Image segmentation using iterated graph cuts with residual graph

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F13%3A86088519" target="_blank" >RIV/61989100:27240/13:86088519 - isvavai.cz</a>

Výsledek na webu

<a href="http://link.springer.com/chapter/10.1007%2F978-3-642-41914-0_23" target="_blank" >http://link.springer.com/chapter/10.1007%2F978-3-642-41914-0_23</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-642-41914-0_23" target="_blank" >10.1007/978-3-642-41914-0_23</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Image segmentation using iterated graph cuts with residual graph

Popis výsledku v původním jazyce

In this paper, we present a new image segmentation method using iterated graph cuts. In the standard graph cuts method, the data term is computed on the basis of the brightness/color distribution of object and background. In this case, some background regions with the brightness/color similar to the object may be incorrectly labeled as an object. We try to overcome this drawback by introducing a new data term that reduces the importance of brightness/color distribution. This reduction is realised by a new part that uses data from a residual graph that remains after performing the max-flow algorithm. According to the residual weights, we change the weights of t-links in the graph and find a new cut on this graph. This operation makes our method iterative. The results and comparison with other graph cuts methods are presented.

Název v anglickém jazyce

Image segmentation using iterated graph cuts with residual graph

Popis výsledku anglicky

In this paper, we present a new image segmentation method using iterated graph cuts. In the standard graph cuts method, the data term is computed on the basis of the brightness/color distribution of object and background. In this case, some background regions with the brightness/color similar to the object may be incorrectly labeled as an object. We try to overcome this drawback by introducing a new data term that reduces the importance of brightness/color distribution. This reduction is realised by a new part that uses data from a residual graph that remains after performing the max-flow algorithm. According to the residual weights, we change the weights of t-links in the graph and find a new cut on this graph. This operation makes our method iterative. The results and comparison with other graph cuts methods are presented.

Druh

D - Stať ve sborníku

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2013

Kód důvěrnosti údajů

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

Název statě ve sborníku

Lecture Notes in Computer Science. Volume 8033

ISBN

978-3-642-41913-3

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

10

Strana od-do

228-237

Název nakladatele

Springer Verlag

Místo vydání

London

Místo konání akce

Rethymnon

Datum konání akce

29. 7. 2013

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—