A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition
An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay lang...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2015
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/43600/ http://psasir.upm.edu.my/id/eprint/43600/1/A%20scalable%20hybrid%20decision%20system%20%28HDS%29%20for%20Roman%20word%20recognition%20using%20ANN%20SVM%20Study%20case%20on%20Malay%20word%20recognition.pdf |
| _version_ | 1848850271334039552 |
|---|---|
| author | Al-Boeridi, Omar N. Syed Ahmad Abdul Rahman, Sharifah Mumtazah Koh, S. P. |
| author_facet | Al-Boeridi, Omar N. Syed Ahmad Abdul Rahman, Sharifah Mumtazah Koh, S. P. |
| author_sort | Al-Boeridi, Omar N. |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications. |
| first_indexed | 2025-11-15T10:03:38Z |
| format | Article |
| id | upm-43600 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T10:03:38Z |
| publishDate | 2015 |
| publisher | Springer |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-436002016-07-21T09:41:49Z http://psasir.upm.edu.my/id/eprint/43600/ A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition Al-Boeridi, Omar N. Syed Ahmad Abdul Rahman, Sharifah Mumtazah Koh, S. P. An off-line handwriting recognition (OFHR) system is a computerized system that is capable of intelligently converting human handwritten data extracted from scanned paper documents into an equivalent text format. This paper studies a proposed OFHR for Malaysian bank cheques written in the Malay language. The proposed system comprised of three components, namely a character recognition system (CRS), a hybrid decision system and lexical word classification system. Two types of feature extraction techniques have been used in the system, namely statistical and geometrical. Experiments show that the statistical feature is reliable, accessible and offers results that are more accurate. The CRS in this system was implemented using two individual classifiers, namely an adaptive multilayer feed-forward back-propagation neural network and support vector machine. The results of this study are very promising and could generalize to the entire Malay lexical dictionary in future work toward scaled-up applications. Springer 2015 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/43600/1/A%20scalable%20hybrid%20decision%20system%20%28HDS%29%20for%20Roman%20word%20recognition%20using%20ANN%20SVM%20Study%20case%20on%20Malay%20word%20recognition.pdf Al-Boeridi, Omar N. and Syed Ahmad Abdul Rahman, Sharifah Mumtazah and Koh, S. P. (2015) A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition. Neural Computing & Applications, 26 (6). pp. 1505-1513. ISSN 0941-0643; ESSN: 1433-3058 http://fcb991b696f563270c39464d67d2c3bd.proxysheep.com/article/10.1007/s00521-015-1824-0 10.1007/s00521-015-1824-0 |
| spellingShingle | Al-Boeridi, Omar N. Syed Ahmad Abdul Rahman, Sharifah Mumtazah Koh, S. P. A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition |
| title | A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition |
| title_full | A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition |
| title_fullStr | A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition |
| title_full_unstemmed | A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition |
| title_short | A scalable hybrid decision system (HDS) for Roman word recognition using ANN SVM: Study case on Malay word recognition |
| title_sort | scalable hybrid decision system (hds) for roman word recognition using ann svm: study case on malay word recognition |
| url | http://psasir.upm.edu.my/id/eprint/43600/ http://psasir.upm.edu.my/id/eprint/43600/ http://psasir.upm.edu.my/id/eprint/43600/ http://psasir.upm.edu.my/id/eprint/43600/1/A%20scalable%20hybrid%20decision%20system%20%28HDS%29%20for%20Roman%20word%20recognition%20using%20ANN%20SVM%20Study%20case%20on%20Malay%20word%20recognition.pdf |