Keyword spotting in historical handwritten documents based on graph matching

dc.contributor.authorStauffer, Michael
dc.contributor.authorFischer, Andreas
dc.contributor.authorRiesen, Kaspar
dc.date.accessioned2024-03-21T10:32:12Z
dc.date.available2024-03-21T10:32:12Z
dc.date.issued2018
dc.description.abstractIn the last decades historical handwritten documents have become increasingly available in digital form. Yet, the accessibility to these documents with respect to browsing and searching remained limited as full automatic transcription is often not possible or not sufficiently accurate. This paper proposes a novel reliable approach for template-based keyword spotting in historical handwritten documents. In particular, our framework makes use of different graph representations for segmented word images and a sophisticated matching procedure. Moreover, we extend our method to a spotting ensemble. In an exhaustive experimental evaluation on four widely used benchmark datasets we show that the proposed approach is able to keep up or even outperform several state-of-the-art methods for template- and learning-based keyword spotting.
dc.identifier.doi10.1016/j.patcog.2018.04.001
dc.identifier.issn0031-3203
dc.identifier.urihttps://irf.fhnw.ch/handle/11654/42316
dc.language.isoen
dc.publisherElsevier
dc.relation.ispartofPattern Recognition
dc.subject.ddc330 - Wirtschaft
dc.titleKeyword spotting in historical handwritten documents based on graph matching
dc.type01A - Beitrag in wissenschaftlicher Zeitschrift
dc.volume81
dspace.entity.typePublication
fhnw.InventedHereYes
fhnw.ReviewTypeAnonymous ex ante peer review of a complete publication
fhnw.affiliation.hochschuleHochschule für Wirtschaft FHNWde_CH
fhnw.affiliation.institutInstitut für Wirtschaftsinformatikde_CH
fhnw.openAccessCategoryClosed
fhnw.pagination240-253
fhnw.publicationStatePublished
relation.isAuthorOfPublication52fd615b-a2fc-4ba1-8853-573e1b2a8d4b
relation.isAuthorOfPublicatione83eff11-b557-4fff-985e-1bbb1fd15e0c
relation.isAuthorOfPublicationd761e073-1612-4d22-8521-65c01c19f97a
relation.isAuthorOfPublication.latestForDiscoveryd761e073-1612-4d22-8521-65c01c19f97a
Dateien

Lizenzbündel

Gerade angezeigt 1 - 1 von 1
Kein Vorschaubild vorhanden
Name:
license.txt
Größe:
1.36 KB
Format:
Item-specific license agreed upon to submission
Beschreibung: