[ { "key": "BRA7AZU2", "version": 1564, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/BRA7AZU2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/BRA7AZU2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Hinrichsen", "parsedDate": "2021-12-01", "numChildren": 0 }, "data": { "key": "BRA7AZU2", "version": 1564, "itemType": "presentation", "title": "Community Building und Community Management in OCR-D", "creators": [ { "creatorType": "presenter", "firstName": "Lena", "lastName": "Hinrichsen" } ], "abstractNote": "", "presentationType": "", "date": "2021-12-01", "meetingName": "#vBIB21", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://nbn-resolving.org/urn:nbn:de:0290-opus4-178109", "accessDate": "", "shortTitle": "https://av.tib.eu/media/55592", "language": "deu", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2022-02-03T08:26:52Z", "dateModified": "2022-02-04T07:21:24Z" } }, { "key": "VBJS94CU", "version": 1555, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/VBJS94CU", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/VBJS94CU", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Baierer et al.", "parsedDate": "2021-10-01", "numChildren": 0 }, "data": { "key": "VBJS94CU", "version": 1555, "itemType": "conferencePaper", "title": "OCR-D & OCR4all: Two Complementary Approaches for Improved OCR of Historical Sources", "creators": [ { "creatorType": "author", "firstName": "Konstantin", "lastName": "Baierer" }, { "creatorType": "author", "firstName": "Andreas", "lastName": "Büttner" }, { "creatorType": "author", "firstName": "Elisabeth", "lastName": "Engl" }, { "creatorType": "author", "firstName": "Lena", "lastName": "Hinrichsen" }, { "creatorType": "author", "firstName": "", "lastName": "Reul, Christian" } ], "abstractNote": "", "proceedingsTitle": "Proceedings of the 6th International Workshop on Computational History (HistoInformatics 2021) co-located with ACM/IEEE Joint Conference on Digital Libraries 2021 (JCDL 2021)", "conferenceName": "HistoInformatics 2021", "publisher": "", "place": "", "date": "2021-10-01", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "", "citationKey": "", "url": "http://ceur-ws.org/Vol-2981/", "accessDate": "", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "englisch", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-11-02T15:22:39Z", "dateModified": "2021-11-02T15:27:26Z" } }, { "key": "DE7ZDKHH", "version": 1550, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/DE7ZDKHH", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/DE7ZDKHH", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Engl et al.", "parsedDate": "2021-05-19", "numChildren": 1 }, "data": { "key": "DE7ZDKHH", "version": 1550, "itemType": "presentation", "title": "Vom Bild zum Text – praktische OCR für die DH. Postcorrection, Hackathon", "creators": [ { "creatorType": "presenter", "firstName": "Elisabeth", "lastName": "Engl" }, { "creatorType": "presenter", "firstName": "Robert", "lastName": "Sachunsky" }, { "creatorType": "presenter", "firstName": "Robert", "lastName": "Fink" }, { "creatorType": "presenter", "firstName": "Robin", "lastName": "Schäfer" } ], "abstractNote": "", "presentationType": "", "date": "2021-05-19", "meetingName": "vDHd2021", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://dhd-ag-ocr.github.io/slides/OCR@vDHd-Z3.pdf", "accessDate": "", "shortTitle": "https://meet.gwdg.de/playback/presentation/2.3/db36b9cd45a79838b121a8b68270a85734c8f026-1621428290680?meetingId=db36b9cd45a79838b121a8b68270a85734c8f026-1621428290680", "language": "deu", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-26T14:07:49Z", "dateModified": "2021-10-27T13:54:57Z" } }, { "key": "VARD35SJ", "version": 1549, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/VARD35SJ", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/VARD35SJ", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Engl et al.", "parsedDate": "2021-05-05", "numChildren": 1 }, "data": { "key": "VARD35SJ", "version": 1549, "itemType": "presentation", "title": "Vom Bild zum Text – praktische OCR für die DH. OCR-D und OCR4all, TEI-Konvertierung", "creators": [ { "creatorType": "presenter", "firstName": "Elisabeth", "lastName": "Engl" }, { "creatorType": "presenter", "firstName": "Konstantin", "lastName": "Baierer" }, { "creatorType": "presenter", "firstName": "Christian", "lastName": "Reul" }, { "creatorType": "presenter", "firstName": "Andreas", "lastName": "Büttner" } ], "abstractNote": "", "presentationType": "", "date": "2021-05-05", "meetingName": "vDHd2021", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://dhd-ag-ocr.github.io/slides/OCR@vDHd-Z1.pdf", "accessDate": "", "shortTitle": "https://meet.gwdg.de/playback/presentation/2.3/db36b9cd45a79838b121a8b68270a85734c8f026-1620218746064?meetingId=db36b9cd45a79838b121a8b68270a85734c8f026-1620218746064", "language": "german", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-26T12:03:45Z", "dateModified": "2021-10-27T13:54:26Z" } }, { "key": "V9BC7R29", "version": 