Abstract
Most of the reports either printed or handwritten comprised of significant data that can be helpful in the future. The papers generally rot with time that can lose data totally or up to some extent. Optical character recognition is the process which is used in sparing information from paper for further processing. Text line segmentation is a significant phase in character recognition because incorrectly divided text lines can cause errors in the recognition stage. In this paper, single-column and multi-column documents from different books, magazines and papers imprinted in Devanagari script had been considered. As a result of the low quality of papers in few documents and the unpredictability and complexity of these documents (background noise, paper decay due to aging, short lines, justified lines, distorted text lines), programmed text line segmentation remains an open research field. In this article, the authors have presented a new technique for unconstrained text line segmentation of Devanagari text using a combination of headline detection and median calculation of text line heights.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sahare P, Dhok SB (2018) Multilingual character segmentation and recognition schemes for Indian document images. IEEE Access 6:10603–10617
Kumar V, Sengar PK (2010) Segmentation of printed text in Devanagari script and Gurmukhi script. Int J Comput Appl 3(8):30–33
Garg R, Garg NK (2014) An algorithm for text line segmentation in handwritten skewed and overlapped Devanagari script. Int J Emerg Trends Eng Dev 4(5):114–118
Lehal GS (2013) Ligature segmentation for Urdu OCR. In: 12th International conference on document analysis and recognition (ICDAR), pp 1130–1134
Palakollu S, Dhir R, Rani R (2012) W2. In: Proceedings of the world congress on engineering and computer science, vol. 1, pp 24–26
Zinjore RS, Ramteke RJ, Pathak VM (2017) Segmentation of merged lines and script identification in handwritten bilingual documents. In: Proceedings of the 9th annual meeting of the forum for ınformation retrieval evaluation, pp 29–32
Shukla MK, Banka H (2014) Line-wise Script segmentation for Indian language documents. Int J Comput Appl 108(9):34–37
Jindal MK, Sharma RK, Lehal GS (2007) Segmentation of horizontally overlapping lines in printed Indian scripts. Int J Comput Int Res 3(4):277–286
Jindal MK, Lehal GS, Sharma RK (2009) On segmentation of touching characters and overlapping lines in degraded printed Gurmukhi script. Int J Image Graph 9(03):321–353
Pal U, Chaudhuri BB (1997) Printed Devanagari script OCR system. Vivek 10:12–24
Chaudhuri BB, Pal U (1997) Skew angle detection of digitized Indian script documents. IEEE Trans Pattern Anal Mach Intell 19(2):182–186
Ramteke AS, Rane ME (2012) Offline handwritten Devanagari script segmentation. Int J Sci Technol Res 1(4):142–145
Malgi S, Pramod, Gayakwad S (2014) Line segmentation of Devanagari handwritten documents. Int J Electron Commun Instrumen Eng Res Dev 4(2):25–32
Lehal GS, Singh C (2000) A Gurmukhi script recognition system. In: Proceedings 15th international conference on pattern recognition 2, pp 557–560
Kumar M, Sharma RK, Jindal MK (2010a) Segmentation of lines and words in handwritten Gurmukhi script documents. In: Proceedings of the first international conference on intelligent interactive technologies and multimedia, 25–28
Mahmud SM, Shahrier N, Hossain AD, Chowdhury MTM, Sattar MA (2003) An efficient segmentation scheme for the recognition of printed Bangla characters. In: Proceedings of ICCIT, pp 283–286
Hasnat MA, Habib SM, Khan M (2008) A high performance domain specific OCR for Bangla script. In: Novel algorithms and techniques in telecommunications, automation and industrial electronics, pp 174–178
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kaur, R.P., Jindal, M.K., Kumar, M. (2021). TxtLineSeg: Text Line Segmentation of Unconstrained Printed Text in Devanagari Script. In: Singh, V., Asari, V.K., Kumar, S., Patel, R.B. (eds) Computational Methods and Data Engineering. Advances in Intelligent Systems and Computing, vol 1257. Springer, Singapore. https://doi.org/10.1007/978-981-15-7907-3_7
Download citation
DOI: https://doi.org/10.1007/978-981-15-7907-3_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7906-6
Online ISBN: 978-981-15-7907-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)