bibtype C - Conference Paper (international conference)
ARLID 0447050
utime 20240103210528.5
mtime 20150922235959.9
WOS 000364705500022
SCOPUS 84945931089
DOI 10.1007/978-3-319-23192-1_22
title (primary) (eng) Unsupervised Surface Reflectance Field Multi-segmenter
specification
page_count 13 s.
media_type P
serial
ARLID cav_un_epca*0447047
ISBN 978-3-319-23192-1
ISSN 0302-9743
title Computer Analysis of Images and Patterns - CAIP 2015
part_num I
part_title 9256
page_num 261-273
publisher
place Switzerland
name Springer International Publishing
year 2015
editor
name1 Azzopardi
name2 George
editor
name1 Petkov
name2 Nicolai
keyword Unsupervised image segmentation
keyword Textural features
keyword Illumination invariants
keyword Surface reflectance field
keyword Bidirectional texture function
author (primary)
ARLID cav_un_auth*0101093
name1 Haindl
name2 Michal
full_dept (cz) Rozpoznávání obrazu
full_dept (eng) Department of Pattern Recognition
department (cz) RO
department (eng) RO
institution UTIA-B
full_dept Department of Pattern Recognition
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0101165
name1 Mikeš
name2 Stanislav
full_dept (cz) Rozpoznávání obrazu
full_dept Department of Pattern Recognition
department (cz) RO
department RO
institution UTIA-B
full_dept Department of Pattern Recognition
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0021088
name1 Kudo
name2 M.
country JP
source
url http://library.utia.cas.cz/separaty/2015/RO/haindl-0447050.pdf
cas_special
project
project_id GA14-10911S
agency GA ČR
country CZ
ARLID cav_un_auth*0303439
abstract (eng) An unsupervised, illumination invariant, multi-spectral, mul/-ti-resolution, multiple-segmenter for textured images with unknown number of classes is presented. The segmenter is based on a weighted combination of several unsupervised segmentation results, each in different resolution, using the modified sum rule. Multi-spectral textured image mosaics are locally represented by eight causal directional multi-spectral random field models recursively evaluated for each pixel. The single-resolution segmentation part of the algorithm is based on the underlying Gaussian mixture model and starts with an over segmented initial estimation which is adaptively modified until the optimal number of homogeneous texture segments is reached. The performance of the presented method is extensively tested on the Prague segmentation benchmark both on the surface reflectance field textures as well as on the static colour textures using the commonest segmentation criteria and compares favourably with several leading alternative image segmentation methods.
action
ARLID cav_un_auth*0319317
name 16th International Conference on Computer Analysis of Images and Patterns
place Valletta
dates 02.09.2015-04.09.2015
country MT
reportyear 2016
RIV BD
num_of_auth 3
presentation_type PO
inst_support RVO:67985556
permalink http://hdl.handle.net/11104/0249426
cooperation
ARLID cav_un_auth*0299017
name Hokkaido University
country JP
confidential S
mrcbT16-s 0.329
mrcbT16-4 Q2
mrcbT16-E Q2
arlyear 2015
mrcbU14 84945931089 SCOPUS
mrcbU34 000364705500022 WOS
mrcbU63 cav_un_epca*0447047 Computer Analysis of Images and Patterns - CAIP 2015 I 978-3-319-23192-1 0302-9743 261 273 Computer Analysis of Images and Patterns - CAIP 2015 Switzerland Springer International Publishing 2015 Lecture Notes in Computer Science 9256
mrcbU67 Azzopardi George 340
mrcbU67 Petkov Nicolai 340