Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Classifying RGB Images with multi-colour Persistent Homology
Linköpings universitet, Matematiska institutionen.
2019 (engelsk)Independent thesis Basic level (degree of Bachelor), 10,5 poäng / 16 hpOppgave
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.

sted, utgiver, år, opplag, sider
2019. , s. 99
Emneord [en]
Persistent Homology, Applied Algebraic Topology, Topological Data Analysis, Image Classification, CUB-200-2011
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-157641ISRN: LiTH-MAT-EX--2019/01--SEOAI: oai:DiVA.org:liu-157641DiVA, id: diva2:1326229
Fag / kurs
Mathematics
Presentation
2019-06-13, Hopningspunkten, B Building, Linköping University, 581 83 LINKÖPING, 09:00 (engelsk)
Veileder
Examiner
Tilgjengelig fra: 2019-06-19 Laget: 2019-06-17 Sist oppdatert: 2019-06-19bibliografisk kontrollert

Open Access i DiVA

fulltext(822 kB)61 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 822 kBChecksum SHA-512
ce2dbbd40346079a0c89f6161aee45632ef734c97d65ce0694dcc62f16157851d71d006f9851fcd3a7031a50c63ff1c2e11b259f0054334acd44a16a4d084dd2
Type fulltextMimetype application/pdf

Søk i DiVA

Av forfatter/redaktør
Byttner, Wolf
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 61 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 566 treff
RefereraExporteraLink to record
Permanent link

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