Unconstrained handwritten character recognition based on fuzzy logic
This paper presents an innovative approach called box method for feature extraction for the recognition of handwritten characters. In this method, the binary image of the character is partitioned into a fixed number of subimages called boxes. The features consist of vector distance (gamma) from each...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
2003
|
| Subjects: | |
| Online Access: | http://shdl.mmu.edu.my/2579/ http://shdl.mmu.edu.my/2579/1/1839.pdf |
| _version_ | 1848790093331955712 |
|---|---|
| author | Hanmandlu, M |
| author_facet | Hanmandlu, M |
| author_sort | Hanmandlu, M |
| building | MMU Institutional Repository |
| collection | Online Access |
| description | This paper presents an innovative approach called box method for feature extraction for the recognition of handwritten characters. In this method, the binary image of the character is partitioned into a fixed number of subimages called boxes. The features consist of vector distance (gamma) from each box to a fixed point. To find gamma the vector distances of all the pixels, lying in a particular box, from the fixed point are calculated and added up and normalized by the number of pixels within that box. Here, both neural networks and fuzzy logic techniques are used for recognition and recognition rates are found to be around 97 percent using neural networks and 98 percent using fuzzy logic. The methods are independent of font, size and with minor changes in preprocessing, it can be adopted for any language. (C) 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved. |
| first_indexed | 2025-11-14T18:07:08Z |
| format | Article |
| id | mmu-2579 |
| institution | Multimedia University |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T18:07:08Z |
| publishDate | 2003 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | mmu-25792014-02-06T03:45:19Z http://shdl.mmu.edu.my/2579/ Unconstrained handwritten character recognition based on fuzzy logic Hanmandlu, M QA75.5-76.95 Electronic computers. Computer science This paper presents an innovative approach called box method for feature extraction for the recognition of handwritten characters. In this method, the binary image of the character is partitioned into a fixed number of subimages called boxes. The features consist of vector distance (gamma) from each box to a fixed point. To find gamma the vector distances of all the pixels, lying in a particular box, from the fixed point are calculated and added up and normalized by the number of pixels within that box. Here, both neural networks and fuzzy logic techniques are used for recognition and recognition rates are found to be around 97 percent using neural networks and 98 percent using fuzzy logic. The methods are independent of font, size and with minor changes in preprocessing, it can be adopted for any language. (C) 2002 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved. 2003-03 Article NonPeerReviewed text en http://shdl.mmu.edu.my/2579/1/1839.pdf Hanmandlu, M (2003) Unconstrained handwritten character recognition based on fuzzy logic. Pattern Recognition, 36 (3). pp. 603-623. ISSN 00313203 http://dx.doi.org/10.1016/S0031-3203(02)00069-9 doi:10.1016/S0031-3203(02)00069-9 doi:10.1016/S0031-3203(02)00069-9 |
| spellingShingle | QA75.5-76.95 Electronic computers. Computer science Hanmandlu, M Unconstrained handwritten character recognition based on fuzzy logic |
| title | Unconstrained handwritten character recognition based on fuzzy logic |
| title_full | Unconstrained handwritten character recognition based on fuzzy logic |
| title_fullStr | Unconstrained handwritten character recognition based on fuzzy logic |
| title_full_unstemmed | Unconstrained handwritten character recognition based on fuzzy logic |
| title_short | Unconstrained handwritten character recognition based on fuzzy logic |
| title_sort | unconstrained handwritten character recognition based on fuzzy logic |
| topic | QA75.5-76.95 Electronic computers. Computer science |
| url | http://shdl.mmu.edu.my/2579/ http://shdl.mmu.edu.my/2579/ http://shdl.mmu.edu.my/2579/ http://shdl.mmu.edu.my/2579/1/1839.pdf |