Tensor-Based Low-Rank and Sparse Prior Information Constraints for Hyperspectral Image Denoising

Guxi Wang, Hongwei Han, Emmanuel John M. Carranza, Si Guo, Ke Guo, Keyan Xiao
2020 IEEE Access  
Hyperspectral data have been widely used in various fields due to its rich spectral and spatial information in recent years. Yet, hyperspectral images are always tainted by a variety of mixed noises. These noises seriously limit the accuracy of subsequent applications. To remove noise, this paper, based on low-rank tensor decomposition, combined with non-local self-similar prior information, proposes a tensor-based non-local low-rank denoising model, where non-local self-similarity uses mainly
more » ... patial correlation while low-rank tensor decomposition method uses mainly spectral correlation between bands. Traditional tensor-based methods are commonly NP-hard to compute and are sensitive to sparse noise. However, the method proposed in this paper can separate efficiently the low-rank clean image from Gaussian noise and sparse noise (pulses, deadlines, stripes, speckle, etc.) by using a new tensor singular value decomposition (T-SVD) and tensor nuclear norm (TNN). The NP-hard task was also achieved well by the alternating direction multiplier method. Due to the full use of spectral and spatial information of the data, Gaussian noise and sparse noise can be effectively removed. The effectiveness of our algorithm was verified through experiments using simulated and real data. INDEX TERMS Hyperspectral image denoising, non-local self-similar, low-rank tensor decomposition, sparse representation. planning [5] , and so on. However, in real scenarios, due to the limitations of the equipment, such as the dark current, sensor sensitivity, transmission errors and calibration during the imaging process, hyperspectral data are certainly tainted by a variety of noises. These noises include Gaussian noise, impulse noise, deadlines, stripes, speckle, among other [6] . The presence of noise in hyperspectral images not only affects the visual effect of images, but also limits the accuracy of ensuing processing, such as classification, spectral unmixing, target detection, and so on [7] .Therefore, it is necessary to remove noise before succeeding work [8] . Up to now, several VOLUME 8, 2020 This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ 102936 VOLUME 8, 2020
doi:10.1109/access.2020.2996303 fatcat:nxwvzhehxncklo2vq6x26coa7a