A bibliometric analysis of off-line handwritten document analysis literature (1990–2020)

• Published in: Pattern recognition 2022-05, Vol.125, p.108513, Article 108513
• Main Authors: Ruiz-Parrado, Victoria, Heradio, Ruben, Aranda-Escolastico, Ernesto, Sánchez, Ángel, Vélez, José F.
• Format: Article
• Language: English
• Subjects: Automatic document analysis; Bibliometrics; Off-line handwriting recognition; Science mapping; Signature verification; Writer identification
• ISSN: 0031-3203; 1873-5142
• DOI: 10.1016/j.patcog.2021.108513

•5389 articles are examined to study the literature on off-line handwritten document analysis for the last thirty years.•Two techniques are applied: performance analysis and science mapping techniques.•The examination reveals the highest influential articles and the most productive authors and their collaboration networks.•The examination reveals which countries and institutions are leading research and the largest publishers.•The most relevant research topics and their evolution are studied and discussed. [Display omitted] Providing computers with the ability to process handwriting is both important and challenging, since many difficulties (e.g., different writing styles, alphabets, languages, etc.) need to be overcome for addressing a variety of problems (text recognition, signature verification, writer identification, word spotting, etc.). This paper reviews the growing literature on off-line handwritten document analysis over the last thirty years. A sample of 5389 articles is examined using bibliometric techniques. Using bibliometric techniques, this paper identifies (i) the most influential articles in the area, (ii) the most productive authors and their collaboration networks, (iii) the countries and institutions that have led research on the topic, (iv) the journals and conferences that have published most papers, and (v) the most relevant research topics (and their related tasks and methodologies) and their evolution over the years.