التعرف الآلي على الأحرف العربية باستخراج سماتها البنيوية
Abstract
يقدم هذا البحث مساهمة جديدة في عملية تطوير خوارزمية فَعّالة تُحقق التعرف على الأحرف العربية لمعالجة صور المستندات النصية باستخدام الشبكات العصبونية التي أثبتت جدواها في حل العديد من المسائل المشابهة, وقد تضمن البحث العديد من الأفكار الجديدة، والخوارزميات, لمواجهة وحل التعقيد البالغ في النصوص العربية كما تم في سياق العمل تقديم دراسة مرجعية حول طرائق التعرف على الأنماط، والخوارزميات المستخدمة للتعرف على الكتابة باللغة العربية، بالإضافة إلى الاهتمام بعلم معالجة الصور مع التركيز على الشبكات العصبونية وخاصة شبكات هامينغ .
اعتُمدَت طريقة استخراج السمات البنيوية للحرف المراد التعرف عليه في عملية التصنيف.
تم التوصل في نهاية البحث إلى مجموعة من النتائج والاستنتاجات، بالإضافة إلى مقارنة أنواع مختلفة من الخطوط، وبأحجام متباينة، حيث كانت نسبة التعرف مرتفعة في أغلب الحالات، بينما انخفضت بشكل بسيط عند زيادة نسبة الضجيج, كما حُددت الحالات الخاصة الواجب التعامل معها أثناء التعرف على الأحرف العربية، وذلك ليتسنى أخذها بعين الاعتبار عند تقديم خوارزميات تعرف جديدة.
This research presents new effective contribution of developing the algorithm of identifying and recognizing Arabic letters in the text document by using neural network which proved its strong ability in solving many similar issues. This research includes also many new ideas and algorithms to solve the extreme complexity of Arabic texts, and in the sequence of work an authoritative study has been set about the methods of identifying modes and algorithms of Arabic language. In addition, the study took care of images processing technology and concentrated on the neural networks (Hamming Networks) specifically.
Extracting the structural features of the letter (which wanted for recognition)has been adopted during the classification process).
At the end of this study a band of conclusions and results has been reached, as well as, the comparison between different kinds of fonts and different sizes of letters. Mostly, a high ratio of successful identification could be reached, the ratio has slightly decreased in the case of high noise. Special cases of recognition of Arabic letters have been classified to be taken into consideration during the introduction of the new algorithms.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2016 ttps://creativecommons.org/licenses/by-nc-sa/4.0/
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
The authors retain the copyright and grant the right to publish in the magazine for the first time with the transfer of the commercial right to Tishreen University Journal for Research and Scientific Studies - Engineering Sciences Series
Under a CC BY- NC-SA 04 license that allows others to share the work with of the work's authorship and initial publication in this journal. Authors can use a copy of their articles in their scientific activity, and on their scientific websites, provided that the place of publication is indicted in Tishreen University Journal for Research and Scientific Studies - Engineering Sciences Series . The Readers have the right to send, print and subscribe to the initial version of the article, and the title of Tishreen University Journal for Research and Scientific Studies - Engineering Sciences Series Publisher
journal uses a CC BY-NC-SA license which mean
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material
- The licensor cannot revoke these freedoms as long as you follow the license terms.
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- NonCommercial — You may not use the material for commercial purposes.
- ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.