A Two-Phase Splitting Approach for the Removal of Gaussian-Impulse Noise from Hyperspectral Images

Aetesam, Hazique; Maji, Suman Kumar; Boulanger, Jérôme

doi:10.1007/978-981-16-1086-8_16

Cited by 4 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ω g and Ω s are the set of Gaussian and impulse noise corrupted pixels 2 respectively. If Ω s = ∅, the image is corrupted by only Gaussian noise, and the image formation model is modified as f = u + g. For an image corrupted by both Gaussian and impulse noise, the image formation model [26], [27] can be simplified as:…”

Section: Preliminaries and Objectivementioning

confidence: 99%

CompoHyDen: Hyperspectral Image Restoration via Nonconvex Componentwise Minimization

Aetesam,

Wasi,

Sharma

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a variational approach for estimating the clean hyperspectral images (HSI) that are corrupted by the combined effect of Gaussian noise, impulse noise, stripes, and deadlines. Successful removal of noise from the corrupted observations is essential for subsequent downstream analyses like classification, spectral unmixing, and target tracking. The main contribution of this work is as follows: Firstly, an objective function is designed for the joint estimation of clean data and impulse corrupted pixels. A rationale is presented for using ℓ0−norm to estimate the exact sparsity induced by impulse noise. Secondly, the problem is reformulated as a multiconvex problem which is solved using proximal projection and alternating minimization. Thirdly, to exploit the spatial-spectral similarity, a non-local and vectorized version of total variation (TV) regularization is proposed to estimate the clean data. Lastly, a study on the parameter sensitivity analysis empirically validates the convergence of the restoration results under different values of the regularization hyperparameters. The experiments conducted over synthetically corrupted and real HSI data obtained from hyperspectral sensors suggest the potential utility of the proposed methodology (CompoHyDen) at a scalable level.

show abstract

Section: Preliminaries and Objectivementioning

confidence: 99%

CompoHyDen: Hyperspectral Image Restoration via Nonconvex Componentwise Minimization

Aetesam,

Wasi,

Sharma

2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…A 3D modelling of noisy HSI data followed by its optimization using primal-dual hybrid gradient is proposed in [17]. A two-phase splitting approach for the recovery of clean estimation is discussed in [18]. Low-rank assumption based on spatial and spectral similarity of data is explored in multitude of works.…”

Section: Related Workmentioning

confidence: 99%

Bayesian Approach in a Learning-Based Hyperspectral Image Denoising Framework

Aetesam¹,

Maji

Yahia

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

Hyperspectral images are corrupted by a combination of Gaussian-impulse noise. On one hand, the traditional approach of handling the denoising problem using maximum a posteriori criterion is often restricted by the time-consuming iterative optimization process and design of hand-crafted priors to obtain an optimal result. On the other hand, the discriminative learning-based approaches offer fast inference speed over a trained model; but are highly sensitive to the noise level used for training. A discriminative model trained with a loss function which does not accord with the Bayesian degradation process often leads to sub-optimal results. In this paper, we design the training paradigm emphasizing the role of loss functions; similar to as observed in model-based optimization methods. As a result; loss functions derived in Bayesian setting and employed in neural network training boosts the denoising performance. Extensive analysis and experimental results on synthetically corrupted and real hyperspectral dataset suggest the potential applicability of the proposed technique under a wide range of homogeneous and heterogeneous noisy settings.

show abstract