Feature Extraction for Online Farsi Characters

This paper demonstrates the effectiveness of proper and efficient features for classifying online Farsi characters. We use these features to classify the main body of Farsi letters to nine groups. We implemented our method on the main bodies of 4000 isolated letters from "TMU dataset". Correct recognition rates of 99% and 94% were achieved for training and test sets respectively.

[1]  Patrick Gallinari,et al.  Stroke level HMMs for on-line handwriting recognition , 2002, Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition.

[2]  Karim Faez,et al.  Handwritten Farsi (Arabic) word recognition: a holistic approach using discrete HMM , 2001, Pattern Recognit..

[3]  Sargur N. Srihari,et al.  On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Masaki Nakagawa,et al.  The state of the art in Japanese online handwriting recognition compared to techniques in western handwriting recognition , 2003, Document Analysis and Recognition.

[5]  Adnan Amin,et al.  Preprocessing and structural feature extraction for a multi-fonts Arabic/Persian OCR , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[6]  Ehsanollah Kabir,et al.  Introducing a very large dataset of handwritten Farsi digits and a study on their varieties , 2007, Pattern Recognit. Lett..

[7]  Saeed Bagheri Shouraki,et al.  Recognition of Persian Online Handwriting Using Elastic Fuzzy Pattern Recognition , 2007, Int. J. Pattern Recognit. Artif. Intell..

[8]  Kemal Oflazer,et al.  An online handwriting recognition system for Turkish , 2004, Proceedings of the IEEE 12th Signal Processing and Communications Applications Conference, 2004..

[9]  Masaki Nakagawa,et al.  'Online recognition of Chinese characters: the state-of-the-art , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Off-line recognition of handwritten middle age Persian characters using moment , 2006, Pattern Recognition and Image Analysis.