Spatial Pattern Templates for Recognition of Objects with Regular Structure

Radim Tylecek, Radim Sára

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

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 specic 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 ecient 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 manually
designed detectors for specic terminal objects.
Original languageEnglish
Title of host publicationPattern Recognition
Subtitle of host publication35th German Conference, GCPR 2013, Saarbrücken, Germany, September 3-6, 2013. Proceedings
PublisherSpringer Berlin Heidelberg
Number of pages11
ISBN (Electronic)978-3-642-40602-7
ISBN (Print)978-3-642-40601-0
Publication statusPublished - 2013

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
ISSN (Print)0302-9743


Dive into the research topics of 'Spatial Pattern Templates for Recognition of Objects with Regular Structure'. Together they form a unique fingerprint.

Cite this