Image Fusion Algorithm based on Sparse Features and Pulse Coupled Neural Networks in Wavelet Transform Domain

DOI

10.2991/icmmcce-15.2015.14How to use a DOI?

Keywords

Image fusion,robust principal component analysis (RPCA), pulse coupled neural networks (PCNN), wavelet transform

Abstract

Multi-focus image fusion has become an advanced research topic in image processing field. The traditionalmethods that are commonly used wavelet transform, principal component analysis (PCA),pulse coupled neural networks (PCNN), which got some results, but they are not effective enough for focused regions. In this paper, an algorithm based on sparse features and pulse coupled neural networks in wavelet transform (WT) domain has been proposed. Robust principal component analysis (RPCA) combined PCNN are applied to low frequency of the wavelet coefficients, and spatial frequency (SF) combined PCNN are applied to high frequency components.The experiment results show that the method proposed not only improve the quality of the fused image, but also preserved clarity and information, which gives better results than the other techniques used.

Copyright

© 2015, 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)

TY  - CONF
AU  - YunXiang Tian
AU  - XiaoLin Tian
PY  - 2015/12
DA  - 2015/12
TI  - Image Fusion Algorithm based on Sparse Features and Pulse Coupled Neural Networks in Wavelet Transform Domain
BT  - Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015
PB  - Atlantis Press
SP  - 74
EP  - 78
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmcce-15.2015.14
DO  - 10.2991/icmmcce-15.2015.14
ID  - Tian2015/12
ER  -