Unsupervised Surface Reflectance Field Multi-segmenter

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F15%3A00447050" target="_blank" >RIV/67985556:_____/15:00447050 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-23192-1_22" target="_blank" >http://dx.doi.org/10.1007/978-3-319-23192-1_22</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-23192-1_22" target="_blank" >10.1007/978-3-319-23192-1_22</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Unsupervised Surface Reflectance Field Multi-segmenter

Popis výsledku v původním jazyce

An unsupervised, illumination invariant, multi-spectral, mul/-ti-resolution, multiple-segmenter for textured images with unknown number of classes is presented. The segmenter is based on a weighted combination of several unsupervised segmentation results, each in different resolution, using the modified sum rule. Multi-spectral textured image mosaics are locally represented by eight causal directional multi-spectral random field models recursively evaluated for each pixel. The single-resolution segmentation part of the algorithm is based on the underlying Gaussian mixture model and starts with an over segmented initial estimation which is adaptively modified until the optimal number of homogeneous texture segments is reached. The performance of the presented method is extensively tested on the Prague segmentation benchmark both on the surface reflectance field textures as well as on the static colour textures using the commonest segmentation criteria and compares favourably with severa

Název v anglickém jazyce

Unsupervised Surface Reflectance Field Multi-segmenter

Popis výsledku anglicky

An unsupervised, illumination invariant, multi-spectral, mul/-ti-resolution, multiple-segmenter for textured images with unknown number of classes is presented. The segmenter is based on a weighted combination of several unsupervised segmentation results, each in different resolution, using the modified sum rule. Multi-spectral textured image mosaics are locally represented by eight causal directional multi-spectral random field models recursively evaluated for each pixel. The single-resolution segmentation part of the algorithm is based on the underlying Gaussian mixture model and starts with an over segmented initial estimation which is adaptively modified until the optimal number of homogeneous texture segments is reached. The performance of the presented method is extensively tested on the Prague segmentation benchmark both on the surface reflectance field textures as well as on the static colour textures using the commonest segmentation criteria and compares favourably with severa

Druh

D - Stať ve sborníku

CEP obor

BD - Teorie informace

OECD FORD obor

—

Projekt

<a href="/cs/project/GA14-10911S" target="_blank" >GA14-10911S: Matematické modelování vzhledu povrchových materiálů</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Computer Analysis of Images and Patterns - CAIP 2015

ISBN

978-3-319-23192-1

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

13

Strana od-do

261-273

Název nakladatele

Springer International Publishing

Místo vydání

Switzerland

Místo konání akce

Valletta

Datum konání akce

2. 9. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000364705500022