A Multiple Classifiers System For Solving The Character Recognition Problem In Arabic Alphabet

Document Type

Conference Proceeding

Publication Date

2006

Abstract

Handwriting is a skill that is personal to individuals. Fundamental characteristics of handwriting are three fold. It consists of artificial graphical marks on a surface; its purpose is to communicate something [1]. It has continued to persist as a means of communication and recording information in day-to-day life due to the convenience of paper and pen as compared to keyboards for numerous day-to-daysituations. There are many classification techniques available for handwriting recognition systems. All of them have their own advantages and drawbacks. In recent years, many researchers have combined such techniques in order to improve the recognition results. The idea does not rely on a single decision-making scheme.Various classifier combination schemes have been devised and it has been experimentally demonstrated that some of them consistently outperform a single best classifier. For character recognition, combining classifiers based on different techniques of pre-processing, feature extraction, and classifier models is effective. In this paper we proposed a multiple-classifier system for handwritten Arabic alphabet recognition, which has achieved an increase of about 27% in the recognition accuracy compared to a single-classifier system.

Link to Full Text

Share

COinS