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).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cardona, G.: Devanagari. (Encyclopædia Britannica, inc.), https://www.britannica.com/topic/Devanagari, last accessed 2017/05/17.
Hanmandlu, M., Murthy, O. R.: Fuzzy model based recognition of handwritten numerals. The journal of the pattern recognition society, 1840–1854 (2007).
Sethi, K., Chatterjee, B.: Machine Recognition of constrained handprinted Devanagari. Pattern Recognition 9, 69–75 (1977).
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).
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).
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).
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).
Goyal, P., Diwakar, S., Agrawal, A.: Devanagari Character Recognition towards natural Human-Computer Interaction. Proceedings India HCI No EPFL-CONF-168804 (2010).
Pal, U., Chaudhuri, B.: Indian script character recognition: a survey. The journal of pattern recognition, 1887–1899 (2004).
Sethi, I. K., Chatterjee, B.: Machine Recognition of handprinted Devanagari Numerals. J. Institute of Electrical Telecommunication Engineering (India) 22, 532–535 (1976).
Sinha, R. M., Mahabala, H. N.: Machine recognition of Devanagari script. IEEE Transactions on Systems, Man and Cybernetics, 435–441(1979).
Siromoney, G., Chandrasekaran, R., Chandrasekaran, M.: Machine recognition of Brahmi script. IEEE Transactions on Systems, Man and Cybernetics (1983).
Sinha, R. M.: Role of contextual postprocessing for Devanagari text recognition. Pattern Recognition, 475–485 (1987).
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).
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).
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).
Kushwah, K. K., Joshi, B. K.: Hindi modifier recognition based on pixel relationship. 2016 Int. Conf. on ICT in Business Industry & Government (ICTBIG) (2016).
Kant, Mr Akshay J., Mrs Arati J. Vyavahare.: Devanagari OCR Using Projection Profile Segmentation Method. International Research Journal of Engineering and Technology (IRJET) (2016).
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).
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).
Bansal, V., Sinha, R.M.K.: Segmentation of touching and fused Devanagari characters. Pattern Recognition 35, 875–893 (2002).
Otsu, N.: A threshold selection method from gray level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 62–66 (1979).
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).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sharma, R., Mudgal, T. (2019). Primitive Feature-Based Optical Character Recognition of the Devanagari Script. In: Panigrahi, C., Pujari, A., Misra, S., Pati, B., Li, KC. (eds) Progress in Advanced Computing and Intelligent Engineering. Advances in Intelligent Systems and Computing, vol 714. Springer, Singapore. https://doi.org/10.1007/978-981-13-0224-4_23
Download citation
DOI: https://doi.org/10.1007/978-981-13-0224-4_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-0223-7
Online ISBN: 978-981-13-0224-4
eBook Packages: EngineeringEngineering (R0)