1548, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/V9BC7R29", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/V9BC7R29", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Engl et al.", "parsedDate": "2021-05-12", "numChildren": 1 }, "data": { "key": "V9BC7R29", "version": 1548, "itemType": "presentation", "title": "Vom Bild zum Text – praktische OCR für die DH. Evaluation, Transkription, Training", "creators": [ { "creatorType": "presenter", "firstName": "Elisabeth", "lastName": "Engl" }, { "creatorType": "presenter", "firstName": "Konstantin", "lastName": "Baierer" }, { "creatorType": "presenter", "firstName": "Andreas", "lastName": "Büttner" }, { "creatorType": "presenter", "firstName": "Jan", "lastName": "Kamlah" } ], "abstractNote": "", "presentationType": "", "date": "2021-05-12", "meetingName": "vDHd2021", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://dhd-ag-ocr.github.io/slides/OCR@vDHd-Z2.pdf", "accessDate": "", "shortTitle": "https://meet.gwdg.de/playback/presentation/2.3/db36b9cd45a79838b121a8b68270a85734c8f026-1620823922694?meetingId=db36b9cd45a79838b121a8b68270a85734c8f026-1620823922694", "language": "german", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-26T12:11:00Z", "dateModified": "2021-10-27T10:47:26Z" } }, { "key": "KGVAJC4Q", "version": 1545, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/KGVAJC4Q", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/KGVAJC4Q", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Hertling and Klaes", "parsedDate": "2021-06-17", "numChildren": 0 }, "data": { "key": "KGVAJC4Q", "version": 1545, "itemType": "presentation", "title": "OCR on demand: Der Ansatz eines User-generated Content", "creators": [ { "creatorType": "presenter", "firstName": "Anke", "lastName": "Hertling" }, { "creatorType": "presenter", "firstName": "Sebastian", "lastName": "Klaes" } ], "abstractNote": "Mit der Initiierung und Durchführung von Massendigitalisierungsprojekten haben Bibliotheken grundlegende Voraussetzungen für den Zugang und die Nutzung digitaler Quellen geschaffen. Vor dem Hintergrund der Weiterentwicklung digitaler Forschungsmethoden u.a. im Bereich Digital Humanities stellt sich nun zunehmend die Frage nach der Qualität insbesondere der Volltexte. Die Volltextqualität in den digitalen Sammlungen ist dabei nicht nur abhängig von Materialbesonderheiten, sondern wird auch durch jeweils eingesetzte Texterkennungssysteme erheblich beeinflusst. Ausgangspunkt des Vortrags ist eine von der Forschungsbibliothek des Georg-Eckert-Instituts – Leibniz-Institut für internationale Schulbuchforschung (GEI) durchgeführte Studie zur Qualität der Texterkennung der seit 2009 im GEI digitalisierten Quellen. Auf Grundlage der Ergebnisse der Studie werden die aktuellen Herausforderungen erörtert, die sich mit einer an der Forschung und das heißt Korpus orientierten Digitalisierung und Volltexterkennung ergeben und die Notwendigkeit aufgezeigt, die Digitalisierung und Volltexterkennung verstärkt nach verschiedenen Nutzungsansprüchen auszudifferenzieren. Digitalisierung muss als gemeinsamer Verständigungsprozess zwischen Bibliothek und Forschung verstanden und verstärkt agil an dem jeweiligen Bedarf der Nutzer*innen ausgerichtet werden. Rekurrierend auf dieses Selbstverständnis wird im zweiten Teil des Vortrags das im OCR-D-Rahmen geplante Vorhaben vorgestellt, die Volltexterkennung anhand materialspezifischer Attribute zu steuern und zu optimieren. Zentral hierfür ist der Ansatz, dass Forscher*innen als wichtige Zielgruppe mit Unterstützung von Bibliotheken in der Lage sein sollen, selbständig OCR-D-Komponenten einzusetzen. Von diesem Angebot können Bibliotheken in zweierlei Hinsicht profitieren: Die von der Forschung optimierten Volltexte können sie für die Weiterentwicklung von OCR-Modellen nachnutzen und ihre Stellung im Bereich Services für die Forschung ausbauen.", "presentationType": "", "date": "2021-06-17", "meetingName": "Bibliothekartag 2021", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://opus4.kobv.de/opus4-bib-info/frontdoor/index/index/docId/17662", "accessDate": "", "shortTitle": "OCR on demand", "language": "deu", "rights": "https://creativecommons.org/licenses/by/4.0/deed.de", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-27T07:05:18Z", "dateModified": "2021-10-27T08:46:45Z" } }, { "key": "FFQB9JW2", "version": 1544, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/FFQB9JW2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/FFQB9JW2", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Würzner