NGMeet Filter

Features:

You can use the NGMeet function to remove noise from hyperspectral data by using the non-local meets global approach.

Steps:

1.      Select Filtering and Enhancement → NGmeet Filter.  

2.      After completion, click OK and visualize the filtered image.

3.      The filtered image can be returned to the original by using Filtering and Enhancement → Remove all Filters and Enhancements or Reset button.

Additional Information:

The NGMeet method estimates the denoised datacube by using these steps. For each iteration, i

1.      Compute spectral low-rank approximation of the noisy input data (Yi) by using singular value decomposition. The approximation results in a reduced datacube (Mi) and the related orthogonal basis Ai.

2.      Perform spatial de-noising of the reduced datacube Mi by using non-local similarity filtering. You can control the degree of smoothing by specifying the smoothing parameter 'Sigma'.

3.      Perform inverse projection. Map the denoised reduced datacube Mi to the original space by using the orthogonal basis Ai. The result is the denoised output (Xi) obtained at iteration i.

4.      Perform iterative regularization. Update the noisy input data, Yi+1 = λXi + (1-λ)Yi.

5.      Repeat steps 1 to 4, for the specified number of iterations. The final value Xi is the denoised hyperspectral data.

References:

He, Wei, Quanming Yao, Chao Li, Naoto Yokoya, and Qibin Zhao. “Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising.” In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6861–70. Long Beach, CA, USA: IEEE, 2019. https://doi.org/10.1109/CVPR.2019.00703.