Detail publikace

Image Background Noise Impact on Convolutional Neural Network Training

RAJNOHA, M. BURGET, R. POVODA, L.

Originální název

Image Background Noise Impact on Convolutional Neural Network Training

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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.

Klíčová slova

snr; signal to noise ratio; background; noise; training; impact; cnn; convolutional neural networks; small dataset

Autoři

RAJNOHA, M.; BURGET, R.; POVODA, L.

Vydáno

6. 11. 2018

Místo

Moskva

ISBN

978-1-5386-9361-2

Kniha

2018 10th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)

Strany od

168

Strany do

171

Strany počet

4

URL

BibTex

@inproceedings{BUT150877,
  author="Martin {Rajnoha} and Radim {Burget} and Lukáš {Povoda}",
  title="Image Background Noise Impact on Convolutional Neural Network Training",
  booktitle="2018 10th International Congress on Ultra Modern Telecommunications and Control Systems
and Workshops (ICUMT)",
  year="2018",
  pages="168--171",
  address="Moskva",
  doi="10.1109/ICUMT.2018.8631242",
  isbn="978-1-5386-9361-2",
  url="https://ieeexplore.ieee.org/document/8631242"
}