and Sachunsky", "parsedDate": "2021-06-17", "numChildren": 0 }, "data": { "key": "FFQB9JW2", "version": 1544, "itemType": "presentation", "title": "Kollaborative Erstellung von Trainingsmaterialien für OCR – Ein Werkstattbericht", "creators": [ { "creatorType": "presenter", "firstName": "Kay-Michael", "lastName": "Würzner" }, { "creatorType": "presenter", "firstName": "Robert", "lastName": "Sachunsky" } ], "abstractNote": "Spätestens seit der Studie „OCR of historical printings\" (Springmann und Lüdeling, 2017) ist die landläufige Annahme, dass die Qualität automatischer Texterkennungsverfahren (OCR) mit zunehmendem Alter der Vorlage schlechter wird, widerlegt. Wird die OCR-Software mit passenden, manuell transkribierten Bild-Text-Paaren trainiert, sind Erkennungsraten jenseits 99 % auch für sehr frühe, vorindustrielle Drucke möglich. Dank quelloffener OCR-Engines wie Tesseract, kraken und Calamari ist es technisch möglich, jegliche Digitalisierungsvorhaben mit passgenauen Erkennungsmodellen zu stützen und so wissenschaftlich nachnutzbare Textergebnisse zu erzielen. Hochqualitative Trainingsmaterialen in ausreichendem Umfang sind jedoch für die meisten Schriftarten und Epochen nach wie vor ein Desiderat. Um diesem zu begegnen, engagieren sich Mitarbeitende der SLUB seit vergangenem Jahr in einer kollaborativen Transkriptionsinitiative. Da existierende Annotationswerkzeuge meist hohe technische Kenntnisse und dadurch eine lange Einarbeitungszeit erfordern, wurde zu diesem Zwecke ein einfacher Arbeitsablauf auf Basis geläufiger Tabellenkalkulationsprogramme entwickelt: Zunächst werden die zu transkribierenden Materialien mit Hilfe der im OCR-D-Projekt entwickelten Workflows vorprozessiert. Die noch fehlerbehafteten Textzeilen werden dann gemeinsam mit ihren korrespondierenden Bildderivaten in ein Tabellendokument exportiert. Anschließend korrigieren zwei Bearbeiter unabhängig voneinander die Volltexte und filtern fehlerhafte Bildausschnitte. Die entstehenden Transkriptionen werden dann miteinander verglichen und nur identische Zeilen gehen in die Trainingsdaten ein. Diese werden über GitHub veröffentlicht, stehen so der Allgemeinheit zur Verfügung und können ggf. nachkorrigiert werden. In unserer Präsentation zeigen wir erste Ergebnisse, adressieren häufige Fragen und mögliche Lösungen und berichten über Planungen, die Initiative als partizipatives Format auch für Nutzende auszurollen.", "presentationType": "", "date": "2021-06-17", "meetingName": "Bibliothekartag 2021", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://opus4.kobv.de/opus4-bib-info/frontdoor/index/index/docId/17661", "accessDate": "", "shortTitle": "", "language": "deu", "rights": "9", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-27T07:04:47Z", "dateModified": "2021-10-27T07:22:24Z" } }, { "key": "GAPF4SGR", "version": 1542, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/GAPF4SGR", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/GAPF4SGR", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Engl", "parsedDate": "2021-06-16", "numChildren": 0 }, "data": { "key": "GAPF4SGR", "version": 1542, "itemType": "presentation", "title": "OCR-D: Von Prototypen zu Digitalisierungsprojekten", "creators": [ { "creatorType": "presenter", "firstName": "Elisabeth", "lastName": "Engl" } ], "abstractNote": "Die DFG-Förderinitiative OCR-D (https://ocr-d.de/) befasst sich sowohl konzeptionell als auch praktisch mit der Verbesserung von Verfahren zur automatischen Text- und Strukturerfassung von digitalisierten Drucken aus dem 16.-19. Jahrhundert. Übergeordnetes Ziel ist es, für Titel der \"Verzeichnisse der im deutschen Sprachraum erschienenen Drucke” (VD) maschinenlesbaren, wissenschaftlich verwertbaren Volltext zu generieren. In einer ersten Projektphase wurden hierfür zunächst Bedarfe ermittelt, die in einer zweiten Projektphase von insgesamt acht DFG-geförderten Modulprojekten bearbeitet wurden. Wie erste Teststellungen um die Jahreswende 2019/2020 und im Sommer 2020 gezeigt haben, ist der vorhandene Prototyp der OCR-D Software bereits sehr robust; für den produktiven Einsatz in der (bibliothekarischen) Praxis muss dieser jedoch noch im Rahmen einer 2021 anlaufenden dritten Projektphase implementiert und optimiert werden. Der Vortrag beschreibt den aktuellen Stand der OCR-D-Software und die vielfältigen geplanten Anwendungsszenarien in bestandshaltenden und -verarbeitenden Einrichtungen mit ihren Anforderungen. Dabei wird auch auf die Desiderate eingegangen, die bei einer Pilotierung im Vorfeld der Implementierungsphase festgestellt wurden und in der dritten Projektphase bearbeitet werden.", "presentationType": "", "date": "2021-06-16", "meetingName": "Bibliothekartag 