Registration of segmented histological images using thin plate splines and belief propagation

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00218861" target="_blank" >RIV/68407700:21230/14:00218861 - isvavai.cz</a>
Result on the web
<a href="http://cmp.felk.cvut.cz/pub/cmp/articles/kybic/Kybic-SPIEMI2014.pdf" target="_blank" >http://cmp.felk.cvut.cz/pub/cmp/articles/kybic/Kybic-SPIEMI2014.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1117/12.2042317" target="_blank" >10.1117/12.2042317</a>

Result language
angličtina
Original language name
Registration of segmented histological images using thin plate splines and belief propagation
Original language description
We register images based on their multiclass segmentations, for cases when correspondence of local features cannot be established. A discrete mutual information is used as a similarity criterion. It is evaluated at a sparse set of location on the interfaces between classes. A thin-plate spline regularization is approximated by pairwise interactions. The problem is cast into a discrete setting and solved efficiently by belief propagation. Further speedup and robustness is provided by a multiresolution framework. Preliminary experiments suggest that our method can provide similar registration quality to standard methods at a fraction of the computational cost.
Czech name
—
Czech description
—

Project
<a href="/en/project/GAP202%2F11%2F0111" target="_blank" >GAP202/11/0111: Automatic analysis of light and electron microscopy neuronal data</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2014
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)