Bangla handwritten character recognition using convolutional neural network
Handwritten character recognition complexity varies among different languages due to distinct shapes, strokes and number of characters. Numerous works in handwritten character recognition are available for English with respect to other major languages such as Bangla. Existing methods use distinct fe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Modern Education and Computer Science (MECS) Press
2015
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/43592/ http://irep.iium.edu.my/43592/1/IJIGSP_BHCR_CNN_Pub_2015_8_52-59.pdf |
| _version_ | 1848782478089650176 |
|---|---|
| author | Rahman, Md. Mahbubar Akhand, Md. Aminul Haque Islam, Shahidul Shill, Pintu Chandra Rahman, M.M. Hafizur |
| author_facet | Rahman, Md. Mahbubar Akhand, Md. Aminul Haque Islam, Shahidul Shill, Pintu Chandra Rahman, M.M. Hafizur |
| author_sort | Rahman, Md. Mahbubar |
| building | IIUM Repository |
| collection | Online Access |
| description | Handwritten character recognition complexity varies among different languages due to distinct shapes, strokes and number of characters. Numerous works in handwritten character recognition are available for English with respect to other major languages such as Bangla. Existing methods use distinct feature extraction techniques and various classification tools in their recognition schemes. Recently, Convolutional Neural Network (CNN) is found efficient for English handwritten character recognition. In this paper, a CNN based Bangla handwritten character recognition is investigated. The proposed method normalizes the written character images and then employ CNN to classify individual characters. It does not employ any feature extraction method like other related works. 20000 handwritten characters with different shapes and variations are used in this study. The proposed method is shown satisfactory recognition accuracy and outperformed some other prominent exiting methods. |
| first_indexed | 2025-11-14T16:06:05Z |
| format | Article |
| id | iium-43592 |
| institution | International Islamic University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T16:06:05Z |
| publishDate | 2015 |
| publisher | Modern Education and Computer Science (MECS) Press |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | iium-435922017-11-09T09:19:47Z http://irep.iium.edu.my/43592/ Bangla handwritten character recognition using convolutional neural network Rahman, Md. Mahbubar Akhand, Md. Aminul Haque Islam, Shahidul Shill, Pintu Chandra Rahman, M.M. Hafizur TK Electrical engineering. Electronics Nuclear engineering Handwritten character recognition complexity varies among different languages due to distinct shapes, strokes and number of characters. Numerous works in handwritten character recognition are available for English with respect to other major languages such as Bangla. Existing methods use distinct feature extraction techniques and various classification tools in their recognition schemes. Recently, Convolutional Neural Network (CNN) is found efficient for English handwritten character recognition. In this paper, a CNN based Bangla handwritten character recognition is investigated. The proposed method normalizes the written character images and then employ CNN to classify individual characters. It does not employ any feature extraction method like other related works. 20000 handwritten characters with different shapes and variations are used in this study. The proposed method is shown satisfactory recognition accuracy and outperformed some other prominent exiting methods. Modern Education and Computer Science (MECS) Press 2015-07 Article PeerReviewed application/pdf en http://irep.iium.edu.my/43592/1/IJIGSP_BHCR_CNN_Pub_2015_8_52-59.pdf Rahman, Md. Mahbubar and Akhand, Md. Aminul Haque and Islam, Shahidul and Shill, Pintu Chandra and Rahman, M.M. Hafizur (2015) Bangla handwritten character recognition using convolutional neural network. International Journal of Image, Graphics and Signal Processing, 7 (8). pp. 52-59. ISSN 2074-9082 (O), 2074-9074(P) http://www.mecs-press.org/ijigsp/ijigsp-v7-n8/IJIGSP-V7-N8-5.pdf 10.5815/ijigsp.2015.08.06 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Rahman, Md. Mahbubar Akhand, Md. Aminul Haque Islam, Shahidul Shill, Pintu Chandra Rahman, M.M. Hafizur Bangla handwritten character recognition using convolutional neural network |
| title | Bangla handwritten character recognition using convolutional neural network |
| title_full | Bangla handwritten character recognition using convolutional neural network |
| title_fullStr | Bangla handwritten character recognition using convolutional neural network |
| title_full_unstemmed | Bangla handwritten character recognition using convolutional neural network |
| title_short | Bangla handwritten character recognition using convolutional neural network |
| title_sort | bangla handwritten character recognition using convolutional neural network |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://irep.iium.edu.my/43592/ http://irep.iium.edu.my/43592/ http://irep.iium.edu.my/43592/ http://irep.iium.edu.my/43592/1/IJIGSP_BHCR_CNN_Pub_2015_8_52-59.pdf |