2021", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://opus4.kobv.de/opus4-bib-info/frontdoor/index/index/docId/17593", "accessDate": "2021-10-27T07:03:34Z", "shortTitle": "OCR-D", "language": "deu", "rights": "https://creativecommons.org/licenses/by/4.0/deed.de", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-27T07:03:35Z", "dateModified": "2021-10-27T07:17:14Z" } }, { "key": "VK97GXI2", "version": 1535, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/VK97GXI2", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/VK97GXI2", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/418719/items/DE7ZDKHH", "type": "application/json" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } } }, "data": { "key": "VK97GXI2", "version": 1535, "parentItem": "DE7ZDKHH", "itemType": "attachment", "linkMode": "linked_url", "title": "", "accessDate": "", "url": "https://meet.gwdg.de/playback/presentation/2.3/db36b9cd45a79838b121a8b68270a85734c8f026-1621428290680?meetingId=db36b9cd45a79838b121a8b68270a85734c8f026-1621428290680", "note": "", "contentType": "", "charset": "", "tags": [], "relations": {}, "dateAdded": "2021-10-27T07:09:10Z", "dateModified": "2021-10-27T07:09:10Z" } }, { "key": "92M9KU8Q", "version": 1534, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/92M9KU8Q", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/92M9KU8Q", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/418719/items/V9BC7R29", "type": "application/json" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } } }, "data": { "key": "92M9KU8Q", "version": 1534, "parentItem": "V9BC7R29", "itemType": "attachment", "linkMode": "linked_url", "title": "", "accessDate": "", "url": "https://meet.gwdg.de/playback/presentation/2.3/db36b9cd45a79838b121a8b68270a85734c8f026-1620823922694?meetingId=db36b9cd45a79838b121a8b68270a85734c8f026-1620823922694", "note": "", "contentType": "", "charset": "", "tags": [], "relations": {}, "dateAdded": "2021-10-27T07:08:29Z", "dateModified": "2021-10-27T07:08:29Z" } }, { "key": "NA74WE96", "version": 1523, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/NA74WE96", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/NA74WE96", "type": "text/html" }, "up": { "href": "https://api.zotero.org/groups/418719/items/VARD35SJ", "type": "application/json" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } } }, "data": { "key": "NA74WE96", "version": 1523, "parentItem": "VARD35SJ", "itemType": "attachment", "linkMode": "linked_url", "title": "", "accessDate": "", "url": "https://meet.gwdg.de/playback/presentation/2.3/db36b9cd45a79838b121a8b68270a85734c8f026-1620218746064?meetingId=db36b9cd45a79838b121a8b68270a85734c8f026-1620218746064", "note": "", "contentType": "", "charset": "", "tags": [], "relations": {}, "dateAdded": "2021-10-26T15:26:49Z", "dateModified": "2021-10-26T15:26:49Z" } }, { "key": "SB4F6DJM", "version": 1519, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/SB4F6DJM", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/SB4F6DJM", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "parsedDate": "2021-09-15", "numChildren": 0 }, "data": { "key": "SB4F6DJM", "version": 1519, "itemType": "presentation", "title": "Vom Bild zum Text – praktische OCR für die DH. Abschlussveranstaltung", "creators": [], "abstractNote": "", "presentationType": "", "date": "2021-09-15", "meetingName": "vDHd2021", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://dhd-ag-ocr.github.io/slides/OCR@vDHd-Abschluss.pdf", "accessDate": "", "shortTitle": "", "language": "german", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-26T14:15:45Z", "dateModified": "2021-10-26T15:18:06Z" } }, { "key": "WMQF43DB", "version": 1519, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/WMQF43DB", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/WMQF43DB", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "parsedDate": "2021-03-23", "numChildren": 0 }, "data": { "key": "WMQF43DB", "version": 1519, "itemType": "presentation", "title": "Vom Bild zum Text – praktische OCR für die DH. Einführungsveranstaltung", "creators": [], "abstractNote": "", "presentationType": "", "date": "2021-03-23", "meetingName": "vDHd2021", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://dhd-ag-ocr.github.io/assets/other/OCR@vDHd.pdf", "accessDate": "", "shortTitle": "", "language": "german", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-26T12:01:36Z", "dateModified": "2021-10-26T15:18:03Z" } }, { "key": "AMSQTNC6", "version": 1382, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/AMSQTNC6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/AMSQTNC6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Klaus et al.", "parsedDate": "2019-03-16", "numChildren": 0 }, "data": { "key": "AMSQTNC6", "version": 1382, "itemType": "presentation", "title": "OCR Nachkorrektur des Royal Society Corpus", "creators": [ { "creatorType": "presenter", "firstName": "Carsten", "lastName": "Klaus" }, { "creatorType": "presenter", "firstName": "Peter", "lastName": "Fankhauser" }, { "creatorType": "presenter", "firstName": "Dietrich", "lastName": "Klakow" } ], "abstractNote": "A single abstract from the DHd-2019 Book of Abstracts.", "presentationType": "", "date": "2019-03-16", "meetingName": "DHd 2019 Digital Humanities multimedial und multimodal. 