Hyperspectral image denoising using constraint smooth rank approximation and weighted enhance 3DTV

In recent years, the sparse coding-based techniques have been widely used for image denoising. However, most of the sparse coding-based mixed noise reduction methods fail to take full advantage of the geometric structure of data samples. In other words, they neglect the common information shared by the similar patches in sparse coding. To address this concern, in this paper, we propose a robust constrained sparse representation (RCSR) method to remove mixed noise. By using the center coefficient of similar patches as the guider which is approximated by the coefficient of query patch in sparse coding, the geometric structure of data can be well preserved. Moreover, different from most existing two-stage mixed noise reduction methods that use explicit detectors to restrain impulse noise, the proposed RCSR adaptively adjusts the contribution of each pixel in the loss function to eliminate the influences of outliers. Experiments on the reconstruction of synthetic data and the removal of mixed noise in real images demonstrate the effectiveness of our proposed method.

This paper studies the problem of the restoration of images corrupted by mixed Gaussian-impulse noise. In recent years, low-rank matrix reconstruction has become a research hotspot in many scientific and engineering domains such as machine learning, image processing, computer vision and bioinformatics, which mainly involves the problem of matrix completion and robust principal component analysis, namely recovering a low-rank matrix from an incomplete but accurate sampling subset of its entries and from an observed data matrix with an unknown fraction of its entries being arbitrarily corrupted, respectively. Inspired by these ideas, we consider the problem of recovering a low-rank matrix from an incomplete sampling subset of its entries with an unknown fraction of the samplings contaminated by arbitrary errors, which is defined as the problem of matrix completion from corrupted samplings and modeled as a convex optimization problem that minimizes a combination of the nuclear norm and the -norm in this paper. Meanwhile, we put forward a novel and effective algorithm called augmented Lagrange multipliers to exactly solve the problem. For mixed Gaussian-impulse noise removal, we regard it as the problem of matrix completion from corrupted samplings, and restore the noisy image following an impulse-detecting procedure. Compared with some existing methods for mixed noise removal, the recovery quality performance of our method is dominant if images possess low-rank features such as geometrically regular textures and similar structured contents; especially when the density of impulse noise is relatively high and the variance of Gaussian noise is small, our method can outperform the traditional methods significantly not only in the simultaneous removal of Gaussian noise and impulse noise, and the restoration ability for a low-rank image matrix, but also in the preservation of textures and details in the image.

This paper presents a novel denoising scheme for video sequences corrupted by mixed Gaussian-impulse noise. From a global viewpoint, such a video sequence contains three parts: temporal-spatially correlated video content, uncorrelated dense Gaussian noise, and uncorrelated sparse impulse noise. This fact motivates us to formulate the mixed Gaussian-impulse noise removal task as a temporal-spatial decomposition problem, which amounts to a convex program. A two-stage algorithm is developed to solve this problem efficiently. Effectiveness of the proposed algorithm on mixed Gaussian-impulse noise removal is validated through experiments. The results are satisfactory in both visual quality and PSNR values, while very few prior knowledge of noise statistic is required compared to most state-of-the-art methods.

We propose a nonlinear filter that is effective in removing both Gaussian and impulse noise. The proposed filter achieves an excellent performance in the restoration of images degraded by mixed noise, combining smoothing for Gaussian noise removal and inpainting for impulse noise removal on the basis of total variation minimization principle. We also propose how to determine smoothing parameter λ that is important for the quality of restored images, according to a surface model of λ with respect to σn and σs, standard deviations of Gaussian noise and original image respectively. In applying the proposed method to images degraded by various mixed noise, we verified that both PSNR and subjective image quality are significantly improved, compared with the conventional filters.

