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

A Unified Bond Graph Modeling Approach for the Ejection Phase of the Cardiovascular System

In this paper the unified Bond Graph model of the left ventricle ejection phase is presented, simulated and validated. The integro-differential and ordinary differential equations obtained from the bond graph models are...

Design and Analysis of Hybrid Tree Multipliers for Reduction of Partial Products

This paper confers one of the three phases of tree multipliers, i.e. the Partial Product reduction phase. In this paper four types of hybrid tree multipliers are studied and proposed using parallel counters (full adders...

Lungs Cancer Detection Using Digital Image Processing Techniques: A Review

From last decade, lung cancer become sign of fear among the people all over the world. As a result, many countries generate funds and give invitation to many scholars to overcome on this disease. Many researchers propose...

Analysis of Caustic Soda of Different Manufacturers in Pakistan for Mercerization of Cotton Textiles

Pakistan has sufficient production capacity of caustic soda to cater the needs of the local industry. Presently, Pakistan has four major plants with production capacity around 435,000 mega ton per year of caustic soda of...

Urban Land Use Planning Trend and Sustainable Challenges in Socio-Economic Development

Land use planning is a technical approach for developing and managing the land into various public interests to endorse sustainable socio-economic development. This paper focuses on socio-economic problems by improper al...

Download PDF file
  • EP ID EP253066
  • DOI 10.22581/muet1982.1801.17
  • Views 110
  • 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