Character Segmentation and Skew Correction for Handwritten Devanagari Scripts: A Friends Technique

Back to Journal

Home»Articles»Character Segmentation and Skew Correction for Handwritten Devanagari Scripts: A Friends Technique

Character Segmentation and Skew Correction for Handwritten Devanagari Scripts: A Friends Technique

Author : Ashok Kumar Bathla, Sunil Kumar Gupta and Manish Kumar Jindal
Volume 8 No.1 January-March 2019 pp 50-54

Abstract

Optical Character Recognition (OCR) technology allows a computer to “read” text (both typed and handwritten) the way a human brain does.Significant research efforts have been put in the area of Optical Character Segmentation (OCR) of typewritten text in various languages, however very few efforts have been put on the segmentation and skew correction of handwritten text written in Devanagari which is a scripting language of Hindi. This paper aims a novel technique for segmentation and skew correction of hand written Devanagari text. It shows the accuracy of 91% and takes less than one second to segment a particular handwritten word.

Keywords

Segmentation, Compound Character, Devanagari

Full Text:

References

[1] K. Jindal, and R. Kumar, “A new method for segmentation of pre-detected Devanagari words from the scene images: Pihu method”, Computers and Electrical Engineering, 2017.
[2] G. Mandal, “An Unprecedented Approach of Skew Detection and Correction for Online Bengali Handwritten Words”, IJARCET, Vol. 7, No. 2, Feb 2018.
[3] D. V Sharma and G. S, Lehal, “An Iterative Algorithm for Segmentation of Isolated Handwritten Words in Gurmukhi Script”, IEEE International Conference ON Pattern Recognition, Vol. 2, pp. 1022-1025, 2006.
[4] M. Kumar, M. K. Jindal and R. K. Sharma, “Segmentation of Isolated and Touching Characters in Offline Handwritten Gurmukhi Script Recognition”, International Journal of Information Technology and Computer Science, Vol. 6, No. 2, pp. 58-63, 2014.
[5] P. Mangla and H. Kaur, “An End Detection Algorithm for segmentation of Broken and Touching characters in Handwritten Gurmukhi Word”, IEEE International Conference on Reliability, Infocom Technologies and Optimization, pp. 1-4, 2014.
[6] B. Thakral and M. Kumar, “Devanagari Handwritten Text Segmentation for Overlapping and Conjunct Characters: A Proficient Technique”, IEEE International Conference on Reliability, Infocom Technologies and Optimization, pp. 1-4, 2014.
[7] P. Mangla. And H. Kaur, “An End Detection Algorithm for segmentation of Broken and Touching characters in Handwritten Gurmukhi Word”, Institute of Electrical and Electronics Engineers (IEEE), pp. 1-4, 2014.
[8] V. Bansal and R. M. K. Sinha, “Segmentation of touching in Devanagari characters”, Proceeding, CVGIP, Delhi, 1998.
[9] G. S. Lehal and C. Singh, “A technique for segmentation of Gurmukhi text”, Computer Analysis of image and patterns, Vol. 21, No. 24, Springer, pp. 191-200, 2001

[10] A. K. Bathla., S.K.Gupta, and M.K. Jindal, “Identification and Recognition of Handwritten Devanagari text Using Machine Learning Classifiers “, IJMDEBM, Vol. 6, No. 2, pp. 21-25, April-June 2018.

[11] M. K. Sachan, G. S. Lehaland V. K. Jain, “A Novel Method to Segment Online Gurmukhi Script”, Information Systems for Indian Languages. ICISIL 2011. Communications in Computer and Information Science, Springer, Vol. 13, No. 9, Berlin, Heidelberg, 2011
[12] U. Garain and B. B. Chaudhuri, “Segmentation of touching characters in printed devanagari and bangla scripts using fuzzy multifactorial analysis”, IEEE Systems, Man, and Cybernetics Society, Vol. 32, No. 4, pp. 449-459, 2002.
[13] S. Bag, and G. Harit, “A survey on optical character recognition for Bangla and Devanagariscripts”,Sadhana, Vol. 38, No.1, pp. 133-168, 2013
[14] U. Bhattacharya, S. K. Parui, and S. Mondal, “Devanagari and Bangla text extraction from natural scene images”, In: IEEE international conference on document analysis and recognition (ICDAR), pp. 171-175, 2009.
[15] R. Jayadevan, S. R. Kolhe, P. M. Patil, and U. Pal, “Offline recognition of Devanagari script- a survey”, IEEE Trans Sys Man Cybern Part C Appl Rev, Vol. 41, No.6, pp. 782-796, 2011
[16] H.Ma,and D.Doermann, “Adaptive Hindi OCR using generalized Hausdorff image comparison”, ACM Trans Asian Lang Inf Process, Vol. 2, No. 3, pp. 193-218, 2003
[17] OVR. Murthy, S. Roy, V. Narang, M. Hanmandlu and S. Gupta , “An approach to divide pre-detected Devanagari words from the scene images into characters”, Signal Image Video Process Vol. 7, No. 6, pp. 1071-1082, 2013
[18] V. Narang, S. Roy, OVR. Murthy, and M. Hanmandlu, “Devanagari character recognition in scene images”, In IEEE international conference on document analysis and recognition (ICDAR), pp. 902-906, 2013.

Asian Journal of Engineering and Applied Technology is a peer-reviewed International research journal aiming at promoting and publishing original high quality research in all disciplines of engineering and applied technology. All research articles submitted to AJEAT should be original in nature, never previously published in any journal or presented in a conference or undergoing such process across the world. All the submissions will be peer-reviewed by the panel of experts associated with particular field. Submitted papers should meet the internationally accepted criteria and manuscripts should follow the style of the journal for the purpose of both reviewing and editing.

AJEAT is covering all aspects of Engineering and Applied Technology areas. Topics include, but are not limited to:

Aerospace engineering Agricultural engineering Architectural engineering Bioengineering and biomedical engineering Chemical engineering Civil engineering Computer engineering Computer science and information science Electrical engineering and electronics engineering Environmental engineering	Industrial engineering Metallurgical engineering Ceramic engineering Materials science Metallurgy Mechanical engineering Nuclear engineering Petroleum engineering Plastics engineering and polymer science Textile & Fashion Technology