6. Tagung des Verbands \"Digital Humanities im deutschsprachigen Raum\" (DHd 2019)", "place": "Frankfurt am Main und Mainz", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://zenodo.org/record/4622058", "accessDate": "2021-10-26T11:24:43Z", "shortTitle": "", "language": "", "rights": "", "extra": "", "tags": [ { "tag": "DHd2019", "type": 1 }, { "tag": "historical corpus", "type": 1 }, { "tag": "misspellings", "type": 1 }, { "tag": "noisy channel model", "type": 1 }, { "tag": "ocr", "type": 1 }, { "tag": "royal society", "type": 1 } ], "collections": [ "VGHM3E6A" ], "relations": {}, "dateAdded": "2021-10-26T11:24:44Z", "dateModified": "2021-10-26T11:25:08Z" } }, { "key": "3UWAPUEF", "version": 1380, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/3UWAPUEF", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/3UWAPUEF", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Bald et al.", "parsedDate": "2019-03-16", "numChildren": 0 }, "data": { "key": "3UWAPUEF", "version": 1380, "itemType": "presentation", "title": "Korrektur von fehlerhaften OCR Ergebnissen durch automatisches Alignment mit Texten eines Korpus", "creators": [ { "creatorType": "presenter", "firstName": "Markus", "lastName": "Bald" }, { "creatorType": "presenter", "firstName": "Vincenzo", "lastName": "Damiani" }, { "creatorType": "presenter", "firstName": "Holger", "lastName": "Essler" }, { "creatorType": "presenter", "firstName": "Björn", "lastName": "Eyeselein" }, { "creatorType": "presenter", "firstName": "Christian", "lastName": "Reul" }, { "creatorType": "presenter", "firstName": "Frank", "lastName": "Puppe" } ], "abstractNote": "A single abstract from the DHd-2019 Book of Abstracts.", "presentationType": "", "date": "2019-03-16", "meetingName": "DHd 2019 Digital Humanities multimedial und multimodal. 6. Tagung des Verbands \"Digital Humanities im deutschsprachigen Raum\" (DHd 2019)", "place": "Frankfurt am Main und Mainz", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://zenodo.org/record/4622024", "accessDate": "2021-10-26T11:23:29Z", "shortTitle": "", "language": "german", "rights": "", "extra": "", "tags": [ { "tag": "Alignment", "type": 1 }, { "tag": "DHd2019", "type": 1 }, { "tag": "Ground Truth Generation", "type": 1 }, { "tag": "Optical Character Recognition", "type": 1 } ], "collections": [ "VGHM3E6A" ], "relations": {}, "dateAdded": "2021-10-26T11:23:30Z", "dateModified": "2021-10-26T11:23:43Z" } }, { "key": "68WFPJ6D", "version": 1377, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/68WFPJ6D", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/68WFPJ6D", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Reul et al.", "parsedDate": "2019-03-16", "numChildren": 0 }, "data": { "key": "68WFPJ6D", "version": 1377, "itemType": "presentation", "title": "State of the Art Optical Character Recognition of 19th Century Fraktur Scripts using Open Source Engines", "creators": [ { "creatorType": "presenter", "firstName": "Christian", "lastName": "Reul" }, { "creatorType": "presenter", "firstName": "Uwe", "lastName": "Springmann" }, { "creatorType": "presenter", "firstName": "Christoph", "lastName": "Wick" }, { "creatorType": "presenter", "firstName": "Frank", "lastName": "Puppe" } ], "abstractNote": "A single abstract from the DHd-2019 Book of Abstracts.", "presentationType": "", "date": "2019-03-16", "meetingName": "DHd 2019 Digital Humanities multimedial und multimodal. 6. Tagung des Verbands \"Digital Humanities im deutschsprachigen Raum\" (DHd 2019),", "place": "Frankfurt am Main und Mainz", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://zenodo.org/record/4622016", "accessDate": "2021-10-26T11:19:24Z", "shortTitle": "", "language": "german", "rights": "", "extra": "", "tags": [ { "tag": "19th century Fraktur", "type": 1 }, { "tag": "DHd2019", "type": 1 }, { "tag": "Mixed Models", "type": 1 }, { "tag": "Optical Character Recognition", "type": 1 } ], "collections": [ "8DGRKRJ9" ], "relations": {}, "dateAdded": "2021-10-26T11:19:25Z", "dateModified": "2021-10-26T11:19:36Z" } }, { "key": "XW3Q2GNW", "version": 