25 October 2016 Algorithm for image fusion via gradient correlation and difference statistics
Author Affiliations +
Proceedings Volume 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control; 101571N (2016) https://doi.org/10.1117/12.2246618
Event: International Symposium on Optoelectronic Technology and Application 2016, 2016, Beijing, China
Abstract
In order to overcome the shortcoming of traditional image fusion based on discrete wavelet transform (DWT), a novel image fusion algorithm based on gradient correlation and difference statistics is proposed in this paper. The source images are decomposed into low-frequency coefficients and high-frequency coefficients by DWT: the former are fused by a local gradient correlation based scheme to extract the local feature information in source images; the latter are fused by a neighbor difference statistics based scheme to reserve the conspicuous edge information. Finally, the fused image is reconstructed by inverse DWT. Experimental results show that the proposed method performs better than other methods in reserving details.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jing Han, Li-juan Wang, Yi Zhang, Lian-fa Bai, Ningjie Mao, "Algorithm for image fusion via gradient correlation and difference statistics", Proc. SPIE 10157, Infrared Technology and Applications, and Robot Sensing and Advanced Control, 101571N (25 October 2016); doi: 10.1117/12.2246618; https://doi.org/10.1117/12.2246618
PROCEEDINGS
12 PAGES


SHARE
Back to Top