Abstract
In this paper, a system is proposed for word-based recognition of handwritten Arabic scripts. Techniques are discussed in details in term of three stages in the system, i.e. preprocessing, feature extraction and classification. Firstly, words are segmented from inputted scripts and also normalized in size. Then, DCT features are extracted for each word sample. Finally, these features are then utilized to train a neural network for classification. The proposed system has been successfully tested on database (version v2.0ple) consisting of 32492 Arabic words handwritten by more than 1000 different writers, and the results were promising and very encouraging.
Original language | English |
---|---|
Title of host publication | 2008 5th International multi-conference on systems, signals and devices |
Publisher | IEEE |
Pages | 486-490 |
Number of pages | 5 |
ISBN (Print) | 9781424422050 |
DOIs | |
Publication status | Published - 2008 |
Event | 5th International Multi-Conference on Systems, Signals and Devices - Amman, Jordan Duration: 20 Jul 2008 → 22 Jul 2008 |
Conference
Conference | 5th International Multi-Conference on Systems, Signals and Devices |
---|---|
Country/Territory | Jordan |
City | Amman |
Period | 20/07/08 → 22/07/08 |
Keywords
- character-recognition
- Arabic scripts