dc.contributor.author | Lumban Tobing, Tabita | |
dc.contributor.author | Yildirim Yayilgan, Sule | |
dc.contributor.author | George, Sony | |
dc.contributor.author | Elgvin, Torleif | |
dc.date.accessioned | 2023-01-13T12:32:26Z | |
dc.date.available | 2023-01-13T12:32:26Z | |
dc.date.created | 2022-08-25T12:09:39Z | |
dc.date.issued | 2022 | |
dc.identifier.issn | 2161-8798 | |
dc.identifier.uri | https://hdl.handle.net/11250/3043371 | |
dc.description.abstract | Character recognition is widely considered an essential factor in preserving and digitizing historical handwritten documents. While it has shown a significant impact, the character recognition of historical handwritten documents is still a challenging task. This work aims to present a study on building a character recognition system for a handwritten ancient Hebrew text utilizing convolutional neural networks, dealing with material degradation, script complexity, and varied handwriting style. Our research underlined the importance of creating a ground-truth dataset for a robust and reliable character recognition system. Moreover, this study compares the performance of four convolutional neural network models applied to our dataset. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | Society for Imaging Science and Technology | en_US |
dc.title | Isolated Handwritten Character Recognition of Ancient Hebrew Manuscripts | en_US |
dc.title.alternative | Isolated Handwritten Character Recognition of Ancient Hebrew Manuscripts | en_US |
dc.type | Journal article | en_US |
dc.description.version | publishedVersion | en_US |
dc.rights.holder | This version will not be available due to the publisher's copyright. | en_US |
dc.source.journal | Archiving Conference: Final Program and Proceedings | en_US |
dc.identifier.doi | 10.2352/issn.2168-3204.2022.19.1.8 | |
dc.identifier.cristin | 2045978 | |
dc.relation.project | Norges forskningsråd: 275293 | en_US |
cristin.ispublished | true | |
cristin.fulltext | original | |