Global features for offline recognition of handwritten Arabic literal amounts
- 1 January 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2007 ITI 5th International Conference on Information and Communications Technology
Abstract
The domain of automatic handwriting recognition has a variety of applications in real world problems such as cheque processing, office automation and data entry applications. In this paper an approach for describing the role of holistic structural features in the recognition of offline handwritten Arabic literal amounts has been presented. Our proposed system attempts to recognize words from their overall shape. The extracted features are presented to several classifiers. The system is trained and tested using an Arabic handwritten database.Keywords
This publication has 8 references indexed in Scilit:
- Parallel univariate decision treesPattern Recognition Letters, 2007
- Classifiers combination and syntax analysis for Arabic literal amount recognitionEngineering Applications of Artificial Intelligence, 2006
- Arabic Word Recognition by Classifiers and ContextJournal of Computer Science and Technology, 2005
- Off-line Recognition of Handwritten Arabic Words Using Multiple Hidden Markov ModelsPublished by Springer Science and Business Media LLC ,2004
- A data base for Arabic handwritten text recognition researchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Efficient C4.5 [classification algorithm]IEEE Transactions on Knowledge and Data Engineering, 2002
- The role of holistic paradigms in handwritten word recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- THE A2iA INTERCHEQUE SYSTEM: COURTESY AMOUNT AND LEGAL AMOUNT RECOGNITION FOR FRENCH CHECKSSeries in Machine Perception and Artificial Intelligence, 1997