Quality Evaluation of Hyperspectral Image Denoising Algorithm Based on Classification Application

摘要

Signal-to-noise ratio (SNR) is a widely accepted image quality evaluation criterion for its easy calculation andrnexplicit mathematical significance. However, for quality evaluation of hyperspectral image denoising algorithms,rnSNR ignores the structure of the spatial information of hyperspectral image, and does not represent the loss ofrnthe spectral information. Therefore, we use classification to assess the hyperspectral image denoisingrnalgorithms. Three hyperspectral image denoising methods are implemented respectively, which are: 1)rnhyperspectral image denoising base on principal component analysis (PCA); 2) multiple linear regression (MLR)rnmodel for hyperspectral image denoising in the wavelet domain; 3) MRL model for hyperspectral imagerndenoising in the curvelet domain. The classification results show that the higher SNR does not alwaysrncontribute to higher overall accuracy of classification. Therefore, the hyperspectral image quality assessmentrnbased on the post application is necessary.