bibtype C - Conference Paper (international conference)
ARLID 0579556
utime 20240402214920.9
mtime 20231215235959.9
SCOPUS 85183540901
DOI 10.1016/j.procs.2023.10.308
title (primary) (eng) Multispectral Texture Benchmark
specification
page_count 10 s.
media_type P
serial
ARLID cav_un_epca*0583149
ISSN 1877-0509
title Procedia Computer Science : Volume 225, 27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023
page_num 3143-3152
publisher
place Amsterdam
name Elsevier
year 2023
keyword textural features
keyword benchmark
keyword representation
keyword multispectral features
author (primary)
ARLID cav_un_auth*0021746
name1 Kříž
name2 P.
country CZ
author
ARLID cav_un_auth*0101093
name1 Haindl
name2 Michal
institution UTIA-B
full_dept (cz) Rozpoznávání obrazu
full_dept Department of Pattern Recognition
department (cz) RO
department RO
full_dept Department of Pattern Recognition
garant A
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source
url http://library.utia.cas.cz/separaty/2023/RO/haindl-0579556.pdf
source
url https://www.sciencedirect.com/science/article/pii/S1877050923014667?via%3Dihub
cas_special
abstract (eng) Dozens of textural features have been published, but their realistic validation for efficient recognition applications still needs to be discovered. Textural features are derived using various approaches. We present a benchmark that can be used to evaluate these features and categorize them based on their information efficiency. We propose how the features can be benchmarked and explain different ways of measuring their properties and performance. Most textural feature-extracting algorithms are only based on information extraction from monospectral images (gray-level). Apart from native multispectral algorithms, we generalize some of these originally monospectral features for hyperspectral textures in our illustrating examples.
action
ARLID cav_un_auth*0459925
name International Conference on Knowledge-Based and Intelligent Information & Engineering Systems 2023 (KES 2023) /27./
dates 20230906
mrcbC20-s 20230908
place Athens
country GR
RIV BD
FORD0 20000
FORD1 20200
FORD2 20205
reportyear 2024
num_of_auth 2
presentation_type PR
inst_support RVO:67985556
permalink https://hdl.handle.net/11104/0349560
cooperation
ARLID cav_un_auth*0401576
name ČVUT Fakulta informačních technologií
institution ČVUT FIT
country CZ
confidential S
mrcbC91 A
mrcbT16-s 0.569
mrcbT16-E Q3
arlyear 2023
mrcbU02 C
mrcbU14 85183540901 SCOPUS
mrcbU24 PUBMED
mrcbU34 WOS
mrcbU63 cav_un_epca*0583149 Procedia Computer Science : Volume 225, 27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023 Elsevier 2023 Amsterdam 3143 3152 1877-0509