Hyperspectral images (HSIs) mixed noise removal is a challenge and essential preprocessing part in remote sensing fields. In this paper, To address the challenge of mixed noise suppression in HSI, we introduce a composite denoising framework that unifies a novel weighted group sparsity regularization based on<i> l_2,PS</i> and low-rank Tucker decomposition (LRPWGS). Rather than applying <i>l_2,1</i>-norm constraints directly to the difference image, a weighted <i>l_2,PS</i>-norm is employed to capture the shared group sparse pattern in the gradient domain of HSI and a shrinkage operator is proposed to effectively solve <i>l_2,PS</i>-norm minimization problem. Furthermore, the conventional low-rank Tucker decomposition is utilized to exploit the global correlations across all HSI tensor modes. The alternating direction multiplier method (ADMM) algorithm is adopted to solve the proposed LRPWGS model. Experimental results demonstrate the superior performance of proposed LRPWGS method in HSI denoising task.

Naturally available noises in the videos are complex but fortunately they can be broadly classified as Gaussian and Impulse noises. Most of the available models for noise removal emphasize on any one kind of noise removal thus an optimum model of mixed noise removal is still a challenge. This paper describes about removal of video flickering and artifacts due to sensor motion, unprofessional recording behaviors, device defects, poor lighting conditions and high dynamic exposure. The adaptive spatio-temporal filter gives excellent result for mixed (Gaussian and Impulse) noise removal. Dense optical flow is introduced to reduce the motion blur and enhance the video. The analysis of PSNR and SSIM values were compared with existed method like Non-local Means and BM3D approach and results are tabulated. The Histogram graph gives the better intensity distribution in frames thus the proposed method even works good for low illumination or night vision surveillance videos.

The motivation of this paper is to introduce a novel framework for the restoration of images corrupted by mixed Gaussian-impulse noise. To this aim, first, an adaptive curvelet thresholding criterion is proposed which tries to adaptively remove the perturbations appeared during denoising process. Then, a new statistical regularization term, called joint adaptive statistical prior (JASP), is established which enforces both the local and nonlocal statistical consistencies, simultaneously, in a unified manner. Furthermore, a novel technique for mixed Gaussian plus impulse noise removal using JASP in a variational scheme is developed--we refer to it as De-JASP. To efficiently solve the above variational scheme, an efficient alternating minimization algorithm based on split Bregman iterative framework is developed. Extensive experimental results manifest the effectiveness of the proposed method comparing with the current state-of-the-art methods in mixed Gaussian-impulse noise removal.

Several bandwise total variation (TV) regularized low-rank (LR)-based models have been proposed to remove mixed noise in hyperspectral images (HSIs). Conventionally, the rank of LR matrix is approximated using nuclear norm (NN). The NN is defined by adding all singular values together, which is essentially a $L_{1}$ -norm of the singular values. It results in non-negligible approximation errors and thus the resulting matrix estimator can be significantly biased. Moreover, these bandwise TV-based methods exploit the spatial information in a separate manner. To cope with these problems, we propose a spatial–spectral TV (SSTV) regularized non-convex local LR matrix approximation (NonLLRTV) method to remove mixed noise in HSIs. From one aspect, local LR of HSIs is formulated using a non-convex $L_{\gamma}$ -norm, which provides a closer approximation to the matrix rank than the traditional NN. From another aspect, HSIs are assumed to be piecewisely smooth in the global spatial domain. The TV regularization is effective in preserving the smoothness and removing Gaussian noise. These facts inspire the integration of the NonLLR with TV regularization. To address the limitations of bandwise TV, we use the SSTV regularization to simultaneously consider global spatial structure and spectral correlation of neighboring bands. Experiment results indicate that the use of local non-convex penalty and global SSTV can boost the preserving of spatial piecewise smoothness and overall structural information.

We have proposed fuzzy filters in order to remove additive nonimpulsive noise (e.g., Gaussian noise) while preserving signal details. In this paper, we propose a novel fuzzy filter for removing mixed noise (i.e., Gaussian noise and impulse noise are mixed). In order to remove mixed noise efficiently, we set fuzzy rules by using multiple difference values between arbitrary two pixels in a filter window. We show tuning result of the proposed fuzzy filter and present some simulation results.

