Deep Learning for Historical Document Analysis and Recognition—A Survey
Nowadays, deep learning methods are employed in a broad range of research fields. The analysis and recognition of historical documents, as we survey in this work, is not an exception. Our study analyzes the papers published in the last few years on this topic from different perspectives: we first pr...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Journal of Imaging |
Subjects: | |
Online Access: | https://www.mdpi.com/2313-433X/6/10/110 |
_version_ | 1797550742444179456 |
---|---|
author | Francesco Lombardi Simone Marinai |
author_facet | Francesco Lombardi Simone Marinai |
author_sort | Francesco Lombardi |
collection | DOAJ |
description | Nowadays, deep learning methods are employed in a broad range of research fields. The analysis and recognition of historical documents, as we survey in this work, is not an exception. Our study analyzes the papers published in the last few years on this topic from different perspectives: we first provide a pragmatic definition of historical documents from the point of view of the research in the area, then we look at the various sub-tasks addressed in this research. Guided by these tasks, we go through the different input-output relations that are expected from the used deep learning approaches and therefore we accordingly describe the most used models. We also discuss research datasets published in the field and their applications. This analysis shows that the latest research is a leap forward since it is not the simple use of recently proposed algorithms to previous problems, but novel tasks and novel applications of state of the art methods are now considered. Rather than just providing a conclusive picture of the current research in the topic we lastly suggest some potential future trends that can represent a stimulus for innovative research directions. |
first_indexed | 2024-03-10T15:34:44Z |
format | Article |
id | doaj.art-99905d1455af4b3a9b0b30855fd58229 |
institution | Directory Open Access Journal |
issn | 2313-433X |
language | English |
last_indexed | 2024-03-10T15:34:44Z |
publishDate | 2020-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Imaging |
spelling | doaj.art-99905d1455af4b3a9b0b30855fd582292023-11-20T17:23:09ZengMDPI AGJournal of Imaging2313-433X2020-10-0161011010.3390/jimaging6100110Deep Learning for Historical Document Analysis and Recognition—A SurveyFrancesco Lombardi0Simone Marinai1Department of Information Engineering (DINFO), School of Engineering, Università degli Studi di Firenze, 50139 Florence, ItalyDepartment of Information Engineering (DINFO), School of Engineering, Università degli Studi di Firenze, 50139 Florence, ItalyNowadays, deep learning methods are employed in a broad range of research fields. The analysis and recognition of historical documents, as we survey in this work, is not an exception. Our study analyzes the papers published in the last few years on this topic from different perspectives: we first provide a pragmatic definition of historical documents from the point of view of the research in the area, then we look at the various sub-tasks addressed in this research. Guided by these tasks, we go through the different input-output relations that are expected from the used deep learning approaches and therefore we accordingly describe the most used models. We also discuss research datasets published in the field and their applications. This analysis shows that the latest research is a leap forward since it is not the simple use of recently proposed algorithms to previous problems, but novel tasks and novel applications of state of the art methods are now considered. Rather than just providing a conclusive picture of the current research in the topic we lastly suggest some potential future trends that can represent a stimulus for innovative research directions.https://www.mdpi.com/2313-433X/6/10/110artificial neural networksdeep learningdocument image analysis and recognitionhistorical documents |
spellingShingle | Francesco Lombardi Simone Marinai Deep Learning for Historical Document Analysis and Recognition—A Survey Journal of Imaging artificial neural networks deep learning document image analysis and recognition historical documents |
title | Deep Learning for Historical Document Analysis and Recognition—A Survey |
title_full | Deep Learning for Historical Document Analysis and Recognition—A Survey |
title_fullStr | Deep Learning for Historical Document Analysis and Recognition—A Survey |
title_full_unstemmed | Deep Learning for Historical Document Analysis and Recognition—A Survey |
title_short | Deep Learning for Historical Document Analysis and Recognition—A Survey |
title_sort | deep learning for historical document analysis and recognition a survey |
topic | artificial neural networks deep learning document image analysis and recognition historical documents |
url | https://www.mdpi.com/2313-433X/6/10/110 |
work_keys_str_mv | AT francescolombardi deeplearningforhistoricaldocumentanalysisandrecognitionasurvey AT simonemarinai deeplearningforhistoricaldocumentanalysisandrecognitionasurvey |