Journal article icon

Journal article

Enhancement of damaged-image prediction through Cahn–Hilliard image inpainting

Abstract:

We assess the benefit of including an image inpainting filter before passing damaged images into a classification neural network. We employ an appropriately modified Cahn–Hilliard equation as an image inpainting filter which is solved numerically with a finite-volume scheme exhibiting reduced computational cost and the properties of energy stability and boundedness. The benchmark dataset employed is Modified National Institute of Standards and Technology (MNIST) dataset, which consists of bin...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1098/rsos.201294

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Role:
Author
More from this funder
Name:
European Commission
Grant:
883363
Publisher:
Royal Society
Journal:
Royal Society Open Science More from this journal
Volume:
8
Issue:
5
Article number:
201294
Publication date:
2021-05-19
Acceptance date:
2021-04-12
DOI:
EISSN:
2054-5703
Language:
English
Keywords:
Pubs id:
1120905
Local pid:
pubs:1120905
Deposit date:
2021-04-21

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP