Weighted Couple Sparse Representation With Classified Regularization for Impulse Noise Removal

Data Subdivision Based Dual-Weighted Robust Principal Component Analysis

Principal Component Analysis (PCA) is one of the most important unsupervised dimensionality reduction algorithms, which uses squared -norm to make it very sensitive to outliers. Those improved versions based on -norm alleviate this problem, but they have other shortcomings, such as optimization difficulties or lack of rotational invariance, etc. Besides, existing methods only vaguely divide normal samples and outliers to improve robustness, but they ignore the fact that normal samples can be more specifically divided into positive samples and hard samples, which should have different contributions to the model because positive samples are more conducive to learning the projection matrix. In this paper, we propose a novel Data Subdivision Based Dual-Weighted Robust Principal Component Analysis, namely DRPCA, which firstly designs a mark vector to distinguish normal samples and outliers, and directly removes outliers according to mark weights. Moreover, we further divide normal samples into positive samples and hard samples by self-constrained weights, and place them in relative positions, so that the weight of positive samples is larger than hard samples, which makes the projection matrix more accurate. Additionally, the optimal mean is employed to obtain a more accurate data center. To solve this problem, we carefully design an effective iterative algorithm and analyze its convergence. Experiments on real-world and RGB large-scale datasets demonstrate the superiority of our method in dimensionality reduction and anomaly detection.

When Broad Learning System Meets Label Noise Learning: A Reweighting Learning Framework

Broad learning system (BLS) is a novel neural network with efficient learning and expansion capacity, but it is sensitive to noise. Accordingly, the existing robust broad models try to suppress noise by assigning each sample an appropriate scalar weight to tune down the contribution of noisy samples in network training. However, they disregard the useful information of the noncorrupted elements hidden in the noisy samples, leading to unsatisfactory performance. To this end, a novel BLS with adaptive reweighting (BLS-AR) strategy is proposed in this article for the classification of data with label noise. Different from the previous works, the BLS-AR learns for each sample a weight vector rather than a scalar weight to indicate the noise degree of each element in the sample, which extends the reweighting strategy from sample level to element level. This enables the proposed network to precisely identify noisy elements and thus highlight the contribution of informative ones to train a more accurate representation model. Thanks to the separability of the model, the proposed network can be divided into several subnetworks, each of which can be trained efficiently. In addition, three corresponding incremental learning algorithms of the BLS-AR are developed for adding new samples or expanding the network. Substantial experiments are conducted to explicate the effectiveness and robustness of the proposed BLS-AR model.

Modal-Regression-Based Broad Learning System for Robust Regression and Classification

A novel neural network, namely, broad learning system (BLS), has shown impressive performance on various regression and classification tasks. Nevertheless, most BLS models may suffer serious performance degradation for contaminated data, since they are derived under the least-squares criterion which is sensitive to noise and outliers. To enhance the model robustness, in this article we proposed a modal-regression-based BLS (MRBLS) to tackle the regression and classification tasks of data corrupted by noise and outliers. Specifically, modal regression is adopted to train the output weights instead of the minimum mean square error (MMSE) criterion. Moreover, the l2,1 -norm-induced constraint is used to encourage row sparsity of the connection weight matrix and achieve feature selection. To effectively and efficiently train the network, the half-quadratic theory is used to optimize MRBLS. The validity and robustness of the proposed method are verified on various regression and classification datasets. The experimental results demonstrate that the proposed MRBLS achieves better performance than the existing state-of-the-art BLS methods in terms of both accuracy and robustness.

