TY - JOUR

T1 - Experimental Evaluation of Arabic OCR Systems

AU - Alghamdi, Mansoor

AU - Teahan, William

PY - 2017/9/6

Y1 - 2017/9/6

N2 - PurposeThe aim of this paper is to experimentally evaluate the effectiveness of the state-of-the-art printed Arabic text recognition systems to determine open areas for future improvements. In addition, this paper proposes a standard protocol with a set of metrics for measuring the effectiveness of Arabic optical character recognition (OCR) systems to assist researchers in comparing different Arabic OCR approaches.Design/methodology/approachThis paper describes an experiment to automatically evaluate four well-known Arabic OCR systems using a set of performance metrics. The evaluation experiment is conducted on a publicly available printed Arabic dataset comprising 240 text images with a variety of resolution levels, font types, font styles and font sizes.FindingsThe experimental results show that the field of character recognition for printed Arabic still requires further research to reach an efficient text recognition method for Arabic script.Originality/valueTo the best of the authors’ knowledge, this is the first work that provides a comprehensive automated evaluation of Arabic OCR systems with respect to the characteristics of Arabic script and, in addition, proposes an evaluation methodology that can be used as a benchmark by researchers and therefore will contribute significantly to the enhancement of the field of Arabic script recognition.

AB - PurposeThe aim of this paper is to experimentally evaluate the effectiveness of the state-of-the-art printed Arabic text recognition systems to determine open areas for future improvements. In addition, this paper proposes a standard protocol with a set of metrics for measuring the effectiveness of Arabic optical character recognition (OCR) systems to assist researchers in comparing different Arabic OCR approaches.Design/methodology/approachThis paper describes an experiment to automatically evaluate four well-known Arabic OCR systems using a set of performance metrics. The evaluation experiment is conducted on a publicly available printed Arabic dataset comprising 240 text images with a variety of resolution levels, font types, font styles and font sizes.FindingsThe experimental results show that the field of character recognition for printed Arabic still requires further research to reach an efficient text recognition method for Arabic script.Originality/valueTo the best of the authors’ knowledge, this is the first work that provides a comprehensive automated evaluation of Arabic OCR systems with respect to the characteristics of Arabic script and, in addition, proposes an evaluation methodology that can be used as a benchmark by researchers and therefore will contribute significantly to the enhancement of the field of Arabic script recognition.

U2 - 10.1108/PRR-05-2017-0026

DO - 10.1108/PRR-05-2017-0026

M3 - Article

VL - 1

SP - 229

EP - 241

JO - PSU (Prince Sultan University) Research Review

JF - PSU (Prince Sultan University) Research Review

SN - 2399-1747

IS - 3

ER -