Image Background Noise Impact on Convolutional Neural Network Training
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F18%3APU129527" target="_blank" >RIV/00216305:26220/18:PU129527 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/8631242" target="_blank" >https://ieeexplore.ieee.org/document/8631242</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/ICUMT.2018.8631242" target="_blank" >10.1109/ICUMT.2018.8631242</a>
Alternative languages
Result language
angličtina
Original language name
Image Background Noise Impact on Convolutional Neural Network Training
Original language description
Small size dataset is general issue that we may encounter when training neural networks for analysis of image data. There are many cases when networks can not start training even with data augmentation. This paper proposes a new method how to allow training of image classification even when traditional approaches fail. It presents an experiment, which shows that subtraction of redundant background from images can significantly improve convergence of neural network training. Improvement is not in accuracy matter but it means that neural network is able to train and to start convergence. For experimental evaluation, person binary classification was used and compared to experiments, where the background was removed.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20203 - Telecommunications
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2018 10th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)
ISBN
978-1-5386-9361-2
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
168-171
Publisher name
Neuveden
Place of publication
Moskva
Event location
Moskva
Event date
Nov 5, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000459238500045