1371, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/XW3Q2GNW", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/XW3Q2GNW", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Hodel et al.", "parsedDate": "2018-02-26", "numChildren": 0 }, "data": { "key": "XW3Q2GNW", "version": 1371, "itemType": "presentation", "title": "Automatic Text Recognition: Mit Transkribus Texterkennung trainieren und anwenden", "creators": [ { "creatorType": "presenter", "firstName": "Tobias", "lastName": "Hodel" }, { "creatorType": "presenter", "firstName": "Tobias", "lastName": "Strauß" }, { "creatorType": "presenter", "firstName": "Markus", "lastName": "Diem" } ], "abstractNote": "A single abstract from the DHd-2018 Book of Abstracts.", "presentationType": "", "date": "2018-02-26", "meetingName": "DHd 2018 Kritik der digitalen Vernunft. 5. Tagung des Verbands \"Digital Humanities im deutschsprachigen Raum\" (DHd 2018)", "place": "Köln", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://zenodo.org/record/4622421", "accessDate": "2021-10-26T11:12:39Z", "shortTitle": "Automatic Text Recognition", "language": "", "rights": "", "extra": "", "tags": [ { "tag": "Automatic Text Recognition", "type": 1 }, { "tag": "DHd2018", "type": 1 }, { "tag": "Quellenarbeit", "type": 1 }, { "tag": "Transkribus", "type": 1 }, { "tag": "Transkriptionssoftware", "type": 1 } ], "collections": [], "relations": {}, "dateAdded": "2021-10-26T11:12:40Z", "dateModified": "2021-10-26T11:13:12Z" } }, { "key": "F4UUNTUK", "version": 1368, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/F4UUNTUK", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/F4UUNTUK", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Hodel", "parsedDate": "2018-02-26", "numChildren": 0 }, "data": { "key": "F4UUNTUK", "version": 1368, "itemType": "conferencePaper", "title": "Konsequenzen automatischer Texterkennung – Ein Aufriss zur Texterkennung mit Machine Learning", "creators": [ { "creatorType": "author", "firstName": "Tobias", "lastName": "Hodel" } ], "abstractNote": "", "proceedingsTitle": "DHd 2018. Kritik der digitalen Vernunft. Konferenzabstracts", "conferenceName": "DHd 2018 Kritik der digitalen Vernunft. 5. Tagung des Verbands \"Digital Humanities im deutschsprachigen Raum\" (DHd 2018)", "publisher": "", "place": "Köln", "date": "2018-02-26", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "249-252", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "978-3-946275-02-2", "citationKey": "", "url": "https://zenodo.org/record/4622423#.YXfFTprP1aQ", "accessDate": "2021-10-26T10:00:00Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "german", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [], "relations": {}, "dateAdded": "2021-10-26T09:06:33Z", "dateModified": "2021-10-26T09:13:21Z" } }, { "key": "PDH4SU55", "version": 1355, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/PDH4SU55", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/PDH4SU55", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Boenig et al.", "parsedDate": "2016-03-11", "numChildren": 0 }, "data": { "key": "PDH4SU55", "version": 1355, "itemType": "presentation", "title": "Über den Mehrwert der Vernetzung von OCR-Verfahren zur Erfassung von Texten des 17. Jahrhunderts", "creators": [ { "creatorType": "presenter", "firstName": "Matthias", "lastName": "Boenig" }, { "creatorType": "presenter", "firstName": "Kay-Michael", "lastName": "Würzner" }, { "creatorType": "presenter", "firstName": "Arne", "lastName": "Binder" }, { "creatorType": "presenter", "firstName": "Uwe", "lastName": "Springmann" } ], "abstractNote": "", "presentationType": "", "date": "2016-03-11", "meetingName": "DHd 2016", "place": "Leipzig", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "http://dhd2016.de/boa.pdf#page=103", "accessDate": "", "shortTitle": "", "language": "germam", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-10-25T15:30:04Z", "dateModified": "2021-10-25T15:33:53Z" } }, { "key": "IKZZCXD6", "version": 1338, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/IKZZCXD6", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/IKZZCXD6", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Weichselbaumer and Christlein", "parsedDate": "2016", "numChildren": 0 }, "data": { "key": "IKZZCXD6", "version": 1338, "itemType": "conferencePaper", "title": "Automatische Typenbestimmung in historischen Drucken", "creators": [ { "creatorType": "author", "firstName": "Nikolaus", "lastName": "Weichselbaumer" }, { "creatorType": "author", "firstName": "Vincent", "lastName": "Christlein" } ], "abstractNote": "", "proceedingsTitle": "DHd 2016. Modellierung - Vernetzung - Visualisierung. Die Digital Humanities als fächerübergreifendes Forschungsparadigma. Konferenzabstracts. 