- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
An Efficient Preprocessing Framework for Arabic Handwriting Recognition System | ||
| Diyala Journal For Pure Science | ||
| Article 1, Volume 12, Issue 3, 2016, Pages 147-163 | ||
| Authors | ||
| Alia Karim Abdul Hassan; Mustafa S. Kadhm | ||
| Abstract | ||
| Image preprocessing has assumed an essential part in Arabic Handwriting Recognition System (AHRS). It has several stages which affect the accuracy of the recognition system. An efficient preprocessing framework for Arabic handwriting recognition system has been proposed in this paper. Since preprocessing stage in AHRS is imperative to reduce the dimensionality of image to remove the undesirable information then increase the processing speed of the AHRS. Besides, it provide correction process for the dataset elements to make it work probably through several processes that will discuss in this paper. Exploratory results with artificial and real life images shows that, the proposed method gives an efficient results that help to get a high recognition rate in the AHRS. | ||
| Keywords | ||
| Preprocessing; AHRS; Arabic text; Thresholding; thinning; Normalization | ||
|
Statistics Article View: 172 PDF Download: 123 |
||