Ground Truth erstellen, OCR-Modelle verbessern

Weil, Stefan

PDF
Kitodo_Praxistreffen_2022_Weil_GT.pdf - Published
Download (3MB)

URN:	urn:nbn:de:bsz:180-madoc-655049
Document Type:	Conference presentation
Year of publication:	2022
Conference title:	Kitodo Praxistreffen
Location of the conference venue:	Braunschweig, Germany
Date of the conference:	20.-21.10.2022
Related URLs:	https://www.kitodo.org/aktuelles/news/ak...
Publication language:	German
Institution:	Zentrale Einrichtungen > University Library
Pre-existing license:	Creative Commons Attribution, Share Alike 4.0 International (CC BY-SA 4.0)
Subject:	004 Computer science, internet 020 Library and information sciences
Subject headings (SWD):	Optische Zeichenerkennung , Open Source
Individual keywords (German):	OCR , automatisierte Texterkennung , Tesseract , Calamari , kraken , Open Source
Keywords (English):	OCR , automated text recognition , Tesseract , Calamari , kraken , Open Source
Abstract:	Der Vortrag beschreibt anhand konkreter Beispiele, wie durch Training von künstlichen neuronalen Netzen automatisierte Texterkennung für historische Drucke bestmögliche Ergebnisse liefern kann.
Translation of the abstract:	The presentation uses concrete examples to describe how automated text recognition for historical prints can deliver the best possible results by training artificial neural networks. (English)