14 November 2007 Wavelet transform image fusion based on regional variance
Author Affiliations +
Proceedings Volume 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications; 67902Y (2007) https://doi.org/10.1117/12.774761
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China
Abstract
A novel method of wavelet transform image fusion based on regional variance is proposed in this paper. Firstly, the source image is decomposed into four sub-images with wavelet transform. Then, their regional variances of each sub-image are calculated, and different fusion rules depending on local variance are applied. Finally, the whole fusion image can be obtained through inverse wavelet transform. Compared with the image fusion based on conventional wavelet transform, regional variance becomes the depending factor in the image fusion method. It effectively distinguishes the influence on image fusion with different frequencies of source images. The experiment results show that the proposed method is not only better than some conventional methods of image fusion but also have universality.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhiqiang Guo, Jie Yang, "Wavelet transform image fusion based on regional variance", Proc. SPIE 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications, 67902Y (14 November 2007); doi: 10.1117/12.774761; https://doi.org/10.1117/12.774761
PROCEEDINGS
6 PAGES


SHARE
Back to Top