Search results
1 – 3 of 3Mansoor Alghamdi and William Teahan
The 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…
Abstract
Purpose
The 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/approach
This 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.
Findings
The 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/value
To 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.
Details
Keywords
Tayyab Amjad, Michael M. Dent and Nur Naha Abu Mansor
The entrepreneurial marketing (EM) literature has grown rapidly during the last decade, yet much is left undiscovered. This paper aims to conduct a bibliometric analysis and text…
Abstract
Purpose
The entrepreneurial marketing (EM) literature has grown rapidly during the last decade, yet much is left undiscovered. This paper aims to conduct a bibliometric analysis and text mining of the EM domain to provide trends in previous EM research to address this issue. Future avenues for EM research are provided.
Design/methodology/approach
Using the Scopus database, a bibliometric analysis and text mining are conducted with EM articles published between 1976 and 2020.
Findings
The paper reports the most frequently published and cited authors and their co-author networks. Journals which contain these articles are included with country data, subject areas and use of author keywords related to the EM topic. Frequencies of keywords and newly-emerging keywords in every three-year period during the past 12 years are also examined. The findings suggest that future researchers should explore the subtopics of EM education, legitimation, entrepreneurial networking and social media/digital marketing within the EM domain.
Originality/value
Bibliometric analysis and text mining are relatively new methods with which to study the EM research domain, allowing for analysis of emerging trends over the past 12 years.
Details