Improving locally weighted denoising method for hyperspectral data in spectral domain

An improved method of locally weighted denoising is introduced and applied to hyperspectal imagery denoising in spectral domain. Weight factors and incidence are self-defined in the method. During the processing, it remains more spectral details for hyperspectral data compared with the conventional weighted averaging method. Experimental results show that the proposed algorithm of locally weighted denoising provides an improvement in SNR for hyperspectal data specially.