Distributed tracking control of structural balance for complex dynamical networks based on the coupling targets of nodes and links

In this paper, the complex dynamical networks (CDNs) with dynamic connections are regarded as an interconnected systems composed of intercoupling links’ subsystem (LS) and nodes’ subsystem (NS). Different from the previous researches on structural balance control of CDNs, the directed CDNs’ structural balance problem is solved. Considering the state of links cannot be measured accurately in practice, we can control the nodes’ state and enforce the weights of links to satisfy the conditions of structural balance via effective coupling. To achieve this aim, a coupling strategy between a predetermined matrix of the structural balance and a reference tracking target of NS is established by the correlative control method. Here, the controller in NS is used to track the reference tracking target, and indirectly let LS track the predetermined matrix and reach a structural balance by the effective coupling for directed and undirected networks. Finally, numerical simulations are presented to verify the theoretical results.

TDPN: Texture and Detail-Preserving Network for Single Image Super-Resolution

Single image super-resolution (SISR) using deep convolutional neural networks (CNNs) achieves the state-of-the-art performance. Most existing SISR models mainly focus on pursuing high peak signal-to-noise ratio (PSNR) and neglect textures and details. As a result, the recovered images are often perceptually unpleasant. To address this issue, in this paper, we propose a texture and detail-preserving network (TDPN), which focuses not only on local region feature recovery but also on preserving textures and details. Specifically, the high-resolution image is recovered from its corresponding low-resolution input in two branches. First, a multi-reception field based branch is designed to let the network fully learn local region features by adaptively selecting local region features in different reception fields. Then, a texture and detail-learning branch supervised by the textures and details decomposed from the ground-truth high resolution image is proposed to provide additional textures and details for the super-resolution process to improve the perceptual quality. Finally, we introduce a gradient loss into the SISR field and define a novel hybrid loss to strengthen boundary information recovery and to avoid overly smooth boundary in the final recovered high-resolution image caused by using only the MAE loss. More importantly, the proposed method is model-agnostic, which can be applied to most off-the-shelf SISR networks. The experimental results on public datasets demonstrate the superiority of our TDPN on most state-of-the-art SISR methods in PSNR, SSIM and perceptual quality. We will share our code on https://github.com/tocaiqing/TDPN.

Multi-Path Deep CNN with Residual Inception Network for Single Image Super-Resolution

Recent research on single-image super-resolution (SISR) using deep convolutional neural networks has made a breakthrough and achieved tremendous performance. Despite their significant progress, numerous convolutional neural networks (CNN) are limited in practical applications, owing to the requirement of the heavy computational cost of the model. This paper proposes a multi-path network for SISR, known as multi-path deep CNN with residual inception network for single image super-resolution. In detail, a residual/ResNet block with an Inception block supports the main framework of the entire network architecture. In addition, remove the batch normalization layer from the residual network (ResNet) block and max-pooling layer from the Inception block to further reduce the number of parameters to preventing the over-fitting problem during the training. Moreover, a conventional rectified linear unit (ReLU) is replaced with Leaky ReLU activation function to speed up the training process. Specifically, we propose a novel two upscale module, which adopts three paths to upscale the features by jointly using deconvolution and upsampling layers, instead of using single deconvolution layer or upsampling layer alone. The extensive experimental results on image super-resolution (SR) using five publicly available test datasets, which show that the proposed model not only attains the higher score of peak signal-to-noise ratio/structural similarity index matrix (PSNR/SSIM) but also enables faster and more efficient calculations against the existing image SR methods. For instance, we improved our method in terms of overall PSNR on the SET5 dataset with challenging upscale factor 8× as 1.88 dB over the baseline bicubic method and reduced computational cost in terms of number of parameters 62% by deeply-recursive convolutional neural network (DRCN) method.

Synchronization of Stochastic Complex Dynamical Networks Subject to Consecutive Packet Dropouts

This paper studies the modeling and synchronization problems for stochastic complex dynamical networks subject to consecutive packet dropouts. Different from some existing research results, both probability characteristic and upper bound of consecutive packet dropouts are involved in the proposed approach of controller design. First, an error dynamical network with stochastic and bounded delay is established by step-delay method, where the randomness of the bounded delay can be verified later by the probability theory method. A new modeling method is introduced to reflect the probability characteristic of consecutive packet dropouts. Based on the proposed model, some sufficient conditions are proposed under which the error dynamical network is globally exponentially synchronized in the mean square sense. Subsequently, a probability-distribution-dependent controller design procedure is then proposed. Finally, two numerical examples with simulations are provided to validate the analytical results and demonstrate the less conservatism of the proposed model method.

Cascading and Enhanced Residual Networks for Accurate Single-Image Super-Resolution

Deep convolutional neural networks (CNNs) have contributed to the significant progress of the single-image super-resolution (SISR) field. However, the majority of existing CNN-based models maintain high performance with massive parameters and exceedingly deeper structures. Moreover, several algorithms essentially have underused the low-level features, thus causing relatively low performance. In this article, we address these problems by exploring two strategies based on novel local wider residual blocks (LWRBs) to effectively extract the image features for SISR. We propose a cascading residual network (CRN) that contains several locally sharing groups (LSGs), in which the cascading mechanism not only promotes the propagation of features and the gradient but also eases the model training. Besides, we present another enhanced residual network (ERN) for image resolution enhancement. ERN employs a dual global pathway structure that incorporates nonlocal operations to catch long-distance spatial features from the the original low-resolution (LR) input. To obtain the feature representation of the input at different scales, we further introduce a multiscale block (MSB) to directly detect low-level features from the LR image. The experimental results on four benchmark datasets have demonstrated that our models outperform most of the advanced methods while still retaining a reasonable number of parameters.

Satellite Multispectral and Hyperspectral Image De-Noising with Enhanced Adaptive Generalized Gaussian Distribution Threshold in the Wavelet Domain

The presence of noise in remote sensing satellite images may cause limitations in analysis and object recognition. Noise suppression based on thresholding neural network (TNN) and optimization algorithms perform well in de-noising. However, there are some problems that need to be addressed. Furthermore, finding the optimal threshold value is a challenging task for learning algorithms. Moreover, in an optimization-based noise removal technique, we must utilize the optimization algorithm to overcome the problem. These methods are effective at reducing noise but may blur some parts of an image, and they are time-consuming. This flaw motivated the authors to develop an efficient de-noising method to discard un-wanted noises from these images. This study presents a new enhanced adaptive generalized Gaussian distribution (AGGD) threshold for satellite and hyperspectral image (HSI) de-noising. This function is data-driven, non-linear, and it can be fitted to any image. Applying this function provides us with an optimum threshold value without using any least mean square (LMS) learning or optimization algorithms. Thus, it is possible to save the processing time as well. The proposed function contains two main parts. There is an AGGD threshold in the interval [−σn, σn], and a new non-linear function behind the interval. These combined functions can tune the wavelet coefficients properly. We applied the proposed technique to various satellite remote sensing images. We also used hyperspectral remote sensing images from AVIRIS, HYDICE, and ROSIS sensors for our experimental analysis and validation process. We applied peak signal-to-noise ratio (PSNR) and Mean Structural Similarity Index (MSSIM) to measure and evaluate the performance analysis of different de-noising techniques. Finally, this study shows the superiority of the developed method as compared with the previous TNN and optimization-based noise suppression methods. Moreover, as the results indicate, the proposed method improves PSNR values and visual inspection significantly when compared with various image de-noising methods.

Trends in Super-High-Definition Imaging Techniques Based on Deep Neural Networks

Images captured by cameras in closed-circuit televisions and black boxes in cities have low or poor quality owing to lens distortion and optical blur. Moreover, actual images acquired through imaging sensors of cameras such as charge-coupled devices and complementary metal-oxide-semiconductors generally include noise with spatial-variant characteristics that follow Poisson distributions. If compression is directly applied to an image with such spatial-variant sensor noises at the transmitting end, complex and difficult noises called compressed Poisson noises occur at the receiving end. The super-high-definition imaging technology based on deep neural networks improves the image resolution as well as effectively removes the undesired compressed Poisson noises that may occur during real image acquisition and compression as well as in transmission and reception systems. This solution of using deep neural networks at the receiving end to solve the image degradation problem can be used in the intelligent image analysis platform that performs accurate image processing and analysis using high-definition images obtained from various camera sources such as closed-circuit televisions and black boxes. In this review article, we investigate the current state-of-the-art super-high-definition imaging techniques in terms of image denoising for removing the compressed Poisson noises as well as super-resolution based on the deep neural networks.