In this paper a FIR nonlinear fuzzy filter for image processing, which is most effective in removal of mixed noise, is proposed. In general itpsilas hard to distinguish noise and edges information. This ambiguity leads us to use fuzzy concepts. Fuzzy similarity is used here to suppress noise and preserve edges. Parameters of the membership function are optimized by genetic algorithm approach. Since our problem here is stochastic, traditional optimization algorithms are of no use anymore. Simulation consists of some combination of Gaussian and salt and pepper noises on different classes of images. Results are compared with traditional median and Wiener filters both from subjective and objective points of view.

Infrared images are susceptible to interference from a variety of factors during acquisition and transmission, resulting in the inclusion of mixed noise, which seriously affects the accuracy of subsequent vision tasks. To solve this problem, we designed a mixed noise removal algorithm for infrared images based on improved CycleGAN. First, we proposed a ResNet-E Block that incorporates the EMA (Efficient Multi-Scale Attention Module) and build a generator based on it using the skip-connection structure to improve the network’s ability to remove mixed noise of different strengths. Second, we added the PSNR (Peak Signal-to-Noise Ratio) as an extra calculation item of cycle consistency loss, so that the network can effectively retain the detailed information of infrared images while denoising. Finally, we conducted experimental validation on both synthetic noisy images and real noisy images, which proved that our algorithm can effectively remove the mixed noise in infrared images and the denoising effect is better than other similar methods.

Due to the physical limitations of the imaging devices, hyperspectral images (HSIs) are commonly distorted by a mixture of Gaussian noise, impulse noise, stripes, and dead lines, leading to the decline in the performance of unmixing, classification, and other subsequent applications. In this paper, we propose a novel end-to-end low-rank spatial-spectral network (LR-Net) for the removal of the hybrid noise in HSIs. By integrating the low-rank physical property into a deep convolutional neural network (DCNN), the proposed LR-Net simultaneously enjoys the strong feature representation ability from DCNN and the implicit physical constraint of clean HSIs. Firstly, spatial-spectral atrous blocks (SSABs) are built to exploit spatial-spectral features of HSIs. Secondly, these spatial-spectral features are forwarded to a multi-atrous block (MAB) to aggregate the context in different receptive fields. Thirdly, the contextual features and spatial-spectral features from different levels are concatenated before being fed into a plug-and-play low-rank module (LRM) for feature reconstruction. With the help of the LRM, the workflow of low-rank matrix reconstruction can be streamlined in a differentiable manner. Finally, the low-rank features are utilized to capture the latent semantic relationships of the HSIs to recover clean HSIs. Extensive experiments on both simulated and real-world datasets were conducted. The experimental results show that the LR-Net outperforms other state-of-the-art denoising methods in terms of evaluation metrics and visual assessments. Particularly, through the collaborative integration of DCNNs and the low-rank property, the LR-Net shows strong stability and capacity for generalization.

This paper proposes a novel non-parametric Bayesian framework for solving mixed noise removal problem. In order to removing unstable effects of outlier noise such as salt-and-pepper in the training data, we decompose the observed data model into three components terms of ideal data, Gaussian noise and sparse outlier. And the proposed model employs spike-slab sparse prior to find the sparser coefficients of desired data term and outlier noise. Note that the proposed non-parametric Bayesian model can infer the noise statistics from the training data and have been robust to the mixed noise without tuning of model parameters. Experimental results demonstrate our proposed algorithm performs well with mixed noise and achieves better performance over other state-of-the-art methods.

Removal of Mixed noise from digital color images is a challenging task because it requires processing of different types of noise. Also, noise need to be distinguished from the original image structures such as edges and details. Fuzzy theory is an effective solution to this problem. In this paper, a new fuzzy method is proposed to reduce impulse and Gaussian noise from color images. A weighted averaging filtering operation is used for this purpose. The weights in the averaging process are assigned using a fuzzy rule system based on a new certainty function, so as to reduce both noise types and to preserve image structures. Experimental results show that the method outperforms the state-of-the-art filters.

CSKNN: Cost-sensitive K-Nearest Neighbor using hyperspectral imaging for identification of wheat varieties