Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Deep learning for historical document anlysis
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0002-6756-0147
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Embedded Internet Systems Lab.ORCID iD: 0000-0003-4029-6574
2020 (English)In: Handbook Of Pattern Recognition And Computer Vision / [ed] C. H. Chen, World Scientific, 2020, 6, p. 287-303Chapter in book (Other academic)
Abstract [en]

This chapter gives an overview of the state of the art and recent methods in the area of historical document analysis. Historical documents differ from the ordinary documents due to the presence of different artifacts. Issues such as poor conditions of the documents, texture, noise and degradation, large variability of page layout, page skew, random alignment, variety of fonts, presence of embellishments, variations in spacing between characters, words, lines, paragraphs and margins, overlapping object boundaries, superimposition of information layers, etc bring complexity issues in analyzing them. Most methods currently rely on deep learning based methods, including Convolutional Neural Networks and Long Short-Term Memory Networks. In addition to the overview of the state of the art, this chapter describes a recently introduced idea for the detection of graphical elements in historical documents and an ongoing effort towards the creation of large database.

Place, publisher, year, edition, pages
World Scientific, 2020, 6. p. 287-303
National Category
Computer Sciences
Research subject
Machine Learning
Identifiers
URN: urn:nbn:se:ltu:diva-79071DOI: 10.1142/9789811211072_0015Scopus ID: 2-s2.0-85124541416OAI: oai:DiVA.org:ltu-79071DiVA, id: diva2:1433635
Note

ISBN för värdpublikation: 978-981-121-106-5, 978-981-121-107-2, 978-981-121-108-9

Available from: 2020-06-01 Created: 2020-06-01 Last updated: 2022-11-04Bibliographically approved

Open Access in DiVA

attachment(7375 kB)649 downloads
File information
File name ATTACHMENT01.pdfFile size 7375 kBChecksum SHA-512
9be4ef4d4d1b6a22f7d2fa8384097c6c2fe286f6a85738994f64ae2066ff3aede33c50871f88f85f42b27ba19336ef0a054ea3089e161e65817f2c735cc1f7c5
Type attachmentMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Liwicki, Foteini SimistiraLiwicki, Marcus

Search in DiVA

By author/editor
Liwicki, Foteini SimistiraLiwicki, Marcus
By organisation
Embedded Internet Systems Lab
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 178 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf