Character Recognition of Arabic Handwritten Characters Using Deep Learning
Optical character recognition (OCR) is used to digitize texts in printed documents and camera images. The most basic step in the OCR process is character recognition. The Arabic language is more complex than other alphabets, as the cursive is written in cursive and the characters have different spel...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Engiscience Publisher
2022-03-01
|
| Series: | Journal of Studies in Science and Engineering |
| Subjects: | |
| Online Access: | https://engiscience.com/index.php/josse/article/view/24 |
| _version_ | 1827956431351971840 |
|---|---|
| author | Mohammed Widad Jbrail Mehmet Emin Tenekeci |
| author_facet | Mohammed Widad Jbrail Mehmet Emin Tenekeci |
| author_sort | Mohammed Widad Jbrail |
| collection | DOAJ |
| description | Optical character recognition (OCR) is used to digitize texts in printed documents and camera images. The most basic step in the OCR process is character recognition. The Arabic language is more complex than other alphabets, as the cursive is written in cursive and the characters have different spellings. Our research has improved a character recognition model for Arabic texts with 28 different characters. Character recognition was performed using Convolutional Neural Network models, which are accepted as effective in image processing and recognition. Three different CNN models have been proposed. In the study, training and testing of the models were carried out using the Hijja data set. Among the proposed models, Model C with a 99.3% accuracy rate has obtained results that can compete with the studies in the literature. |
| first_indexed | 2024-04-09T15:04:18Z |
| format | Article |
| id | doaj.art-accae398b5d04ddb815711f31cee616a |
| institution | Directory Open Access Journal |
| issn | 2789-634X |
| language | English |
| last_indexed | 2024-04-09T15:04:18Z |
| publishDate | 2022-03-01 |
| publisher | Engiscience Publisher |
| record_format | Article |
| series | Journal of Studies in Science and Engineering |
| spelling | doaj.art-accae398b5d04ddb815711f31cee616a2023-04-30T22:09:47ZengEngiscience PublisherJournal of Studies in Science and Engineering2789-634X2022-03-0121324010.53898/josse202221324Character Recognition of Arabic Handwritten Characters Using Deep LearningMohammed Widad Jbrail0https://orcid.org/0000-0002-8745-4296Mehmet Emin Tenekeci1https://orcid.org/0000-0002-8745-4296Department of Computer Engineering, Faculty of Engineering, Harran University, 63050 Şanlıurfa, TurkeyDepartment of Computer Engineering, Faculty of Engineering, Harran University, 63050 Şanlıurfa, TurkeyOptical character recognition (OCR) is used to digitize texts in printed documents and camera images. The most basic step in the OCR process is character recognition. The Arabic language is more complex than other alphabets, as the cursive is written in cursive and the characters have different spellings. Our research has improved a character recognition model for Arabic texts with 28 different characters. Character recognition was performed using Convolutional Neural Network models, which are accepted as effective in image processing and recognition. Three different CNN models have been proposed. In the study, training and testing of the models were carried out using the Hijja data set. Among the proposed models, Model C with a 99.3% accuracy rate has obtained results that can compete with the studies in the literature.https://engiscience.com/index.php/josse/article/view/24ocrarabic character recognition hijja dataset convolutional neural networkdeep learning |
| spellingShingle | Mohammed Widad Jbrail Mehmet Emin Tenekeci Character Recognition of Arabic Handwritten Characters Using Deep Learning Journal of Studies in Science and Engineering ocr arabic character recognition hijja dataset convolutional neural network deep learning |
| title | Character Recognition of Arabic Handwritten Characters Using Deep Learning |
| title_full | Character Recognition of Arabic Handwritten Characters Using Deep Learning |
| title_fullStr | Character Recognition of Arabic Handwritten Characters Using Deep Learning |
| title_full_unstemmed | Character Recognition of Arabic Handwritten Characters Using Deep Learning |
| title_short | Character Recognition of Arabic Handwritten Characters Using Deep Learning |
| title_sort | character recognition of arabic handwritten characters using deep learning |
| topic | ocr arabic character recognition hijja dataset convolutional neural network deep learning |
| url | https://engiscience.com/index.php/josse/article/view/24 |
| work_keys_str_mv | AT mohammedwidadjbrail characterrecognitionofarabichandwrittencharactersusingdeeplearning AT mehmetemintenekeci characterrecognitionofarabichandwrittencharactersusingdeeplearning |