Hypspectral image denoising with a multi-view fusion strategy
Qiangqiang Yuan, Huanfeng Shen, Liangpei Zhang, Xia Lan · 2012
The amount of noise included in a hyperspectral image limits its application and has a negative impact on hyperspectral image classification, unmixing, target detection, and so on. In this paper, we propose a hyperspectral image denoising algorithm with a spatial and spectral fusion strategy. The idea is to denoise the noisy hyperspectral 3D cube using a given 2D denoising algorithm but applied from spatial and spectral views. A fusion algorithm is then designed to merge the resulting multiple-view denoised image into one, so that the visual quality of the fused hyperspectral image is improved. A number of experiments illustrate that the proposed approach can surprisingly produce a better denoising result than both spatial and spectral view denoising result, especially at high noise level.