National Journal of System and Information Technology

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Horizontal and Vertical Projection Techniques for Line & Word Segmentation Process in Offline Handwritten Gujarati Text


Affiliations
1 Marwadi Education Foundation Group of Institutions, Rajkot, India
2 Dept. of Computer Science, Bhavnagar University, India
     

   Subscribe/Renew Journal


This research paper describes two important techniques Horizontal&Vertical Projection for character segmentation process in Offline Handwritten Gujarati Text Recognition process (OHGTR). Segmentation is one of the key steps in Text Recognition process which is one of the factors in recognition accuracy. This research paper mainly focuses on segmentation techniques: Horizontal&Vertical projection. Recognition process is required to perform many preprocessing and post processing steps to recognize the character. If segmentation of scan documentation is properly happen then rest of the process will become easy otherwise it will reflect on final recognition process. It is easy to segment printed character scan document as compare to hand written document because of the same font size and style where in hand written text document is , the content character size is different, even the same document is written by the same person.

Keywords

OHGTR, Pre Processing, Post Processing, Horizontal & Vertical Projection, Offline Hand Written Text Recognition (OHGTR).
Subscription Login to verify subscription
User
Notifications
Font Size


  • Handwritten Gurumukhi Character Recognition Using Neural Networks, Naveen Garg, Computer Science And Engineering Epartment, Thapar University, Patiala

  • Gujarati Script Recognition: A Review By : Mamta Maloo, Dr.K.V.Kale, IJCSI International Journal of Computer Science Issues, Vol. 8, Issue 4, No 1, July 2011, ISSN (Online): 1694-0814

  • Handwritten Character Recognition System Using Artificial Neural Networks, Pelin GORGEL Oguzhan O, ZTAS, Journal Of Electrical & Electronics Engineering

  • Efficiency zone based feature extraction algorithm for handwritten numeral recognition of four popular south-Indian scripts”, S. V. Rajashekararadhya, and P. Vanajaranjan, Journal of Theoretical and Applied Information Technology, JATIT, vol. 4, no. 12, pp. 1171-1181,2008.

  • “Devanagiri document segmentation using histogram approach”,Vigas J Dongre and Vijay H Mankar,International Journal of Computer Science, Engineering and Information Technology,2011

  • Gujarati Character Identification: A Survey, Mitul Modi, Fedrik Macwan, Ravindra Prajapati, International Journal Of Innovative Research In Electrical, Electronics, Instrumentation And Control Engineering, Vol. 2, Issue 2, February 2014

  • Segmentation of Offline Malayalam Handwritten Character Recognition, Sangeetha Sasidharan & Anjitha Mary Paul, IJARCSSE, Volume 3, Issue 11, November 2013

  • “Gujarati handwritten numeral optical character reorganization through neural network”, A. Desai, , Pattern Recognition Vol 43 2010 pp. 2582-2589

  • Off-Line Cursive Handwriting Recognition Using NNs, A. W. Senior, 1994, University of Cambridge, England

  • A System for Off-Line Oriya Handwritten Character Recognition Using Curvature Feature, Wakabayashi, T. Kimura, Information Technology, (ICIT 2007). 10th International Conference , 2007 IEEE.

  • Extraction of Characters and Modifiers from Hand written Gujarati Words, Chhaya Patel, Apurva Desai, International Journal of Computer Applications, Volume 73– No.3, July 2013

  • Kannada , Telugu and Devanagari Handwritten Numeral Recognition with Probabilistic Neural Network : A Novel Approach, B. V. Dhandra, R.G.Benne, M. Hangarge, Recent Trends in Image Processing and Pattern Recognition, pp. 83-88, 2010

  • Character Recognition of Gujarati and Devanagari Script : A Review, S. S. Magare,Y. K. Gedam,D. S. Randhave,Prof. R. R. Deshmukh, International Journal of Engineering Research & Technology (IJERT),Vol. 3 Issue 1, January – 2014

  • Offline Handwritten Devanagari Script Recognition, Ved Prakash Agnihotri, I.J. Information Technology and Computer Science, 2012, 8, 37-42, Published Online July 2012 in MECS

  • Off-Line Cursive Handwritten Tamil Character Recognition, R. J. Kannan, R. Prabhakar, 2008, Signal Processing, vol. 4, no. 6, pp. 351-360.


Abstract Views: 391

PDF Views: 3




  • Horizontal and Vertical Projection Techniques for Line & Word Segmentation Process in Offline Handwritten Gujarati Text

Abstract Views: 391  |  PDF Views: 3

Authors

Ashwin R. Dobariya
Marwadi Education Foundation Group of Institutions, Rajkot, India
V. R. Rathod
Dept. of Computer Science, Bhavnagar University, India

Abstract


This research paper describes two important techniques Horizontal&Vertical Projection for character segmentation process in Offline Handwritten Gujarati Text Recognition process (OHGTR). Segmentation is one of the key steps in Text Recognition process which is one of the factors in recognition accuracy. This research paper mainly focuses on segmentation techniques: Horizontal&Vertical projection. Recognition process is required to perform many preprocessing and post processing steps to recognize the character. If segmentation of scan documentation is properly happen then rest of the process will become easy otherwise it will reflect on final recognition process. It is easy to segment printed character scan document as compare to hand written document because of the same font size and style where in hand written text document is , the content character size is different, even the same document is written by the same person.

Keywords


OHGTR, Pre Processing, Post Processing, Horizontal & Vertical Projection, Offline Hand Written Text Recognition (OHGTR).

References