Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications

Dark Background Image-denosing Based on KPCA Method

Authors
Yiran Xiao, Xiaolin Tian
Corresponding Author
Yiran Xiao
Available Online January 2017.
DOI
10.2991/icmmita-16.2016.208How to use a DOI?
Keywords
Image-denosing; Principle Component Analysis; Kernel Function; Dark background image
Abstract

In this paper, a dark background image-denosing method based on KPCA is discussed. First of all, the analysis of KPCA features is used to extract features from the training samples, and then discards the features which had small variance to form the feature space. Second, for reducing the noise, the principal components analysis is used to restructure the pattern for the smallest error in the feature space. Also, the value of parameter in kernel function is adjusted to fit the dark-background images. According to the testing results, this method is effective and operational.

Copyright
© 2017, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications
Series
Advances in Computer Science Research
Publication Date
January 2017
ISBN
978-94-6252-285-5
ISSN
2352-538X
DOI
10.2991/icmmita-16.2016.208How to use a DOI?
Copyright
© 2017, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - Yiran Xiao
AU  - Xiaolin Tian
PY  - 2017/01
DA  - 2017/01
TI  - Dark Background Image-denosing Based on KPCA Method
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-16.2016.208
DO  - 10.2991/icmmita-16.2016.208
ID  - Xiao2017/01
ER  -