Adaptive Wavelet Based MRI Brain Image De-noising

This paper presents a unique approach for wavelet-based MRI brain image de-noising. Adaptive soft and hard threshold functions are first proposed to improve the results of standard soft and hard threshold functions for image de-noising in the wavelet domain. Then, we applied the newly emerged improved adaptive generalized Gaussian distributed oriented threshold function (improved AGGD) on the MRI images to improve the results of the adaptive soft and hard threshold functions and also to display, this non-linear and data-driven function can work promisingly even in de-noising the medical images. The most important characteristic of this function is that it is dependent on the image since it is combined with an adaptive generalized Gaussian distribution function.Traditional thresholding neural network (TNN) and optimized based noise reduction have good results but fail to keep the visual quality and may blur some parts of an image. In TNN and optimized based image de-noising, it was required to use Least-mean-square (LMS) learning and optimization algorithms, respectively to find the optimum threshold value and parameters of the threshold functions which was time consuming. To address these issues, the improved AGGD based image de-noising approach is introduced to enhance the qualitative and quantitative performance of the above mentioned image de-noising techniques. De-noising using improved AGGD threshold function provides better results in terms of Peak Signal to Noise Ratio (PSNR) and also faster processing time since there is no need to use any Least-mean-square (LMS) learning and optimization algorithms for obtaining the optimum value and parameters of the thresholding functions. The experimental results indicate that image de-noising using improved AGGD threshold performs pretty well comparing with the adaptive threshold, standard threshold, improved wavelet threshold, and the optimized based noise reduction methods.

Image Restoration Using Fixed-Point-Like Methods for New TVL1 Variational Problems

In this paper, we first propose two TVL1 variational problems for restoring images degraded by blurring and impulse noise, and then we propose two fixed-point-like methods, using proximal operators, for solving the new proposed TVL1 problems. Numerical experiments for several test images blurred by Gaussian kernel and corrupted by salt-and-pepper impulse noise are provided to demonstrate the efficiency and reliability of the proposed fixed-point-like methods. Numerical results show that two fixed-point-like methods for solving the new TVL1 variational problems perform very well in both PSNR (Peak signal-to-noise ratio) values and CPU time as compared with the fixed-point-like methods for solving two existing TVL1 variational problems.

Image Processing for Laser Imaging Using Adaptive Homomorphic Filtering and Total Variation

Laser active imaging technology has important practical value and broad application prospects in military fields such as target detection, radar reconnaissance, and precise guidance. However, factors such as uneven laser illuminance, atmospheric backscatter, and the imaging system itself will introduce noise, which will affect the quality of the laser active imaging image, resulting in image contrast decline and blurring image edges and details. Therefore, an image denoising algorithm based on homomorphic filtering and total variation cascade is proposed in this paper, which strives to reduce the noise while retaining the edge features of the image to the maximum extent. Firstly, the image type is determined according to the characteristics of the laser image, and then the speckle noise in the low-frequency region is suppressed by adaptive homomorphic filtering. Finally, the image denoising method of minimizing the total variation is adopted for the impulse noise and Gaussian noise. Experimental results show that compared with separate homomorphic filtering, total variation filtering, and median filtering, the proposed algorithm significantly improves the contrast, retains edge details, achieves the expected effect. It can better adjust the image brightness and is beneficial for subsequent processing.

