Image segmentation using iterated graph cuts with residual graph

Result code in 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>
Result on the web
<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>

Result language
angličtina
Original language name
Image segmentation using iterated graph cuts with residual graph
Original language description
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.
Czech name
—
Czech description
—

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)