CorDeep and the Sacrobosco Dataset: Detection of Visual Elements in Historical Documents

dc.contributor.authorBüttner, Jochen
dc.contributor.authorMartinetz, Julius
dc.contributor.authorEl-Hajj, Hassan
dc.contributor.authorValleriani, Matteo
dc.date.accessioned2022-12-28T11:57:30Z
dc.date.available2022-12-28T11:57:30Z
dc.date.issued2022-10-15
dc.date.updated2022-11-10T12:52:42Z
dc.description.abstractRecent advances in object detection facilitated by deep learning have led to numerous solutions in a myriad of fields ranging from medical diagnosis to autonomous driving. However, historical research is yet to reap the benefits of such advances. This is generally due to the low number of large, coherent, and annotated datasets of historical documents, as well as the overwhelming focus on Optical Character Recognition to support the analysis of historical documents. In this paper, we highlight the importance of visual elements, in particular illustrations in historical documents, and offer a public multi-class historical visual element dataset based on the Sphaera corpus. Additionally, we train an image extraction model based on YOLO architecture and publish it through a publicly available web-service to detect and extract multi-class images from historical documents in an effort to bridge the gap between traditional and computational approaches in historical studies.
dc.description.sponsorshipBMBF, 01IS18037A, Verbundprojekt BIFOLD-BZML: Berlin Institute for the Foundations of Learning and Data
dc.identifier.eissn2313-433X
dc.identifier.urihttps://depositonce.tu-berlin.de/handle/11303/17893
dc.identifier.urihttps://doi.org/10.14279/depositonce-16682
dc.language.isoen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subject.ddc900 Geschichte und Geografiede
dc.subject.othersphaera
dc.subject.otherobject detection
dc.subject.otherhistorical illustrations
dc.subject.otherdigital humanities
dc.subject.otherartificial intelligence
dc.subject.otherdataset
dc.titleCorDeep and the Sacrobosco Dataset: Detection of Visual Elements in Historical Documents
dc.typeArticle
dc.type.versionpublishedVersion
dcterms.bibliographicCitation.articlenumber285
dcterms.bibliographicCitation.doi10.3390/jimaging8100285
dcterms.bibliographicCitation.issue10
dcterms.bibliographicCitation.journaltitleJournal of Imaging
dcterms.bibliographicCitation.originalpublishernameMDPI
dcterms.bibliographicCitation.originalpublisherplaceBasel
dcterms.bibliographicCitation.volume8
dcterms.rightsHolder.referenceCreative-Commons-Lizenz
tub.accessrights.dnbfree
tub.affiliationFak. 1 Geistes- und Bildungswissenschaften::Inst. Philosophie-, Literatur-, Wissenschafts- und Technikgeschichte::FG Wissenschaftsgeschichte
tub.publisher.universityorinstitutionTechnische Universität Berlin

Files

Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
jimaging-08-00285-v3.pdf
Size:
53.75 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.86 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections