Spatial Pattern Templates for Recognition of Objects with Regular Structure

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00212539" target="_blank" >RIV/68407700:21230/13:00212539 - isvavai.cz</a>
Result on the web
<a href="http://cmp.felk.cvut.cz/~tylecr1/papers/Tylecek-GCPR2013.pdf" target="_blank" >http://cmp.felk.cvut.cz/~tylecr1/papers/Tylecek-GCPR2013.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-642-40602-7_39" target="_blank" >10.1007/978-3-642-40602-7_39</a>

Result language
angličtina
Original language name
Spatial Pattern Templates for Recognition of Objects with Regular Structure
Original language description
We propose a method for semantic parsing of images with regular structure. The structured objects are modeled in a densely connected CRF. The paper describes how to embody specific spatial relations in a representation called Spatial Pattern Templates(SPT), which allows us to capture regularity constraints of alignment and equal spacing in pairwise and ternary potentials. Assuming the input image is pre-segmented to salient regions the SPT describe which segments could interact in the structured graphical model. The model parameters are learnt to describe the formal language of semantic labelings. Given an input image, a consistent labeling over its segments linked in the CRF is recognized as a word from this language. The CRF framework allows us to apply efficient algorithms for both recognition and learning. We demonstrate the approach on the problem of facade image parsing and show that results comparable with state of the art methods are achieved without introducing additional manu
Czech name
—
Czech description
—

Project
<a href="/en/project/GAP103%2F12%2F1578" target="_blank" >GAP103/12/1578: Structural and Semantic Modeling of Architecture as a Digital Image Interpretation Problem</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

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

Article name in the collection
GCPR 2013: Proceedings of 35th German Conference on Pattern Recognition
ISBN
978-3-642-40601-0
ISSN
0302-9743
e-ISSN
—
Number of pages
11
Pages from-to
364-374
Publisher name
Springer
Place of publication
Heidelberg
Event location
Saarbruecken
Event date
Sep 3, 2013
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000329236100039

Similar results(10)