Fusion algorithm based on W-transfrom and an improved local energy
- DOI
- 10.2991/ifmeita-16.2016.164How to use a DOI?
- Keywords
- W-system Image Fusion Fusion rules Objective evaluation index
- Abstract
W-transform is a new kind of orthogonal transform which provides a method to eliminate the phenomenon of Gibbs. This paper proposes a new fusion algorithm based on the W-transform. Compared to the classical fusion algorithm based on DCT and Haar transform, the algorithm based on the W-transform proposed in this article is improved in four evaluation index including the standard deviation, information entropy, average gradient, and spatial frequency. This paper also presents an improved fusion rule according to the characteristics of low frequency and high frequency components obtained by the W-transform, it adopts weighted average method in the low frequency part by introducing information entropy as the weights, while combines local region features and each single pixel value in the high frequency band. Compared to the fusion rule based only on local region energy, the improved fusion rule can effectively improve the objective evaluation index and visual effect of the fused image. Experimental results reveal the superiority of algorithm proposed in this paper compared to comparable algorithms.
- Copyright
- © 2016, 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 - Nuo Xu AU - Lu Wang AU - Ke Zhao AU - Sai-Nan Pi AU - Xiao-Chun Wang PY - 2016/01 DA - 2016/01 TI - Fusion algorithm based on W-transfrom and an improved local energy BT - Proceedings of the 2016 International Forum on Management, Education and Information Technology Application PB - Atlantis Press SP - 895 EP - 904 SN - 2352-5398 UR - https://doi.org/10.2991/ifmeita-16.2016.164 DO - 10.2991/ifmeita-16.2016.164 ID - Xu2016/01 ER -