Comparison of DT-CWT based rotation variant and invariant methods on tissue characterization

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Researchers

Research units

  • Tampere University of Technology
  • Tampere University

Abstract

The goal of this study is to compare the effect of rotation variance on dual-tree complex wavelet transform (DT-CWT) based tissue characterization methods. Rotation variant features are especially useful when estimating orientations of textures. On the other hand, since tissues can turn and orient themselves on different directions, in segmentation or classification problems, rotation invariance becomes important. The methods are tested on two texture compositions from the Brodatz texture database and two actual magnetic resonance (MR) images. Results show that, the classification performance is not significantly affected by using rotation variant or invariant methods. On the other hand, regarding segmentation, rotation invariant DT-CWT features performed slightly better compared to rotation variant features.

Details

Original languageEnglish
Title of host publication14th Nordic-Baltic Conference on Biomedical Engineering and Medical Physics, NBC 2008
Publication statusPublished - 1 Dec 2008
MoE publication typeA4 Article in a conference publication
EventNordic-Baltic Conference on Biomedical Engineering and Medical Physics - Riga, Latvia
Duration: 16 Jun 200820 Jun 2008
Conference number: 14

Conference

ConferenceNordic-Baltic Conference on Biomedical Engineering and Medical Physics
Abbreviated titleNBC
CountryLatvia
CityRiga
Period16/06/200820/06/2008

    Research areas

  • DTCWT, texture analysis, tissue characterization

ID: 29135731