kth.sePublications
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
Shearlets as feature extractor for semantic edge detection: the model-based and data-driven realm
Tech Univ Berlin, Inst Math, D-10623 Berlin, Germany..
Tech Univ Berlin, Inst Math, D-10623 Berlin, Germany.;Tech Univ Berlin, Fak Elektrotech & Informat, D-10587 Berlin, Germany.;Univ Tromso, Dept Phys & Technol, Tromso, Norway..
KTH, School of Engineering Sciences (SCI), Mathematics (Dept.), Mathematics (Div.).ORCID iD: 0000-0002-1118-6483
2020 (English)In: Proceedings of the Royal Society. Mathematical, Physical and Engineering Sciences, ISSN 1364-5021, E-ISSN 1471-2946, Vol. 476, no 2243, article id 20190841Article in journal (Refereed) Published
Abstract [en]

Semantic edge detection has recently gained a lot of attention as an image-processing task, mainly because of its wide range of real-world applications. This is based on the fact that edges in images contain most of the semantic information. Semantic edge detection involves two tasks, namely pure edge detection and edge classification. Those are in fact fundamentally distinct in terms of the level of abstraction that each task requires. This fact is known as the distracted supervision paradox and limits the possible performance of a supervised model in semantic edge detection. In this work, we will present a novel hybrid method that is based on a combination of the model-based concept of shearlets, which provides probably optimally sparse approximations of a model class of images, and the data-driven method of a suitably designed convolutional neural network. We show that it avoids the distracted supervision paradox and achieves high performance in semantic edge detection. In addition, our approach requires significantly fewer parameters than a pure data-driven approach. Finally, we present several applications such as tomographic reconstruction and show that our approach significantly outperforms former methods, thereby also indicating the value of such hybrid methods for biomedical imaging.

Place, publisher, year, edition, pages
The Royal Society , 2020. Vol. 476, no 2243, article id 20190841
Keywords [en]
multiscale geometric analysis, harmonic analysis, deep learning, feature extraction
National Category
Mathematics
Identifiers
URN: urn:nbn:se:kth:diva-288430DOI: 10.1098/rspa.2019.0841ISI: 000595762600001PubMedID: 33363436Scopus ID: 2-s2.0-85097925677OAI: oai:DiVA.org:kth-288430DiVA, id: diva2:1530829
Note

QC 20210224

Available from: 2021-02-24 Created: 2021-02-24 Last updated: 2022-06-25Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Öktem, Ozan

Search in DiVA

By author/editor
Öktem, Ozan
By organisation
Mathematics (Div.)
In the same journal
Proceedings of the Royal Society. Mathematical, Physical and Engineering Sciences
Mathematics

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 43 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