Publikation: Dissertationsschrift

Neural text line extraction in historical documents

Grunddaten
Abstract
Autoren

Grunddaten

Titel	Neural text line extraction in historical documents
Untertitel	a two-stage clustering approach
Erscheinungsjahr	2018
Verlag	Universität Rostock
Verlagsort	Rostock
Publikationsform	Elektronische Ressource
Publikationsart	Dissertationsschrift
Sprache	Englisch
DOI	10.18453/rosdok_id00002427
Letzte Änderung	10.05.2019 13:47:41
Bearbeitungsstatus	durch UB Rostock abschließend validiert
Dauerhafte URL	http://purl.uni-rostock.de/fodb/pub/60710
Links zu Katalogen

Abstract

Accessibility of the valuable cultural heritage which is hidden in countless scanned historical documents is the motivation for the presented dissertation. The developed (fully automatic) text line extraction methodology combines state-of-the-art machine learning techniques and modern image processing methods. It demonstrates its quality by outperforming several other approaches on a couple of benchmarking datasets. The method is already being used by a wide audience of researchers from different disciplines and thus contributes its (small) part to the aforementioned goal.

Autor

Grüning, Tobias