Separable Reversible Data Hiding in Encrypted Image Based on Two-Dimensional Permutation and Exploiting Modification Direction

In this paper, we propose a separable reversible data hiding method in encrypted image (RDHEI) based on two-dimensional permutation and exploiting modification direction (EMD). The content owner uses two-dimensional permutation to encrypt original image through encryption key, which provides confidentiality for the original image. Then the data hider divides the encrypted image into a series of non-overlapping blocks and constructs histogram of adjacent encrypted pixel errors. Secret bits are embedded into a series of peak points of the histogram through EMD. Direct decryption, data extraction and image recovery can be performed separately by the receiver according to the availability of encryption key and data-hiding key. Different from some state-of-the-art RDHEI methods, visual quality of the directly decrypted image can be further improved by the receiver holding the encryption key. Experimental results demonstrate that the proposed method outperforms some state-of-the-art methods in embedding capacity and visual quality.

Quaternion Locality-Constrained Coding for Color Face Hallucination

Recently, the locality linear coding (LLC) has attracted more and more attentions in the areas of image processing and computer vision. However, the conventional LLC with real setting is just designed for the grayscale image. For the color image, it usually treats each color channel individually or encodes the monochrome image by concatenating all the color channels, which ignores the correlations among different channels. In this paper, we propose a quaternion-based locality-constrained coding (QLC) model for color face hallucination in the quaternion space. In QLC, the face images are represented as quaternion matrices. By transforming the channel images into an orthogonal feature space and encoding the coefficients in the quaternion domain, the proposed QLC is expected to learn the advantages of both quaternion algebra and locality coding scheme. Hence, the QLC cannot only expose the true topology of image patch manifold but also preserve the inherent correlations among different color channels. Experimental results demonstrated that our proposed QLC method achieved superior performance in color face hallucination compared with other state-of-the-art methods.

Robust Face Hallucination via Locality-Constrained Bi-Layer Representation

Recently, locality-constrained linear coding (LLC) has been drawn great attentions and been widely used in image processing and computer vision tasks. However, the conventional LLC model is always fragile to outliers. In this paper, we present a robust locality-constrained bi-layer representation model to simultaneously hallucinate the face images and suppress noise and outliers with the assistant of a group of training samples. The proposed scheme is not only able to capture the nonlinear manifold structure but also robust to outliers by incorporating a weight vector into the objective function to subtly tune the contribution of each pixel offered in the objective. Furthermore, a high-resolution (HR) layer is employed to compensate the missed information in the low-resolution (LR) space for coding. The use of two layers (the LR layer and the HR layer) is expected to expose the complicated correlation between the LR and HR patch spaces, which helps to obtain the desirable coefficients to reconstruct the final HR face. The experimental results demonstrate that the proposed method outperforms the state-of-the-art image super-resolution methods in terms of both quantitative measurements and visual effects.

Noise Robust Face Image Super-Resolution Through Smooth Sparse Representation

Face image super-resolution has attracted much attention in recent years. Many algorithms have been proposed. Among them, sparse representation (SR)-based face image super-resolution approaches are able to achieve competitive performance. However, these SR-based approaches only perform well under the condition that the input is noiseless or has small noise. When the input is corrupted by large noise, the reconstruction weights (or coefficients) of the input low-resolution (LR) patches using SR-based approaches will be seriously unstable, thus leading to poor reconstruction results. To this end, in this paper, we propose a novel SR-based face image super-resolution approach that incorporates smooth priors to enforce similar training patches having similar sparse coding coefficients. Specifically, we introduce the fused least absolute shrinkage and selection operator-based smooth constraint and locality-based smooth constraint to the least squares representation-based patch representation in order to obtain stable reconstruction weights, especially when the noise level of the input LR image is high. Experiments are carried out on the benchmark FEI face database and CMU+MIT face database. Visual and quantitative comparisons show that the proposed face image super-resolution method yields superior reconstruction results when the input LR face image is contaminated by strong noise.

