Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Identifying cross-depicted historical motifs
Document Image and Voice Analysis Group (DIVA), University of Fribourg, Switzerland.
Document Image and Voice Analysis Group (DIVA), University of Fribourg, Switzerland.
Staatsbibliothek zu Berlin, Preußischer Kulturbesitz, Berlin, Germany.
Document Image and Voice Analysis Group (DIVA), University of Fribourg, Switzerland.
Visa övriga samt affilieringar
2018 (Engelska)Ingår i: Proceedings of International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, IEEE, 2018, s. 333-338, artikel-id 8583783Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Cross-depiction is the problem of identifying the same object even when it is depicted in a variety of manners.This is a common problem in handwritten historical document image analysis, for instance when the same letter or motif is depicted in several different ways. It is a simple task for humans yet conventional computer vision methods struggle to cope with it. In this paper we address this problem using state-of-the-art deep learning techniques on a dataset of historical watermarks containing images created with different methods of reproduction, such as hand tracing, rubbing, and radiography.To study the robustness of deep learning based approaches to the cross-depiction problem, we measure their performance on two different tasks: Classification and similarity rankings. For the former we achieve a classification accuracy of 96 % using deep convolutional neural networks. For the latter we have a false positive rate at 95% recall of 0.11. These results outperform state-of-the-art methods by a significant margin

Ort, förlag, år, upplaga, sidor
IEEE, 2018. s. 333-338, artikel-id 8583783
Serie
International Conference on Handwriting Recognition, ISSN 2167-6445
Nyckelord [en]
convolutional neural network, cross-depiction, deep learning, machine learning, watermarks
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
Maskininlärning
Identifikatorer
URN: urn:nbn:se:ltu:diva-72981DOI: 10.1109/ICFHR-2018.2018.00065ISI: 000454983200056Scopus ID: 2-s2.0-85060032898ISBN: 978-1-5386-5875-8 (tryckt)OAI: oai:DiVA.org:ltu-72981DiVA, id: diva2:1290886
Konferens
16th International Conference on Frontiers in Handwriting Recognition, ICFHR 2018, 5- August 2018, Niagara Fall, United States
Tillgänglig från: 2019-02-21 Skapad: 2019-02-21 Senast uppdaterad: 2019-03-11Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Personposter BETA

Liwicki, Marcus

Sök vidare i DiVA

Av författaren/redaktören
Liwicki, Marcus
Av organisationen
EISLAB
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 25 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf