A Novel OCR System for Calculating Handwritten Persian Arithmetic Expressions

Author

Khalighi, Sirvan ; Tirdad, Parisa ; Rabiee, Hamid R. ; Parviz, Mehdi

Author_Institution

Electical & Comput. Eng. Dept., Islamic Azad Univ. of Qazvin, Qazvin, Iran

fYear

2009

fDate

13-15 Dec. 2009

Firstpage

755

Lastpage

758

Abstract

In this paper, we propose a novel OCR system which can recognize and calculate handwritten Persian arithmetic expressions without using a keyboard or a memory to store the intermediate results. Our system is composed of two major phases: character recognition and calculation. The recognition phase is based on a new approach for feature extraction followed by a Fuzzy Support Vector Machines (FSVMs) as the classifier. In calculation phase a simple algorithm is used for calculating the recognized arithmetic expressions. The performance of the system was evaluated on a database consisting of 3400 digits and symbols written by 20 different people. 92 percent accuracy in recognition proves the good performance of the proposed system.

Keywords

feature extraction; fuzzy set theory; handwritten character recognition; optical character recognition; support vector machines; OCR system; arithmetic expressions; character recognition; feature extraction approach; fuzzy support vector machines; handwritten Persian arithmetic expressions; Character recognition; Digital arithmetic; Discrete wavelet transforms; Handwriting recognition; Keyboards; Neural networks; Optical character recognition software; Support vector machine classification; Support vector machines; Writing; Digit Recognition; Fuzzy Support Vector Machine (FSVM); Optical Character Recognition (OCR);

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Applications, 2009. ICMLA '09. International Conference on

Conference_Location

Miami Beach, FL

Print_ISBN

978-0-7695-3926-3

Type

conf

DOI

10.1109/ICMLA.2009.83

Filename

5381313