bibtype C - Conference Paper (international conference)
ARLID 0463638
utime 20240103212724.0
mtime 20161010235959.9
SCOPUS 85006812184
WOS 000390782002026
DOI 10.1109/ICIP.2016.7532721
title (primary) (eng) Texture fidelity criterion
specification
page_count 5 s.
media_type E
serial
ARLID cav_un_epca*0464937
ISBN 978-1-4673-9961-6
ISSN Proceedings of the 2016 IEEE International Conference on Image Processing
title Proceedings of the 2016 IEEE International Conference on Image Processing
publisher
place Piscataway
name IEEE
year 2016
keyword Image texture
keyword texture fidelity
keyword visual quality criterion
keyword Markovian texture model
author (primary)
ARLID cav_un_auth*0287263
full_dept (cz) Rozpoznávání obrazu
full_dept (eng) Department of Pattern Recognition
department (cz) RO
department (eng) RO
full_dept Department of Pattern Recognition
name1 Kudělka
name2 Miloš
institution UTIA-B
country CZ
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0101093
full_dept (cz) Rozpoznávání obrazu
full_dept Department of Pattern Recognition
department (cz) RO
department RO
full_dept Department of Pattern Recognition
name1 Haindl
name2 Michal
institution UTIA-B
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source
url http://library.utia.cas.cz/separaty/2016/RO/haindl-0463638.pdf
cas_special
project
ARLID cav_un_auth*0303439
project_id GA14-10911S
agency GA ČR
country CZ
abstract (eng) Visual texture fidelity evaluation is important but still unsolved problem. Evaluation of how well various texture models conform with human visual perception of their original measured pattern is required not only for assessing the visual dissimilarities between a model output and the original measured texture, but also for optimal settings of model parameters, for fair comparison of distinct models, or visual scene understanding. We propose a novel texture fidelity criterion based on the fully multi-spectral generative underlying Markovian texture model, which correlates well with human texture quality ranking verified on the texture fidelity benchmark.
action
ARLID cav_un_auth*0334434
name 2016 IEEE International Conference on Image Processing (ICIP)
dates 25.09.2016-28.09.2016
place Phoenix, AZ
country US
RIV BD
reportyear 2017
num_of_auth 2
mrcbC52 4 A hod 4ah 20231122141919.2
presentation_type PO
inst_support RVO:67985556
permalink http://hdl.handle.net/11104/0263673
mrcbC61 1
mrcbC64 1 Department of Pattern Recognition UTIA-B 10201 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
confidential S
mrcbC86 n.a. Proceedings Paper Engineering Electrical Electronic|Imaging Science Photographic Technology
arlyear 2016
mrcbTft \nSoubory v repozitáři: haindl-0463638.pdf
mrcbU14 85006812184 SCOPUS
mrcbU34 000390782002026 WOS
mrcbU63 cav_un_epca*0464937 Proceedings of the 2016 IEEE International Conference on Image Processing 978-1-4673-9961-6 2381-8549 Piscataway IEEE 2016