Handwritten Sindhi Character Recognition Using Neural Networks

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%.

Authors and Affiliations

S. A. Awan, Z. H. Abro, A. H. Jalbani, D. N. Hakro, M. Hameed

Keywords

Related Articles

On The Design and Characteristics of a Sub-Optimal Observer for Boeing-747

LPV (Linear Parameter Varying) system is an important class of system, as it covers many physical systems. In the existing design theory related to control system, the major part is related to linear and non-linear syste...

Effective Image Segmentation using Composite Energy Metric in Levelset Based Curve Evolution

The linguistic corpus of Sindhi language is significant for computational linguistics process, machine learning process, language features identification and analysis, semantic and sentiment analysis, information retriev...

An Experimental Study on the Deterioration of Paint Coatings in the Bilges of a Sea Vessel

Scantling and rolling tolerances have gradually improved. The durability of anticorrosive property of coatings is the critical factor in safeguarding the capital investment locked up in the structure of the vessel. Under...

Development of Entrepreneurial and Marketing Capabilities in Engineering & Technology Based Firms

EM (Entrepreneurial Making) and MC (Marketing Capabilities) play a crucial role in the success of a firm. Many engineering and technology firms are run by people having an engineering degree which have less exposure to m...

Effect of Cryogenic Treatment on Mechanical Properties of AISI 4340 and AISI 4140 Steel

From last epoch till to date, AISI 4340 and AISI 4140 have been widely used in different engineering applications. These applications include bolt, screws, gears, drive shafts, crane shaft and piston rods for engines due...

Download PDF file
  • EP ID EP253066
  • DOI 10.22581/muet1982.1801.17
  • Views 115
  • Downloads 0

How To Cite

S. A. Awan, Z. H. Abro, A. H. Jalbani, D. N. Hakro, M. Hameed (2018). Handwritten Sindhi Character Recognition Using Neural Networks. Mehran University Research Journal of Engineering and Technology, 37(1), 191-196. https://europub.co.uk/articles/-A-253066