Novel edge detection scheme in the trinion space for use in medical images with multiple components
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62690094%3A18450%2F16%3A50005012" target="_blank" >RIV/62690094:18450/16:50005012 - isvavai.cz</a>
Výsledek na webu
<a href="http://dx.doi.org/10.1007/978-3-319-45246-3_22" target="_blank" >http://dx.doi.org/10.1007/978-3-319-45246-3_22</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-319-45246-3_22" target="_blank" >10.1007/978-3-319-45246-3_22</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Novel edge detection scheme in the trinion space for use in medical images with multiple components
Popis výsledku v původním jazyce
Very recently we proposed a promising scheme for tissue classification of multi-parametric magnetic resonance images (MP-MRI) of the brain based on signal analysis in higher dimensional vector spaces. The method treats MP-MR images as colors represented holistically in three (trinion) or four (quaternion) algebraic spaces. Compared to the well known quaternions, the recently proposed three component trinions are more efficient in representation of images with three channels and the respective Fourier transforms allow visualization of their wavenumber spectra as a whole. The current study discusses an edge detection scheme based on statistical metrics derived from locally computed trinion Fourier transforms for use in robust edge detection of MP-MR images and other color medical images. Performance of the proposed scheme is compared against a quaternion formulation and with another vectorial approach. Application of the method is shown in edge detection of various color test images and scenes with different degrees of difficulty. Discussion and preliminary results on the application of the proposed scheme on MP-MR images of brain scans of patients treated for glioblastoma multiforme (GBM) have also been included.
Název v anglickém jazyce
Novel edge detection scheme in the trinion space for use in medical images with multiple components
Popis výsledku anglicky
Very recently we proposed a promising scheme for tissue classification of multi-parametric magnetic resonance images (MP-MRI) of the brain based on signal analysis in higher dimensional vector spaces. The method treats MP-MR images as colors represented holistically in three (trinion) or four (quaternion) algebraic spaces. Compared to the well known quaternions, the recently proposed three component trinions are more efficient in representation of images with three channels and the respective Fourier transforms allow visualization of their wavenumber spectra as a whole. The current study discusses an edge detection scheme based on statistical metrics derived from locally computed trinion Fourier transforms for use in robust edge detection of MP-MR images and other color medical images. Performance of the proposed scheme is compared against a quaternion formulation and with another vectorial approach. Application of the method is shown in edge detection of various color test images and scenes with different degrees of difficulty. Discussion and preliminary results on the application of the proposed scheme on MP-MR images of brain scans of patients treated for glioblastoma multiforme (GBM) have also been included.
Klasifikace
Druh
J<sub>x</sub> - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)
CEP obor
JC - Počítačový hardware a software
OECD FORD obor
—
Návaznosti výsledku
Projekt
—
Návaznosti
S - Specificky vyzkum na vysokych skolach
Ostatní
Rok uplatnění
2016
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
Computational collective intelligence (ICCCI 2016)
ISSN
0302-9743
e-ISSN
—
Svazek periodika
9876
Číslo periodika v rámci svazku
2016
Stát vydavatele periodika
DE - Spolková republika Německo
Počet stran výsledku
11
Strana od-do
231-241
Kód UT WoS článku
—
EID výsledku v databázi Scopus
2-s2.0-84989278733