Image segmentation based on k-means clustering and energy-transfer proximity

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F11%3A86080950" target="_blank" >RIV/61989100:27240/11:86080950 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1007/978-3-642-24031-7_57" target="_blank" >http://dx.doi.org/10.1007/978-3-642-24031-7_57</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-24031-7_57" target="_blank" >10.1007/978-3-642-24031-7_57</a>

Result language
angličtina
Original language name
Image segmentation based on k-means clustering and energy-transfer proximity
Original language description
In image segmentation, measuring the distances is an important problem. The distance should tell whether two image points belong to a single or, respectively, to two different image segments. Although the Euclidean distance is often used, the disadvantage is that it does not take into account anything what happens between the points whose distance is measured. In this paper, we introduce a new quantity called the energy-transfer proximity that reflects the distances between the points on the image manifold and that can be used in the image-segmentation algorithms. In the paper, we focus especially on its use in the algorithm that is based on k-means clustering. The needed theory as well as some experimental results are presented.
Czech name
—
Czech description
—

Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
IN - Informatics
OECD FORD branch
—

Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)