Mosul University
  • Register
  • Login
  • العربیة

AL-Rafidain Journal of Computer Sciences and Mathematics

Notice

As part of Open Journals’ initiatives, we create website for scholarly open access journals. If you are responsible for this journal and would like to know more about how to use the editorial system, please visit our website at https://ejournalplus.com or
send us an email to info@ejournalplus.com

We will contact you soon

  1. Home
  2. Volume 3, Issue 1
  3. Authors

Current Issue

By Issue

By Subject

Keyword Index

Author Index

Indexing Databases XML

About Journal

Aims and Scope

Editorial Board

Editorial Staff

Publication Ethics

Indexing and Abstracting

Related Links

Peer Review Process

News

Software for Arabic Machine Printed Optical Character Recognition (MACRS)

    Mahdi F. Al- Obaidi Laheeb Mohammad Ibrahim

AL-Rafidain Journal of Computer Sciences and Mathematics, 2006, Volume 3, Issue 1, Pages 23-41
10.33899/csmj.2006.164033

  • Show Article
  • Download
  • Cite
  • Statistics
  • Share

Abstract

Machine printed Arabic Character Recognition System (MACRS] is concerned with recognition of machine printed alphanumeric Arabic characters. In the present work, characters have been represented (extracted) by using geometric moment invariant (3 order). The technique used in this research can be divided into three major steps. The first step is digitization and preprocessing to create connected component, detect the skew of a character image and correct it. The second is feature extraction, where geometric moment invariant features of the input, Arabic character is used to extract features. Finally, we describe an advanced system of classification using probabilistic neural networks structure which yields significant speed improvements. MACRS is tested using 2961 patterns for a total 141 classes with roughly 21 patterns in each class. It is important to note here that the system performs extremely well with recognition rates ranging between 84% and 88% on different folds and the overall recognition is 85.8%. This is a very good performance taking into account the fact that we have a limited number of samples in each class and that, the recognition on the training data is also extremely high (99.8%) which represents a very good training.
 
Keywords:
    Machine printed Arabic Character Recognition System (MACRS] probabilistic neural networks
  • PDF (542 K)
  • XML
(2006). Software for Arabic Machine Printed Optical Character Recognition (MACRS). AL-Rafidain Journal of Computer Sciences and Mathematics, 3(1), 23-41. doi: 10.33899/csmj.2006.164033
Mahdi F. Al- Obaidi; Laheeb Mohammad Ibrahim. "Software for Arabic Machine Printed Optical Character Recognition (MACRS)". AL-Rafidain Journal of Computer Sciences and Mathematics, 3, 1, 2006, 23-41. doi: 10.33899/csmj.2006.164033
(2006). 'Software for Arabic Machine Printed Optical Character Recognition (MACRS)', AL-Rafidain Journal of Computer Sciences and Mathematics, 3(1), pp. 23-41. doi: 10.33899/csmj.2006.164033
Software for Arabic Machine Printed Optical Character Recognition (MACRS). AL-Rafidain Journal of Computer Sciences and Mathematics, 2006; 3(1): 23-41. doi: 10.33899/csmj.2006.164033
  • RIS
  • EndNote
  • BibTeX
  • APA
  • MLA
  • Harvard
  • Vancouver
  • Article View: 99
  • PDF Download: 124
  • LinkedIn
  • Twitter
  • Facebook
  • Google
  • Telegram
  • Home
  • Glossary
  • News
  • Aims and Scope
  • Privacy Policy
  • Sitemap
This journal is licensed under a Creative Commons Attribution 4.0 International (CC-BY 4.0)

Powered by eJournalPlus