Texture-Based Image Transformations for Improved Deep Learning Classification

Tomas Majtner*, Buda Bajić, Jürgen Herp

*Kontaktforfatter for dette arbejde

Publikation: Kapitel i bog/rapport/konference-proceedingKonferencebidrag i proceedingsForskningpeer review

Abstrakt

In this paper, we examine the effect of texture-based image transformation on classification performance. A novel combination of mathematical morphology operations and contrast-limited adaptive histogram equalization is proposed to enhance image textural features. The suggested operations are applied in HSV colour space, where the intensity component is separated from the colour information. Two publicly available, texture-oriented datasets are used for evaluation in this study. The KTH-TIPS2-b dataset is utilised to illustrate the general effectiveness and applicability of the proposed solution on standardized texture images. The Virus Texture dataset is subsequently used to demonstrate a statistically significant classification improvement in a particular biomedical image recognition task
OriginalsprogEngelsk
Titel Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2021 : 25th Iberoamerican Congress, CIARP 2021, Porto, Portugal, May 10–13, 2021, Revised Selected Papers
RedaktørerJoão Manuel Tavares, João Paulo Papa, Manuel González Hidalgo
ForlagSpringer
Publikationsdato2021
Sider207-216
ISBN (Trykt)978-3-030-93419-4
ISBN (Elektronisk)978-3-030-93420-0
DOI
StatusUdgivet - 2021
Begivenhed25th Iberoamerican Congress: CIARP 2021 - Porto, Portugal
Varighed: 10. maj 202113. maj 2021

Konference

Konference25th Iberoamerican Congress
Land/OmrådePortugal
ByPorto
Periode10/05/202113/05/2021
NavnLecture Notes in Computer Science
Vol/bind12702
ISSN0302-9743

Fingeraftryk

Dyk ned i forskningsemnerne om 'Texture-Based Image Transformations for Improved Deep Learning Classification'. Sammen danner de et unikt fingeraftryk.

Citationsformater