Hyperspectral image noise removing method and apparatus

Abstract

The present invention discloses a hyperspectral image noise removing method and apparatus. The method comprises: performing Tucker decomposition on a hyperspectral image to obtain a core tensor; calculating an energy information vector of the core tensor in three dimensions; calculating an energy-to-noise ratio of the hyperspectral image in the three dimensions; calculating a tensor rank according to the energy information vector and the energy-to-noise ratio; and decomposing the hyperspectral image according to the tensor rank to remove noise.

Description

technical field

[0001] The invention relates to the technical field of image processing, in particular to a method and device for removing noise of a hyperspectral image. Background technique

[0002] Spectral images with a spectral resolution in the range of 10l are called hyperspectral images. Usually, the equipment for collecting hyperspectral images contains multiple sensors that can collect light wave data of different wavelengths, and each sensor can generate a two-dimensional grayscale image at its wavelength. In this way, these two-dimensional grayscale images are combined to form a three-dimensional hyperspectral image.

[0003] Denoising hyperspectral images is a key preprocessing step in the subsequent processing of hyperspectral images for object classification and target recognition. Some existing methods for removing noise from hyperspectral images convert 3D image data into 2D image data first, and then use 2D denoising methods to denoise hyperspectral image...

Examples

Embodiment Construction

[0014] Exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be understood that the implementations shown and described in the drawings are only exemplary, intended to explain the principle and spirit of the present invention, rather than limit the scope of the present invention.

[0015] refer to figure 1 , figure 1 It is a flowchart of an embodiment 100 of the method for removing noise of a hyperspectral image according to the present invention. figure 1 The illustrated embodiment 100 may include steps 101 to 105 as follows.

[0016] In step 101, the hyperspectral image is subjected to Tucker decomposition to obtain a nuclear tensor.

[0017] In one embodiment of the present invention, Tucker decomposition without truncation can be performed on hyperspectral images. That is: if the noisy hyperspectral image Then the kernel tensor obtained by untruncated Tucker decomposition in, Indicate...

technical field

[0001] The invention relates to the technical field of image processing, in particular to a method and device for removing noise of a hyperspectral image. Background technique

[0002] Spectral images with a spectral resolution in the range of 10l are called hyperspectral images. Usually, the equipment for collecting hyperspectral images contains multiple sensors that can collect light wave data of different wavelengths, and each sensor can generate a two-dimensional grayscale image at its wavelength. In this way, these two-dimensional grayscale images are combined to form a three-dimensional hyperspectral image.

[0003] Denoising hyperspectral images is a key preprocessing step in the subsequent processing of hyperspectral images for object classification and target recognition. Some existing methods for removing noise from hyperspectral images convert 3D image data into 2D image data first, and then use 2D denoising methods to denoise hyperspectral image...

Examples

Embodiment Construction

[0014] Exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be understood that the implementations shown and described in the drawings are only exemplary, intended to explain the principle and spirit of the present invention, rather than limit the scope of the present invention.

[0015] refer to figure 1 , figure 1 It is a flowchart of an embodiment 100 of the method for removing noise of a hyperspectral image according to the present invention. figure 1 The illustrated embodiment 100 may include steps 101 to 105 as follows.

[0016] In step 101, the hyperspectral image is subjected to Tucker decomposition to obtain a nuclear tensor.

[0017] In one embodiment of the present invention, Tucker decomposition without truncation can be performed on hyperspectral images. That is: if the noisy hyperspectral image Then the kernel tensor obtained by untruncated Tucker decomposition in, Indicate...

Images