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
Classifying RGB Images with multi-colour Persistent Homology
Linköping University, Department of Mathematics.
2019 (English)Independent thesis Basic level (degree of Bachelor), 10,5 credits / 16 HE creditsStudent thesis
Abstract [en]

In Image Classification, pictures of the same type of object can have very different pixel values. Traditional norm-based metrics therefore fail to identify objectsin the same category. Topology is a branch of mathematics that deals with homeomorphic spaces, by discarding length. With topology, we can discover patterns in the image that are invariant to rotation, translation and warping.

Persistent Homology is a new approach in Applied Topology that studies the presence of continuous regions and holes in an image. It has been used successfully for image segmentation and classification [12]. However, current approaches in image classification require a grayscale image to generate the persistence modules. This means information encoded in colour channels is lost.

This thesis investigates whether the information in the red, green and blue colour channels of an RGB image hold additional information that could help algorithms classify pictures. We apply two recent methods, one by Adams [2] and the other by Hofer [25], on the CUB-200-2011 birds dataset [40] andfind that Hofer’s method produces significant results. Additionally, a modified method based on Hofer that uses the RGB colour channels produces significantly better results than the baseline, with over 48 % of images correctly classified, compared to 44 % and with a more significant improvement at lower resolutions.This indicates that colour channels do provide significant new information and generating one persistence module per colour channel is a viable approach to RGB image classification.

Place, publisher, year, edition, pages
2019. , p. 99
Keywords [en]
Persistent Homology, Applied Algebraic Topology, Topological Data Analysis, Image Classification, CUB-200-2011
National Category
Mathematics
Identifiers
URN: urn:nbn:se:liu:diva-157641ISRN: LiTH-MAT-EX--2019/01--SEOAI: oai:DiVA.org:liu-157641DiVA, id: diva2:1326229
Subject / course
Mathematics
Presentation
2019-06-13, Hopningspunkten, B Building, Linköping University, 581 83 LINKÖPING, 09:00 (English)
Supervisors
Examiners
Available from: 2019-06-19 Created: 2019-06-17 Last updated: 2019-06-19Bibliographically approved

Open Access in DiVA

fulltext(822 kB)59 downloads
File information
File name FULLTEXT01.pdfFile size 822 kBChecksum SHA-512
ce2dbbd40346079a0c89f6161aee45632ef734c97d65ce0694dcc62f16157851d71d006f9851fcd3a7031a50c63ff1c2e11b259f0054334acd44a16a4d084dd2
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Byttner, Wolf
By organisation
Department of Mathematics
Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 59 downloads
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

urn-nbn

Altmetric score

urn-nbn
Total: 564 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