Handwritten Sindhi Character Recognition using Neural Networks.

Shafique Ahmed Awan; ZAHID HUSSAIN ABRO; Akhtar Hussain Jalbani; Dil Nawaz Hakro; MARYAM HAMEED

Author(s)

Shafique Ahmed Awan Department of Information Technology, Quaid-e-Awam University of Engineering, Sciences & Technology, Nawabshah, Pakistan

ZAHID HUSSAIN ABRO Department of Information Technology, Quaid-e-Awam University of Engineering, Sciences & Technology, Nawabshah, Pakistan

Akhtar Hussain Jalbani Department of Information Technology, Quaid-e-Awam University of Engineering, Sciences & Technology, Nawabshah, Pakistan

Dil Nawaz Hakro Institute of Information & Communication Technology, University of Sindh, Jamshoro, Pakistan

MARYAM HAMEED Institute of Information & Communication Technology, University of Sindh, Jamshoro, Pakistan

Abstract

OCR (OpticalCharacter Recognition) is a technology in which text image is used to understand and write text by machines. The work on languages containing isolated characters such as German, English, French and others is at its peak. The OCR and ICR (Intelligent Character Recognition) research in Sindhi script is currently at in starting stages and not sufficient work have been cited in this area even though Sindhi language is rich in culture and history. This paper presents one of the initial steps in recognizing Sindhi handwritten characters. The isolated characters of Sindhi script written by thesubjects have been recognized. The various subjects were asked to write Sindhi characters in unconstrained form and then the written samples were collected and scanned through a flatbed scanner. The scanned documents were preprocessedwith the help of binary conversion, removing noise by pepper noise and the lines were segmented with the help of horizontal profile technique. The segmented lines were used to extract characters from scanned pages.This character segmentation was done by vertical projection. The extracted characters have been used to extract features so that the characters can be classified easily. Zoning was used for the feature extraction technique. For the classification, neural network has been used. The recognized characters converted into editable text with an average accuracy of 85%.

Publication Details

Page(s) 191-196

DOI DOI not available

Published Journal: Mehran University Research Journal of Engineering and Technology, Volume: 37, Issue: 1, Year: 2018

Request the full text from PASTIC

References

Hamid , A.,Haraty, 2001.A Neuro-Heuristice Approach for Segmenting Hand written Arabic Tex”,ACS/IEEE International Conference on Computer Systems and Applications 25 -26

Bhatti , Z.,Ismaili , I.A.,Hakro , D.N.,Waqas , A., 2014.“Unicode Based Bilingual Sindhi-English Pictorial Dictionary for Children”,American Journal of Software Engineering 2 1 -7

Bhatti , Z.,Waqas , A.,Ismaili , I.A.,Hakro , D.N.,Soomro, 2014.Phonetic Based SoundEx&ShapeEx Algorithm for Sindhi Spell Checker System”,arXiv Preprint arXiv 1405 -

Bhatti , Z.,Ismaili , I.A.,Soomro , W.J.,Hakro , D.N., 2014.Word Segmentation Model for Sindhi Text”,American Journal of Computing Research Repository 2 1 -7

Hakro , D.N.,Ismaili , I.A.,Tabalib , A.Z.,Mojai , G.N.,Jamshoro, 2014.Issues and Challenges in Sindhi OCR”, 46 -

Hakro , D.N.,Talib , Z.,Mojai , G.N., 2015.Multilingual Text Image Database for OCR”, 47 181 -186

Hakro , D.N.,Ismaili , I.A.,Talib , A.Z.,Bhatti , Z.,Mojai , G.N., 2014.“A Study of Sindhi Related and Arabic Script Adapted languages Recognition”, 46 323 -334

Assabie , Y.,Bigun, 2011.Offline Handwritten Amharic Word Recognition”,Pattern Recognition Letters 32 1089 -1099

Zaafouri , A.,Sayadi , M.,Fnaiech , F., 2012.Printed Arabic Character Recognition using Local Energy and Structural Features”,2nd International Conference on Communications, Computing and Control Applications 1 -5

Pal , U.,Sarkar , A., 2003.“Recognition of Printed Urdu Script”,Proceedings of 7th International Conference on Document Analysis and Recognition, Computer Society 1183 -1187

Hakro , D.N.,Talib , A.Z., 2016.Printed Text Image Database for Sindhi OCR”,ACM Transactions on Asian Low-Resource Language Information Process 15 1 -18

Dileep , D., 2012.A Feature Extraction Technique Based on Character Geometry for Character Recognition”,arXiv preprint arXiv 1202 -

Dileep, D., “A Feature Extraction Technique Based on Character Geometry for Character Recognition”, arXiv preprint arXiv, 1202.3884, 2012