Nonorthogonal Tensor Matricization for Hyperspectral Image Filtering

Abstract

A generalized multidimensional Wiener filter for denoising is adapted to hyperspectral images (HSIs). Multidimensional Wiener filtering (MWF) uses the signal subspace of each n-mode flattening matrix of the HSI, which is a third-order tensor. However, in the HSI case, the n-mode ranks are close to the n-mode dimensions. Thus, the signal subspace dimension can be underestimated. This leads to a loss of spatial resolution-edge blurring-and artifacts in the restored HSI. To cope with the underestimation while preserving edges, a new method is proposed. It estimates the relevant directions of flattening that may not be parallel to HSI dimensions. We adapt the bidimensional straight line detection algorithm that estimates the HSI main directions, which are used to flatten the HSI tensor. We also generalize the quadtree decomposition to tensors in order to adapt the filtering to the local image characteristics. Comparative studies with MWF, principal component analysis-stationary wavelet transform, and channel-by-channel Wiener filtering show that our algorithm provides better performance while restoring impaired HYDICE HSIs.Index Terms-Flattening directions, hyperspectral, multidimensional Wiener filtering (MWF), quadtree, tensor.

Multispectral texture characterization: application to computer aided diagnosis on prostatic tissue images

“…columns are I n dimensional vectors obtained from X by varying the index i n and keeping the other indices fixed [44]. These vectors are called "n-mode vectors".…”

About Classification Methods Based on Tensor Modelling for Hyperspectral Images

“…Our methods are based on tensor representation to keep the initial spatial structure and insure the neighborhood effects. Tensor processing have proven its efficiency in several domains, telecommunications [21], image processing [1,22,23] and, more recently in hyperspectral image analysis [9][10][11].…”

“…Therefore, they rely on spectral properties only, neglecting the spatial rearrangement. To overcome these disadvantages, [9][10][11] recently introduced a new HSI representation based on tensor. This representation involves a powerful mathematical framework for analyzing jointly the spatial and spectral structure of data.…”

Blind source separation of underdetermined mixtures of event-related sources

“…In the recent years, a lot of attention has been paid to blind source separation (BSS) due to its wide-ranging applications in many areas [1] such as audio and speech processing [2], telecommunications [3], biomedical engineering [4], hyperspectral imaging [5], etc. Assuming an M -dimensional observation vector, y(k), this problem is mathematically expressed as:…”