bibtype C - Conference Paper (international conference)
ARLID 0571255
utime 20240402213835.2
mtime 20230428235959.9
SCOPUS 85160816520
DOI 10.1007/978-3-031-31438-4_8
title (primary) (eng) Impact of Image Blur on Classification and Augmentation of Deep Convolutional Networks
specification
page_count 10 s.
media_type P
serial
ARLID cav_un_epca*0571254
ISBN 978-3-031-31437-7
title Image Analysis: 23rd Scandinavian Conference, SCIA 2023
page_num 108-117
publisher
place Cham
name Springer
year 2023
editor
name1 Gade
name2 R.
keyword Image recognition
keyword Blur
keyword Augmentation of the training set
keyword Convolutional neural network
author (primary)
ARLID cav_un_auth*0377447
name1 Lébl
name2 Matěj
institution UTIA-B
full_dept (cz) Zpracování obrazové informace
full_dept (eng) Department of Image Processing
department (cz) ZOI
department (eng) ZOI
full_dept Department of Image Processing
country CZ
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0101209
name1 Šroubek
name2 Filip
institution UTIA-B
full_dept (cz) Zpracování obrazové informace
full_dept Department of Image Processing
department (cz) ZOI
department ZOI
full_dept Department of Image Processing
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
author
ARLID cav_un_auth*0101087
name1 Flusser
name2 Jan
institution UTIA-B
full_dept (cz) Zpracování obrazové informace
full_dept Department of Image Processing
department (cz) ZOI
department ZOI
full_dept Department of Image Processing
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source
url http://library.utia.cas.cz/separaty/2023/ZOI/lebl-0571255.pdf
cas_special
project
project_id GA21-03921S
agency GA ČR
ARLID cav_un_auth*0412209
abstract (eng) Blur is a common phenomenon in image acquisition that negatively influences the recognition rate of most classifiers. This paper studies the influence of image blurring of various types and sizes on the recognition rate achieved by a deep convolutional network. We confirm that the blur significantly decreases the performance if the network has been trained on clear images only. When the training set is augmented with blurred samples, the recognition rate becomes sufficiently high even if the blur in query images is of different size than the blur used for training. However, this is mostly not true if query images contain blur of a different type from the one used for training.
action
ARLID cav_un_auth*0449343
name Scandinavian Conference on Image Analysis 2023 /23./
dates 20230418
mrcbC20-s 20230421
place Levi
country FI
RIV JD
FORD0 20000
FORD1 20200
FORD2 20206
reportyear 2024
num_of_auth 3
presentation_type PO
inst_support RVO:67985556
permalink https://hdl.handle.net/11104/0342934
confidential S
arlyear 2023
mrcbU14 85160816520 SCOPUS
mrcbU24 PUBMED
mrcbU34 WOS
mrcbU63 cav_un_epca*0571254 Image Analysis: 23rd Scandinavian Conference, SCIA 2023 978-3-031-31437-7 108 117 Cham Springer 2023 Lecture notes on computer science LNCS 13886
mrcbU67 Gade R. 340