2. überarbeitete und erweiterte Ausgabe", "conferenceName": "DHd 2016. Modellierung - Vernetzung - Visualisierung. Die Digital Humanities als fächerübergreifendes Forschungsparadigma", "publisher": "nisaba", "place": "Universität Leipzig", "date": "2016", "eventPlace": "", "volume": "", "issue": "", "numberOfVolumes": "", "pages": "321-322", "series": "", "seriesNumber": "", "DOI": "", "ISBN": "978-3-941379-06-0", "citationKey": "", "url": "https://zenodo.org/record/3679331#.YXbFxZrP2ck", "accessDate": "2021-10-25T10:00:00Z", "ISSN": "", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "German", "libraryCatalog": "", "callNumber": "", "rights": "", "extra": "", "tags": [], "collections": [ "X5978Q33" ], "relations": {}, "dateAdded": "2021-10-25T14:51:14Z", "dateModified": "2021-10-25T14:59:00Z" } }, { "key": "SINJ7NBD", "version": 1309, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/SINJ7NBD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/SINJ7NBD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 8253754, "username": "hinrichsen", "name": "Lena Hinrichsen", "links": { "alternate": { "href": "https://www.zotero.org/hinrichsen", "type": "text/html" } } }, "creatorSummary": "Hartwig", "parsedDate": "2021-07-06", "numChildren": 0 }, "data": { "key": "SINJ7NBD", "version": 1309, "itemType": "presentation", "title": "Open Source OCR-Systeme", "creators": [ { "creatorType": "presenter", "firstName": "Uwe", "lastName": "Hartwig" } ], "abstractNote": "", "presentationType": "", "date": "2021-07-06", "meetingName": "", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://doi.org/10.5281/zenodo.5076012", "accessDate": "", "shortTitle": "", "language": "german", "rights": "", "extra": "", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-07-13T06:46:45Z", "dateModified": "2021-07-19T13:56:17Z" } }, { "key": "PK2MWGRN", "version": 1294, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/PK2MWGRN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/PK2MWGRN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 6781390, "username": "ElisabethEngl", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/elisabethengl", "type": "text/html" } } }, "lastModifiedByUser": { "id": 2711152, "username": "ElisaHerrmann", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/elisaherrmann", "type": "text/html" } } }, "creatorSummary": "Neudecker", "parsedDate": "2020-10-20", "numChildren": 0 }, "data": { "key": "PK2MWGRN", "version": 1294, "itemType": "presentation", "title": "OCR-D: An open ecosystem for improving OCR on historical documents", "creators": [ { "creatorType": "presenter", "firstName": "Clemens", "lastName": "Neudecker" } ], "abstractNote": "", "presentationType": "Vortrag", "date": "20.10.2020", "meetingName": "Mini-ELAG", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://elag.org/mini-elag-october-20-2020/ocr-d-an-open-ecosystem-for-improving-ocr-on-historical-documents/", "accessDate": "", "shortTitle": "", "language": "englisch", "rights": "", "extra": "ZSCC: NoCitationData[s0]", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2020-10-02T06:38:51Z", "dateModified": "2021-04-13T09:33:23Z" } }, { "key": "FJHYE4CN", "version": 1293, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/FJHYE4CN", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/FJHYE4CN", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2711152, "username": "ElisaHerrmann", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/elisaherrmann", "type": "text/html" } } }, "lastModifiedByUser": { "id": 65, "username": "rcrath", "name": "Richard C. Rath", "links": { "alternate": { "href": "https://www.zotero.org/rcrath", "type": "text/html" } } }, "creatorSummary": "Engl", "parsedDate": "2021-01-03", "numChildren": 0 }, "data": { "key": "FJHYE4CN", "version": 1293, "itemType": "presentation", "title": "Massendigitalisierung alter Drucke – OCR-D in Bibliotheken", "creators": [ { "creatorType": "presenter", "firstName": "Elisabeth", "lastName": "Engl" } ], "abstractNote": "", "presentationType": "Vortrag", "date": "01.03.2021", "meetingName": "3. Workshop zur Retrodigitalisierung. OCR – Prozesse und Entwicklungen", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://wiki.zbw.eu/pages/viewpage.action?pageId=33620559&preview=/33620559/33620562/2021-02-24_Engl_Massendigitalisierung%20alter%20Drucke.pdf", "accessDate": "", "shortTitle": "", "language": "deutsch", "rights": "", "extra": "ZSCC: NoCitationData[s0]", "tags": [ { "tag": "#nosource" } ], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-03-05T12:56:00Z", "dateModified": "2021-03-09T20:37:42Z" } }, { "key": "4AWT6KIC", "version": 1288, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/4AWT6KIC", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/4AWT6KIC", "type": "text/html" } }, "meta": { "createdByUser": { "id": 