Texture-Based Image Transformations for Improved Deep Learning Classification

Tomas Majtner*, Buda Bajić, Jürgen Herp

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

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
Original languageEnglish
Title of host publication 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
EditorsJoão Manuel Tavares, João Paulo Papa, Manuel González Hidalgo
PublisherSpringer
Publication date2021
Pages207-216
ISBN (Print)978-3-030-93419-4
ISBN (Electronic)978-3-030-93420-0
DOIs
Publication statusPublished - 2021
Event25th Iberoamerican Congress: CIARP 2021 - Porto, Portugal
Duration: 10. May 202113. May 2021

Conference

Conference25th Iberoamerican Congress
Country/TerritoryPortugal
CityPorto
Period10/05/202113/05/2021
SeriesLecture Notes in Computer Science
Volume12702
ISSN0302-9743

Keywords

  • HSV colour model
  • Image processing
  • Texture recognition
  • Transfer learning

Fingerprint

Dive into the research topics of 'Texture-Based Image Transformations for Improved Deep Learning Classification'. Together they form a unique fingerprint.

Cite this