Online Farsi Character Recognition Using Structural Features

Subject Areas : Renewable energy

Vahid Ghods ¹ , Ehsanollah Kabir ²

1 - Lecture/Semnan Branch, Islamic Azad University
2 - Professor/Tarbiat Modarres University, Tehran

Received: 2011-09-08 Accepted : 2012-02-27 Published : 2013-06-01

Keywords: recognition, grouping, Farsi, Decision tree, Online handwriting, Discrete letters,

Abstract :

In this paper, grouping and recognition of online Farsi discrete characters are presented according to their structural features. The letters are divided into 9 groups based on the form and structure of their main bodies. After feature extraction, grouping is performed using a decision tree. Final recognition of letters is carried out in each group by delayed strokes. The proposed method is a rapid method in character recognition because time-consuming methods have not been used. Our proposed method was tested on TMU-OFS dataset, and a recognition rate of 94% and 92% was achieved for character grouping and recognition, respectively. The mean processing time for recognizing a letter was 3ms.