Title :
Feature Extraction for Online Farsi Characters
Author :
Ghods, Vahid ; Kabir, Ehsanollah
Author_Institution :
Dept. of Electr. Eng., Islamic Azad Univ., Semnan, Iran
Abstract :
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.
Keywords :
Internet; character recognition; feature extraction; image classification; natural languages; TMU dataset; character recognition; feature extraction; online Farsi character classification; Arabic; Character recognition; Decision tree; Farsi; Feature extraction; Online handwriting; Persian;
Conference_Titel :
Frontiers in Handwriting Recognition (ICFHR), 2010 International Conference on
Conference_Location :
Kolkata
Print_ISBN :
978-1-4244-8353-2
DOI :
10.1109/ICFHR.2010.81
