Image segmentation based on k-means clustering and energy-transfer proximity
The result's identifiers
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>
Alternative languages
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
—
Classification
Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
IN - Informatics
OECD FORD branch
—
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Lecture Notes in Computer Science
ISSN
0302-9743
e-ISSN
—
Volume of the periodical
2011
Issue of the periodical within the volume
6939
Country of publishing house
DE - GERMANY
Number of pages
10
Pages from-to
567-577
UT code for WoS article
—
EID of the result in the Scopus database
—