Abstract
Segmentation of characters is a major step in the OCR system, and recognition accuracy will highly depend on good segmentation. The segmentation in Devanagari script is more cumbersome than Latin script because of the presence of a large character set which includes modifiers, compound characters, complex connected characters, and shirorekha. Shirorekha creates the major problem in Devanagari character segmentation, and it reduces segmentation accuracy as compared to Latin script. This paper gives a comparative study on various segmentation techniques used for Devanagari script and finds an efficient approach from these techniques.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Singh R, Yadav S, Verma P (2010) Optical character recognition (OCR) for printed Devanagari script using artificial neural network. Int J Comput Sci Commun 1(1):91–95
Sahare P, Dhok SB (2018) Robust character segmentation and recognition schemes for multilingual Indian document images. IETE Techn Rev. https://doi.org/10.1080/02564602.2018.1450649
Mathew M, Singh AK, Jawahar CV (2016) Multilingual OCR for Indic scripts. In: Proceedings of 12th IAPR Workshop Document Analysis Systems, pp 186—191. IEEE Press, Santorini (2016)
Kumar V, Senger PK (2010) Segmentation of printed text in Devanagari Script and Gurmukhi Script. Int J Comput Appl 3(8):0975–8887
Thakral B, Kumar M (2014) Devanagari handwritten text segmentation for overlapping and conjunct characters—a proficient technique. In: Proceedings of 3rd International conference on reliability, Infocom Technologies and Optimization. https://doi.org/10.1109/ICRITO.2014.7014746
Kohli M, Kumar S (2020) Comparative analysis of segmentation and recognition techniques for offline handwritten words. Int Res J Adv Sci Hub (IRJASH) 02:41–48
Bag S, Krishna A (2015) Character segmentation of hindi unconstrained handwritten words. In: Proceedings of the 17th International Workshop on combinatorial image analysis, pp 247–260. Springer, Cham
Castro MJ, Jose M, Moya JG, Martinez FZ (2011) Improving offline handwritten text recognition with hybrid HMM/ANN models. IEEE Trans Pattern Anal Mach Intell 33:767–779
Sharma MK, Dhaka VP (2016) Pixel plot and trace-based segmentation method for bilingual handwritten scripts using feedforward neural network. Neural Comput Appl 27(7):1817–1829
Sharma MK, Dhaka VP (2015) An efficient segmentation technique for Devanagari off-line handwritten scripts using the feedforward neural network. Neural Comput Appl 26(8):1881–1893
Sharma MK, Dhaka VP (2016) Segmentation of English off-line handwritten cursive scripts using a feedforward neural network. Neural Comput Appl 27(5):1369–1379
Roy PP, Pal U, Lladós J (2012) Delalandre: multi-oriented touching text character segmentation in graphical documents using dynamic programming. Pattern Recogn 45(5):1972–1983
Bansal V, Sinha RMK (2002) Segmentation of touching and fused Devanagari characters. Pattern Recogn 35:875–893
Garain U, Chaudhuri BB (2001) Segmentation of touching characters in printed Devanagari and Bangla scripts using fuzzy multifactorial analysis. IEEE Trans Syst Man Cybern Part C Appl Rev, 805—809
Kompalli S, Nayak S, Setlur S, Govindaraju V (2005) Challenges in OCR of Devanagari documents. In: Proceedings of 8th conference on document analysis and recognition, pp 1–5. IEEE Press, Seoul
Garain U, Chaudhuri BB (2002) On OCR of degraded documents using fuzzy multifactorial analysis. In: Proceedings of AFSS international conference on fuzzy systems (AFSS-ICFS), pp 388–394. Springer, Calcutta
Bathla AK, Gupta SK, Jindal MK (2019) Character segmentation and skew correction for handwritten Devanagari scripts: a friends technique. Asian J Eng Appl Technol 8(1):50–54
Malpe K, Wankhade M (2018) Segmentation of Hindi handwritten words and personality prediction using word spacing and margin. Int J Innov Res Sci Eng Technol 7(2):1250–1260
Vishwanath NV, Manjunathachari K, Prasad KS (2020) Edge-oriented filter and feature invariant coding for multilingual character segmentation and recognition. J Crit Rev 7(14):610–620
Sharma P, Sachan MK (2017) A technique for character segmentation in the middle zone of handwritten Hindi words using hybrid approach. Int J Fut Revol Comput Sci Commun Eng 3(7):1–10
Jindal K, Kumar R (2018) A new method for segmentation of pre-detected Devanagari words from the scene images: Pihu method. Comput Electr Eng 70:754–763
Pramanik R, Bag S, Kumar R (2018) A fuzzy and contour-based segmentation methodology for handwritten Hindi words in legal documents. In: 4th Int’l conference on recent advances in information technology, pp 388–394. IEEE Press, Dhanbad
Kaur M, Bathla AK (2017) Segmentation of characters of Devanagari script documents. World Wide J Multidisc Res Dev 3(11):253–257
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sonkusare, M., Gupta, R., Moghe, A. (2021). A Review on Character Segmentation Approach for Devanagari Script. In: Sheth, A., Sinhal, A., Shrivastava, A., Pandey, A.K. (eds) Intelligent Systems. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-16-2248-9_19
Download citation
DOI: https://doi.org/10.1007/978-981-16-2248-9_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2247-2
Online ISBN: 978-981-16-2248-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)