Author : Pruthvi B K 1
Date of Publication :7th May 2016
Abstract: Segmentation is a vital procedure of any Optical Character Recognition (OCR) framework. It isolates the image content documents first into lines then to words lastly to characters. The accuracy of OCR framework for the most part relies on upon the segmentation algorithm being utilized. Segmentation of printed content of some Indian dialects like Kannada, Telugu and Assamese is troublesome when contrasted and Latin based dialects as a result of its auxiliary many-sided quality and expanded character set. It is be partitioned as vowels and consonants which can likewise contain subscripts and conjunct consonants. In spite of a few effective works in OCR everywhere throughout the world, advancement of OCR instruments in Indian dialects is still a progressing process. Character segmentation assumes a vital part in character acknowledgment in light of the fact that erroneously divided characters are unrealistic to be perceived accurately. In this paper, a segmentation plan for dividing printed Kannada scripts into lines and words utilizing Run Length Smoothing Algorithm (RLSA) and Variational Bayes (VB) strategies are proposed and their comparative analysis is carried out.
Reference :
-
[1] Zaidi Razak, Khansa Zulkiflee, Mohd Yamani IdnaIdris, Emran Mohd Tamil, Mohd Noorzaily, Mohamed Noor, Rosli Salleh, MohdYaakob, Zulkifli Mohd Yusof, and Mashkuri Yaacob, “Off-line Handwriting Text Line Segmentation: A Review”, 2008.
[2] S. Nicolas, T. Paquet, L. Heutte, “Text line segmentation in handwritten document using a production system”, 2004.
[3] F. Yin and C L Liu, “A Variational Bayes Method for Handwritten Text Line Segmentation”, 2009.
[4] T. Sari and M. Sellami, “Overview of Some Algorithms of Off-Line Arabic Handwriting Segmentation”, 2007.
[5] B. Gatos, A. Antonacopoulos and N. Stamatopoulos, “ICDAR2009 Handwriting Segmentation Contest”, 2009.
[6] C. Zhang and G.S. Lee, “Text Line Segmentation in Chinese Handwritten Text Images”, 2011.
[7] R. Kumar and A. Singh, “Detection and Segmentation of Lines and Words in Gurmukhi Handwritten Text”, 2010.
[8] U. Pal and S. Datta, “Segmentation of Bangla unconstrained handwritten text”, 2003.
[9] N. Kumar Garg, L Kaur and M. K. Jindal “Segmentation of Handwritten Hindi Text”, 2010. [10] J. D. Gupta and B. Chanda, “A Model Based Text Line Segmentation Method for Off-line handwritten Document”, 2010.
[11] Mamatha H and Srikantamurthy K “Skew Detection, Correction and Segmentation of Handwritten Kannada Document”, 2012.
[12] J.Venkatesh and C. Sureshkumar “Tamil Handwritten Character Recognition Using Kohonon's Self Organizing Map”, 2009.
[13] Mamatha H R and Srikantamurthy K, “Morphological Operations and Projection Profiles based Segmentation of Handwritten Kannada Document”, 2012.
[14] Alireza Alaei, P. Nagabhushan and Umapada Pal “A New Dataset of Persian Handwritten Documents and its Segmentation”, 2011