Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study
Handwriting processing is a domain in great expansion which in the present day begins to see several industrial realizations. The field of personal computing has begun to make a transition from the desktop to handheld devices, thereby requiring input paradigms that are more suited for single hand en...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2006
|
| Online Access: | http://eprints.utm.my/8745/ http://eprints.utm.my/8745/1/ICEIS-2006.pdf |
| _version_ | 1848891758214119424 |
|---|---|
| author | Zafar, Muhammad Faisal Mohamad, Dzulkifli Othman, Muhamad Razib |
| author_facet | Zafar, Muhammad Faisal Mohamad, Dzulkifli Othman, Muhamad Razib |
| author_sort | Zafar, Muhammad Faisal |
| building | UTeM Institutional Repository |
| collection | Online Access |
| description | Handwriting processing is a domain in great expansion which in the present day begins to see several industrial realizations. The field of personal computing has begun to make a transition from the desktop to handheld devices, thereby requiring input paradigms that are more suited for single hand entry than a keyboard. Online handwriting recognition allows for such input modalities. Handwriting recognition has always been a tough problem because of the handwriting variability, ambiguity and illegibility. This paper describes a simple approach involved in online handwriting recognition. Conventionally, the data obtained needs a lot of preprocessing including filtering, smoothing, slant removing and size normalization before recognition process. Instead of doing such lengthy preprocessing, this paper presents a simple approach to extract the useful character information. The whole process requires no preprocessing and size normalization. The method is applicable for off-line character recognition as well. This is a writer-independent system based on two neural net (NN) techniques: back propagation neural network (BPN) and counter propagation neural network (CPN). Performances of BPN and CPN are tested for upper-case English alphabets for a number of different styles from different peoples. |
| first_indexed | 2025-11-15T21:03:03Z |
| format | Conference or Workshop Item |
| id | utm-8745 |
| institution | Universiti Teknologi Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T21:03:03Z |
| publishDate | 2006 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utm-87452017-08-30T04:26:55Z http://eprints.utm.my/8745/ Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study Zafar, Muhammad Faisal Mohamad, Dzulkifli Othman, Muhamad Razib Handwriting processing is a domain in great expansion which in the present day begins to see several industrial realizations. The field of personal computing has begun to make a transition from the desktop to handheld devices, thereby requiring input paradigms that are more suited for single hand entry than a keyboard. Online handwriting recognition allows for such input modalities. Handwriting recognition has always been a tough problem because of the handwriting variability, ambiguity and illegibility. This paper describes a simple approach involved in online handwriting recognition. Conventionally, the data obtained needs a lot of preprocessing including filtering, smoothing, slant removing and size normalization before recognition process. Instead of doing such lengthy preprocessing, this paper presents a simple approach to extract the useful character information. The whole process requires no preprocessing and size normalization. The method is applicable for off-line character recognition as well. This is a writer-independent system based on two neural net (NN) techniques: back propagation neural network (BPN) and counter propagation neural network (CPN). Performances of BPN and CPN are tested for upper-case English alphabets for a number of different styles from different peoples. 2006 Conference or Workshop Item PeerReviewed application/pdf en http://eprints.utm.my/8745/1/ICEIS-2006.pdf Zafar, Muhammad Faisal and Mohamad, Dzulkifli and Othman, Muhamad Razib (2006) Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study. In: In Proc IEEE Int'l Conf Engineering of Intelligent Systems (ICEIS'2006), Islamabad, Pakistan. |
| spellingShingle | Zafar, Muhammad Faisal Mohamad, Dzulkifli Othman, Muhamad Razib Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study |
| title | Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study |
| title_full | Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study |
| title_fullStr | Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study |
| title_full_unstemmed | Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study |
| title_short | Neural Nets for On-line Isolated Handwritten Character Recognition: A Comparative Study |
| title_sort | neural nets for on-line isolated handwritten character recognition: a comparative study |
| url | http://eprints.utm.my/8745/ http://eprints.utm.my/8745/1/ICEIS-2006.pdf |