Abstract
Segmentation is an important step in Offline Handwritten Character Recognition (Offline HCR). Line segmentation is an important activity included in segmentation process. Line segmentation is a challenging task and it becomes even more challenging when one needs to segment lines in a skewed offline handwritten document. Improper segmentation decreases the recognition accuracy considerably. In this paper, strip based projection profile technique and smearing technique with contour tracing (proposed combination) have been used for line segmentation in offline handwritten Gurmukhi script documents. We have achieved an accuracy of 98.26% for line segmentation with proposed technique and an accuracy of 93.05% for line segmentation with strip based projection profile technique.
References
Pal U, Chaudhuri BB (2004) Indian Script character recognition: a survey. Pattern Recogn 37(9):1887–1899
Shapiro V, Gluhchev G, Sgurev V (1993) Handwritten document image segmentation and analysis. Pattern Recogn 14(1):71–78
Wong K, Casey R, Wahl F (1982) Document analysis system. IBM J Res Dev 26(6):647–656
Sulem LL, Faure C (1994) Extracting text lines in handwritten documents by perceptual grouping. In: Proceedings of advances in handwriting and drawing: a multidisciplinary approach. pp 41–52
Kennard, Barret WA (2006) Separating lines of text in free-form handwritten historical documents. In: Proceedings of second international conference on document image analysis for libraries. pp. 12–23
Shi Z, Govindaraju V (2004) Line separation for complex document images using fuzzy run length. In: Proceedings of first international workshop on document image analysis for libraries. pp 306–312
Yanikoglu B, Sandon PA (1998) Segmentation of offline cursive handwriting using linear programming. Pattern Recogn 31(12):1825–1833
Li Y, Zheng Y, Doremann D, Jaeger S (2006) A new algorithm for detecting text line in handwritten documents. In: Proceedings of international workshop on handwriting recognition (IWFHR). pp 35–40
Lemaitre A, Camillerapp J (2006) Text line extraction in handwritten document with Kalman filter applied on low resolution image. In: Proceedings of international conference on DIAL. pp 38–45
Shi Z, Setlur S, Govindaraju V (2005) Text extraction from gray scale historical document images using adaptive local connectivity map. In: Proceedings of international conference on document analysis and recognition (ICDAR). pp 794–798
Basu S, Chaudhuri C, Kundu M, Nasipuri M, Basu DK (2007) Text line extraction from multi-skewed handwritten documents. Pattern Recogn 40(6):1825–1839
Bansal V, Sinha RMK (2002) Segmentation of touching and fused Devanagri characters. Pattern Recogn 35(4):875–893
Arivazhagan M, Srinivasan H, Srihari S (2007) A statistical approach to line segmentation in handwritten documents. In: Proceedings of SPIE. p 6500T
Chang F, Chen CJ (2003) A component-labeling algorithm using contour tracing technique. In: Proceedings of 7th international conference on document analysis and recognition (ICDAR). pp. 741–745
Kumar M, Sharma RK, Jindal MK (2010) Segmentation of lines and words in handwritten Gurmukhi script documents. In: Proceedings of 1st international conference on IITM. pp 27–30
Zahour A, Taconet B, Mercy P, Ramdane S (2001) Arabic hand-written text-line extraction. In: Proceedings of the 6th international conference on document analysis and recognition (ICDAR). pp 281–285
Tripathy N, Pal U (2004) Handwriting segmentation of unconstrained Oriya text. In: Proceedings of international workshop on frontiers in handwriting recognition (IWFHR). pp 306–311
Arivazhagan M, Srinivasan H, Srihari SN (2007) A statistical approach to handwritten line segmentation. In: Proceedings of SPIE document recognition and retrieval XIV. San Jose, CA
Li Y, Zheng Y, Doermann D, Jaeger S (2006) A new algorithm for detecting text line in handwritten documents. In: Proceedings of international workshop on frontiers in handwriting recognition (IWFHR). pp 35–40, 2006
Acknowledgements
Authors are thankful to the “Department of Computer Science & Engineering” at the Thapar University, Patiala for providing the necessary facilities for carrying out this work. Authors are also thankful to the writers for writing the handwritten Gurmukhi script documents.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kumar, M., Jindal, M.K. & Sharma, R.K. A Novel Technique for Line Segmentation in Offline Handwritten Gurmukhi Script Documents. Natl. Acad. Sci. Lett. 40, 273–277 (2017). https://doi.org/10.1007/s40009-017-0558-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40009-017-0558-1