmentation: A Non-linear Fuzzy Approach. Proc. (CD) of IEEE Conference on AI Tools and Engineering (ICAITE-08) (2008).Google Scholar
  7. 7.
    Mukherji, P., Rege, P. P.: Shape Feature and Fuzzy Logic Based Offline Devnagari Handwritten Optical Character Recognition. Journal of Pattern Recognition Research, 52–68 (2009).Google Scholar
  8. 8.
    Goyal, P., Diwakar, S., Agrawal, A.: Devanagari Character Recognition towards natural Human-Computer Interaction. Proceedings India HCI No EPFL-CONF-168804 (2010).Google Scholar
  9. 9.
    Pal, U., Chaudhuri, B.: Indian script character recognition: a survey. The journal of pattern recognition, 1887–1899 (2004).Google Scholar
  10. 10.
    Sethi, I. K., Chatterjee, B.: Machine Recognition of handprinted Devanagari Numerals. J. Institute of Electrical Telecommunication Engineering (India) 22, 532–535 (1976).Google Scholar
  11. 11.
    Sinha, R. M., Mahabala, H. N.: Machine recognition of Devanagari script. IEEE Transactions on Systems, Man and Cybernetics, 435–441(1979).Google Scholar
  12. 12.
    Siromoney, G., Chandrasekaran, R., Chandrasekaran, M.: Machine recognition of Brahmi script. IEEE Transactions on Systems, Man and Cybernetics (1983).Google Scholar
  13. 13.
    Sinha, R. M.: Role of contextual postprocessing for Devanagari text recognition. Pattern Recognition, 475–485 (1987).Google Scholar
  14. 14.
    Marudarajan, A. R., Jayanthi, K., Rajeswari, M.: Extension of adaptive threshold logic to printed Hindi numeral recognition. Journal of Institute of Electricaland Telecommunication Engineering (India), 223–225 (1978).Google Scholar
  15. 15.
    Banashree., P. N., Dharani, A., Vasanta, R., Satyanarayana, P. S.: OCR for Script Identification of Hindi (Devnagari) Numerals using Error Diffusion Halftoning Algorithm with Neural Classifier. International Journal of Computer, Electrical, Automation, Control and Information Engineering 1, 307–311 (2007).Google Scholar
  16. 16.
    Ghosh, R., Roy, P. P.: Study of two zone-based features for online Bengali and Devanagari character recognition. 2015 13th Int. Conf. on Document Analysis and Recognition (ICDAR), 401–405 (2015).Google Scholar
  17. 17.
    Kushwah, K. K., Joshi, B. K.: Hindi modifier recognition based on pixel relationship. 2016 Int. Conf. on ICT in Business Industry & Government (ICTBIG) (2016).Google Scholar
  18. 18.
    Kant, Mr Akshay J., Mrs Arati J. Vyavahare.: Devanagari OCR Using Projection Profile Segmentation Method. International Research Journal of Engineering and Technology (IRJET) (2016).Google Scholar
  19. 19.
    Gupta, M.K., Lakshmi, C.V., Hanmandlu, M., Patvardhan, C.: An Exhaustive Font and Size Invariant Classification Scheme for OCR of Devanagari Character. International Journal on Natural Language Computing, 4(1), 1–21 (2014).Google Scholar
  20. 20.
    Chaudhuri, A., Mandaviya, K., Badelia, P., Ghosh, S. K.: Optical Character Recognition Systems for Hindi Language. In Optical Character Recognition Systems for Different Languages with Soft Computing, pp. 193–216. Springer International Publishing (2017).Google Scholar
  21. 21.
    Bansal, V., Sinha, R.M.K.: Segmentation of touching and fused Devanagari characters. Pattern Recognition 35, 875–893 (2002).Google Scholar
  22. 22.
    Otsu, N.: A threshold selection method from gray level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 62–66 (1979).Google Scholar
  23. 23.
    Kumar, R., Kumar, A., Ahmed, P.: A benchmark dataset for Devanagari document recognition research. 6th International Conference on Visualization, Imaging and Simulation (VIS’13), 258–263 (2013).Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer ScienceKeshav Mahavidyalaya, University of DelhiNew DelhiIndia

Personalised recommendations