Dictionary learning based noisy image super-resolution via distance penalty weight model

In this study, we address the problem of noisy image super-resolution. Noisy low resolution (LR) image is always obtained in applications, while most of the existing algorithms assume that the LR image is noise-free. As to this situation, we present an algorithm for noisy image super-resolution which can achieve simultaneously image super-resolution and denoising. And in the training stage of our method, LR example images are noise-free. For different input LR images, even if the noise variance varies, the dictionary pair does not need to be retrained. For the input LR image patch, the corresponding high resolution (HR) image patch is reconstructed through weighted average of similar HR example patches. To reduce computational cost, we use the atoms of learned sparse dictionary as the examples instead of original example patches. We proposed a distance penalty model for calculating the weight, which can complete a second selection on similar atoms at the same time. Moreover, LR example patches removed mean pixel value are also used to learn dictionary rather than just their gradient features. Based on this, we can reconstruct initial estimated HR image and denoised LR image. Combined with iterative back projection, the two reconstructed images are applied to obtain final estimated HR image. We validate our algorithm on natural images and compared with the previously reported algorithms. Experimental results show that our proposed method performs better noise robustness.

Mixed Noise Removal via Laplacian Scale Mixture Modeling and Nonlocal Low-Rank Approximation

Recovering the image corrupted by additive white Gaussian noise (AWGN) and impulse noise is a challenging problem due to its difficulties in an accurate modeling of the distributions of the mixture noise. Many efforts have been made to first detect the locations of the impulse noise and then recover the clean image with image in painting techniques from an incomplete image corrupted by AWGN. However, it is quite challenging to accurately detect the locations of the impulse noise when the mixture noise is strong. In this paper, we propose an effective mixture noise removal method based on Laplacian scale mixture (LSM) modeling and nonlocal low-rank regularization. The impulse noise is modeled with LSM distributions, and both the hidden scale parameters and the impulse noise are jointly estimated to adaptively characterize the real noise. To exploit the nonlocal self-similarity and low-rank nature of natural image, a nonlocal low-rank regularization is adopted to regularize the denoising process. Experimental results on synthetic noisy images show that the proposed method outperforms existing mixture noise removal methods.

Iterative Re-Constrained Group Sparse Face Recognition With Adaptive Weights Learning

In this paper, we consider the robust face recognition problem via iterative re-constrained group sparse classifier (IRGSC) with adaptive weights learning. Specifically, we propose a group sparse representation classification (GSRC) approach in which weighted features and groups are collaboratively adopted to encode more structure information and discriminative information than other regression based methods. In addition, we derive an efficient algorithm to optimize the proposed objective function, and theoretically prove the convergence. There are several appealing aspects associated with IRGSC. First, adaptively learned weights can be seamlessly incorporated into the GSRC framework. This integrates the locality structure of the data and validity information of the features into l_2,p -norm regularization to form a unified formulation. Second, IRGSC is very flexible to different size of training set as well as feature dimension thanks to the l_2,p -norm regularization. Third, the derived solution is proved to be a stationary point (globally optimal if p ≥ 1 ). Comprehensive experiments on representative data sets demonstrate that IRGSC is a robust discriminative classifier which significantly improves the performance and efficiency compared with the state-of-the-art methods in dealing with face occlusion, corruption, and illumination changes, and so on.

Weighted Joint Sparse Representation for Removing Mixed Noise in Image

Joint sparse representation (JSR) has shown great potential in various image processing and computer vision tasks. Nevertheless, the conventional JSR is fragile to outliers. In this paper, we propose a weighted JSR (WJSR) model to simultaneously encode a set of data samples that are drawn from the same subspace but corrupted with noise and outliers. Our model is desirable to exploit the common information shared by these data samples while reducing the influence of outliers. To solve the WJSR model, we further introduce a greedy algorithm called weighted simultaneous orthogonal matching pursuit to efficiently approximate the global optimal solution. Then, we apply the WJSR for mixed noise removal by jointly coding the grouped nonlocal similar image patches. The denoising performance is further improved by incorporating it with the global prior and the sparse errors into a unified framework. Experimental results show that our denoising method is superior to several state-of-the-art mixed noise removal methods.