Nonlinear filtering of hyperspectral images with anisotropic diffusion

M. Lennon1, G. Mercier2, L. Hubert-Moy3
1Département ITI, École Nationale Supérieure des Télécommunications, Brest, France
2Département ITI, École Nationale Supécommunications de Bretagne, Brest, France
3Laboratoire COSTEL,UMR, Université de Rennes, Rennes, France

Tóm tắt

A vectorial extension of the scalar anisotropic diffusion nonlinear filtering process applied on hyperspectral images is presented. In a first step, data are projected in a transformed space with a Maximum Noise Fraction transform, allowing the new components to be sorted in order of signal to noise ratio. The filtering is adapted to the signal to noise ratio of each component and a spectral dissimilarity vectorial measure is used in the filtering process. The inverse transform allows the filtered data to be reprojected in the original space. This process is useful for denoising hyperspectral images and for reducing spatial and spectral variability in each class of interest, leading to increase the performance of further segmentation or classification algorithms.

Từ khóa

#Filtering #Hyperspectral imaging #Anisotropic magnetoresistance #Signal to noise ratio #Hyperspectral sensors #Principal component analysis #Covariance matrix #Smoothing methods #Noise measurement #Image segmentation

Tài liệu tham khảo

10.1007/978-94-017-1699-4_4 10.1109/34.56205 10.1109/IAI.1998.666877 10.1080/014311697217404 10.1109/83.541429 10.1109/36.338369 10.1109/36.54356 10.1007/978-3-662-03978-6 10.1109/36.3001