Line Segmentation Challenges in Tamil Language Palm Leaf Manuscripts
R. Spurgen Ratheash1, M. Mohamed Sathikn2

1R. Spurgen Ratheash*, Assistant Professor of Information Technology, received his MCA degree in Computer Applications from Bishop Heber College, Bharathidasan University, Trichy, India.
2M. Mohamed Sathik, PG and Research Department of Computer Science, Sadakathullah Appa College, Tirunelveli, Tamilnadu, India. Manonmaniam Sundaranar University, Tamilnadu, India.

Manuscript received on October 15, 2019. | Revised Manuscript received on 24 October, 2019. | Manuscript published on November 10, 2019. | PP: 2363-2367 | Volume-9 Issue-1, November 2019. | Retrieval Number: L31591081219/2019©BEIESP | DOI: 10.35940/ijitee.L3159.119119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: The process of an Optical Character Recognition (OCR) for ancient hand written documents or palm leaf manuscripts is done by means of four phases. The four phases are ‘line segmentation’, ‘word segmentation’, ‘character segmentation’, and ‘character recognition’. The colour image of palm leaf manuscripts are changed into binary images by using various pre-processing methods. The first phase of an OCR might break through the hurdles of touching lines and overlapping lines. The character recognition becomes futile when the line segmentation is erroneous. In Tamil language palm leaf manuscript recognition, there are only a handful of line segmentation methods. Moreover, the available methods are not viable to meet the required standards. This article is proposed to fill the lacuna in terms of the methods necessary for line segmentation in Tamil language document analysis. The method proposed compares its efficiency with the line segmentation algorithms work on binary images such as the Adaptive Partial Projection (APP) and A* Path Planning (A*PP). The tools and criteria of evaluation metrics are measured from ICDAR 2013 Handwriting Segmentation Contest.
Keywords: Line Segmentation, Tamil palm leaf Manuscripts, Connected Component, Historical Documents, Tamil Character Recognition
Scope of the Article: Pattern Recognition