bibtype C - Conference Paper (international conference)
ARLID 0471593
utime 20240103213656.5
mtime 20170224235959.9
SCOPUS 85013468585
WOS 000418399200011
DOI 10.1007/978-3-319-52277-7_11
title (primary) (eng) Scale Sensitivity of Textural Features
specification
page_count 8 s.
media_type P
serial
ARLID cav_un_epca*0471591
ISBN 978-3-319-52276-0
title Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: 21st Iberoamerican Congress, CIARP 2016
page_num 84-92
publisher
place Cham
name Springer International Publishing
year 2017
editor
name1 Beltran-Castanon
name2 C.
editor
name1 Nystrom
name2 I.
editor
name1 Famili
name2 F.
keyword Textural features
keyword texture scale recognition sensitivity
keyword surface material recognition
keyword Markovian illumination invariant features
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*0213290
name1 Vácha
name2 Pavel
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.
source
url http://library.utia.cas.cz/separaty/2017/RO/haindl-0471593.pdf
cas_special
project
ARLID cav_un_auth*0303439
project_id GA14-10911S
agency GA ČR
country CZ
abstract (eng) Prevailing surface material recognition methods are based on textural features but most of these features are very sensitive to scale variations and the recognition accuracy significantly declines with scale incompatibility between visual material measurements used for learning and unknown materials to be recognized. This effect of mutual incompatibility between training and testing visual material measurements scale on the recognition accuracy is investigated for leading textural features and verified on a wood database, which contains veneers from sixty-six varied European and exotic wood species. The results show that the presented textural features, which are illumination invariants extracted from a generative multispectral Markovian texture representation, outperform the most common alternatives, such as Local Binary Patterns, Gabor features, or histogram-based approaches.
action
ARLID cav_un_auth*0343392
name CIARP 2016 - 21st Iberoamerican Congress 2016
dates 20161108
mrcbC20-s 20161111
place Lima
country PE
RIV BD
FORD0 10000
FORD1 10200
FORD2 10201
reportyear 2018
num_of_auth 2
presentation_type PR
inst_support RVO:67985556
permalink http://hdl.handle.net/11104/0271350
confidential S
mrcbC86 3+4 Proceedings Paper Computer Science Artificial Intelligence|Computer Science Theory Methods|Imaging Science Photographic Technology
mrcbC86 3+4 Proceedings Paper Computer Science Artificial Intelligence|Computer Science Theory Methods|Imaging Science Photographic Technology
mrcbC86 3+4 Proceedings Paper Computer Science Artificial Intelligence|Computer Science Theory Methods|Imaging Science Photographic Technology
arlyear 2017
mrcbU14 85013468585 SCOPUS
mrcbU24 PUBMED
mrcbU34 000418399200011 WOS
mrcbU63 cav_un_epca*0471591 Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: 21st Iberoamerican Congress, CIARP 2016 Springer International Publishing 2017 Cham 84 92 978-3-319-52276-0 Lecture Notes in Computer Science 10125
mrcbU67 340 Beltran-Castanon C.
mrcbU67 340 Nystrom I.
mrcbU67 340 Famili F.