文章基本信息

标题：On Arabic Character Recognition Employing Hybrid Neural Network
本地全文：下载
作者：Al-Amin Bhuiyan ; Fawaz Waselallah Alsaade
期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2017
卷号：8
期号：6
DOI：10.14569/IJACSA.2017.080612
出版社：Science and Information Society (SAI)
摘要：Arabic characters illustrate intricate, multidimensional and cursive visual information. Developing a machine learning system for Arabic character recognition is an exciting research. This paper addresses a neural computing concept for Arabic Optical Character Recognition (OCR). The method is based on local image sampling of each character to a selected feature matrix and feeding these matrices into a Bidirectional Associative Memory followed by Multilayer Perceptron (BAMMLP) with back propagation learning algorithm. The efficacy of the system has been justified over different test patterns of Arabic characters. Experimental results validate that the system is well efficient to recognize Arabic characters with overall more than 82% accuracy.
关键词：Arabic characters; Arabic OCR; image histogram; BAMMLP; hybrid neural network