Robust metrics for evaluating arabic OCR systems

Author

Saber, Shimaa ; Ahmed, Ali ; Hadhoud, Mohy

Author_Institution

Fac. of Comput. & Inf, Menoufia, Shebin El-kom, Egypt

fYear

2014

Firstpage

1

Lastpage

6

Abstract

Evaluating OCR software is an important task to test the accuracy and to compare the strengths and weaknesses of distinct OCR systems. Research in the past has been done to compare the performance of OCR systems, all metrics used before dependent only on the character accuracy. This paper introduces word-based accuracy as well as character accuracy metrics to evaluate and to compare the performance of Arabic OCR systems. Different types of real scanned images such as newspapers, books, and journals image samples are used. The experimental results proved that such metrics are useful for evaluation of Arabic OCR systems and for Arabic text retrieval applications.

Keywords

image sampling; optical character recognition; software performance evaluation; Arabic OCR system evaluation; Arabic text retrieval; OCR software evaluation; image sampling; robust metrics; Accuracy; Character recognition; Conferences; Image processing; Optical character recognition software; Performance evaluation; AOCR products; Accuracy metrics; performance evaluation;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, Applications and Systems Conference (IPAS), 2014 First International

Print_ISBN

978-1-4799-7068-1

Type

conf

DOI

10.1109/IPAS.2014.7043272

Filename

7043272