2711152, "username": "ElisaHerrmann", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/elisaherrmann", "type": "text/html" } } }, "lastModifiedByUser": { "id": 65, "username": "rcrath", "name": "Richard C. Rath", "links": { "alternate": { "href": "https://www.zotero.org/rcrath", "type": "text/html" } } }, "creatorSummary": "Weichselbaumer et al.", "parsedDate": "2020", "numChildren": 0 }, "data": { "key": "4AWT6KIC", "version": 1288, "itemType": "journalArticle", "title": "New Approaches to OCR for Early Printed Books", "creators": [ { "creatorType": "author", "firstName": "Nikolaus", "lastName": "Weichselbaumer" }, { "creatorType": "author", "firstName": "Mathias", "lastName": "Seuret" }, { "creatorType": "author", "firstName": "Saskia", "lastName": "Limbach" }, { "creatorType": "author", "firstName": "Rui", "lastName": "Dong" }, { "creatorType": "author", "firstName": "Manuel", "lastName": "Burghardt" }, { "creatorType": "author", "firstName": "Vincent", "lastName": "Christlein" } ], "abstractNote": "Books printed before 1800 present major problems for OCR. One of the main obstacles is the lack of diversity of historical fonts in training data. The OCR-D project, consisting of book historians and computer scientists, aims to address this deficiency by focussing on three major issues. Our first target was to create a tool that identifies font groups automatically in images of historical documents. We concentrated on Gothic font groups that were commonly used in German texts printed in the 15th and 16th century: the well-known Fraktur and the lesser known Bastarda, Rotunda, Textura und Schwabacher. The tool was trained with 35,000 images and reaches an accuracy level of 98%. It can not only differentiate between the above-mentioned font groups but also Hebrew, Greek, Antiqua and Italic. It can also identify woodcut images and irrelevant data (book covers, empty pages, etc.). In a second step, we created an online training infrastructure (okralact), which allows for the use of various open source OCR engines such as Tesseract, OCRopus, Kraken and Calamari. At the same time, it facilitates training for specific models of font groups. The high accuracy of the recognition tool paves the way for the unprecedented opportunity to differentiate between the fonts used by individual printers. With more training data and further adjustments, the tool could help to fill a major gap in historical research.", "publicationTitle": "DigItalia", "publisher": "", "place": "", "date": "Dezember 2020", "volume": "15", "issue": "2", "section": "", "partNumber": "", "partTitle": "", "pages": "74-87", "series": "", "seriesTitle": "", "seriesText": "", "journalAbbreviation": "DigItalia", "DOI": "10/ghstmx", "citationKey": "", "url": "https://doi.org/10.36181/digitalia-00015", "accessDate": "2021-01-11T10:37:25Z", "PMID": "", "PMCID": "", "ISSN": "1972-621X", "archive": "", "archiveLocation": "", "shortTitle": "", "language": "eng", "libraryCatalog": "DOI.org (CSL JSON)", "callNumber": "", "rights": "", "extra": "ZSCC: 0000000", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2021-01-11T10:37:25Z", "dateModified": "2021-01-12T21:04:48Z" } }, { "key": "DHYHUXJD", "version": 1284, "library": { "type": "group", "id": 418719, "name": "OCR-D", "links": { "alternate": { "href": "https://www.zotero.org/groups/ocr-d", "type": "text/html" } } }, "links": { "self": { "href": "https://api.zotero.org/groups/418719/items/DHYHUXJD", "type": "application/json" }, "alternate": { "href": "https://www.zotero.org/groups/ocr-d/items/DHYHUXJD", "type": "text/html" } }, "meta": { "createdByUser": { "id": 6781390, "username": "ElisabethEngl", "name": "", "links": { "alternate": { "href": "https://www.zotero.org/elisabethengl", "type": "text/html" } } }, "creatorSummary": "Boenig", "parsedDate": "2020-08-10", "numChildren": 0 }, "data": { "key": "DHYHUXJD", "version": 1284, "itemType": "presentation", "title": "Digitale Transformation: OCR-D, Angebot und Vision", "creators": [ { "creatorType": "presenter", "firstName": "Matthias", "lastName": "Boenig" } ], "abstractNote": "", "presentationType": "Vortrag", "date": "08.10.2020", "meetingName": "FAIR & Co.: Sicht- und Verfügbarkeit der digitalen Akademieforschung in einer vernetzten Wissenschaftslandschaft", "place": "", "series": "", "sessionTitle": "", "DOI": "", "citationKey": "", "url": "https://docs.google.com/presentation/d/1JCzfGq_Reze7R3TaecYyBocnkD6uNy94eukJTlYUbNI/edit#slide=id.g9d954d5829_0_469", "accessDate": "", "shortTitle": "", "language": "deutsch", "rights": "", "extra": "ZSCC: NoCitationData[s0]", "tags": [], "collections": [ "PHG36EJR" ], "relations": {}, "dateAdded": "2020-09-16T12:42:02Z", "dateModified": "2020-10-08T15:19:27Z" } } ]