Parallel Multispectral Image Super-resolution Based on Sparse Representations

We present a self-learning approach for single image super-resolution (SR), with the ability to preserve high frequency components such as edges in resulting high resolution (HR) images. Given a low-resolution (LR) input image, we construct its image pyramid and produce a super pixel dataset. By extracting context information from the super-pixels, we propose to deploy context-specific contour let transform on them in order to model the relationship (via support vector regression) between the input patches and their associated directional high-frequency responses. These learned models are applied to predict the SR output with satisfactory quality. Unlike prior learning-based SR methods, our approach advances a self-learning technique and does not require the self similarity of image patches within or across image scales. More importantly, we do not need to collect training LR/HR image data in advance and only require a single LR input image. Empirical results verify the effectiveness of our approach, which quantitatively and qualitatively outperforms existing interpolation or learning-based SR methods.

Recent deep learning approaches in single image super-resolution (SISR) can generate high-definition textures for super-resolved (SR) images. However, they tend to hallucinate fake textures and even produce artifacts. An alternative to SISR, reference-based SR (RefSR) approaches use high-resolution (HR) reference (Ref) images to provide HR details that are missing in the low-resolution (LR) input image. We propose a novel framework that leverages existing SISR approaches and enhances them with RefSR. Specifically, we refine the output of SISR methods using neural texture transfer, where HR features are queried from the Ref images. The query is conducted by computing the similarity of textural and semantic features between the input image and the Ref images. The most similar HR features, patch-wise, to the LR image is used to augment the SR image through an augmentation network. In the case of dissimilar Ref images from the LR input image, we prevent performance degradation by including the similarity scores in the input features of the network. Furthermore, we use random texture patches during the training to condition our augmentation network to not always trust the queried texture features. Different from past RefSR approaches, our method can use arbitrary Ref images and its lower-bound performance is based on the SR image. We showcase that our method drastically improves the performance of the base SISR approach.

This chapter concentrates the problem of recovery a high-resolution (HR) image from a single low-resolution input image. Recent research proposed to deal with the image super-resolution problem with sparse coding, which is based on the well reconstruction of any local image patch by a sparse linear combination of an appropriately chosen over-complete dictionary. Therein the chosen LR (Low-resolution) and HR (High-resolution) dictionaries have to be exactly corresponding for well reconstructing the local image patterns. However, the conventional sparse coding based image super-resolution usually achieves a global dictionary D=[D l ; D h ] by jointly training the concatenated LR and HR local image patches, and then reconstruct the LR and HR image as a linear combination of the separated D l and D h . This strategy only can achieve the global minimum reconstructing error of LR and HR local patches, and usually cannot obtain the exactly corresponding LR and HR dictionaries. In addition, the accurate coefficients for reconstructing the HR image patch using HR dictionary D h are also unable to be estimated using only the LR input and the LR dictionary D l . Therefore, this paper proposes to firstly learn the HR dictionary D h from the features of the training HR local patches, and then propagates the HR dictionary to the LR one, called as HR2LR dictionary propagation, by mathematical proving and statistical analysis. The effectiveness of the proposed HR2LR dictionary propagation in sparse coding for super-resolution is demonstrated by comparison with the conventional super-resolution approaches such as sparse coding and interpolation.

In this paper we propose a technique for obtaining a high resolution (HR) image from a single low resolution (LR) image -using joint learning dictionary - on the basis of image statistic research. It suggests that with an appropriate choice of an over-complete dictionary, image patches can be well represented as a sparse linear combination. Medical imaging for clinical analysis and medical intervention is being used for creating visual representations of the interior of a body, as well as visual representation of the function of some organs or tissues (physiology). A number of medical imaging techniques are in use like MRI, CT scan, X-rays and Optical Coherence Tomography (OCT). OCT is one of the new technologies in medical imaging and one of its uses is in ophthalmology where it is being used for analysis of the choroidal thickness in the eyes in healthy and disease states such as age-related macular degeneration, central serous chorioretinopathy, diabetic retinopathy and inherited retinal dystrophies. We have proposed a technique for enhancing the OCT images which can be used for clearly identifying and analyzing the particular diseases. Our method uses dictionary learning technique for generating a high resolution image from a single input LR image. We train two joint dictionaries, one with OCT images and the second with multiple different natural images, and compare the results with previous SR technique. Proposed method for both dictionaries produces HR images which are comparatively superior in quality with the other proposed method of SR. Proposed technique is very effective for noisy OCT images and produces up-sampled and enhanced OCT images.

In this paper single image superresolution problem using sparse data representation is described. Image super-resolution is ill - posed inverse problem. Several methods have been proposed in the literature starting from simple interpolation techniques to learning based approach and under various regularization frame work. Recently many researchers have shown interest to super-resolve the image using sparse image representation. We slightly modified the procedure described by a similar work proposed recently. The modification suggested in the proposed approach is the method of dictionary training, feature extraction from the trained data base images and regularization. We have used singular values as prior for regularizing the ill-posed nature of the single image superresolution problem. Method of Optimal Directions algorithm (MOD) has been used in the proposed algorithm for obtaining high resolution and low resolution dictionaries from training image patches. Using the two dictionaries the given low resolution input image is superresolved. The results of the proposed algorithm showed improvements in visual, PSNR, RMSE and SSIM metrics over other similar methods.

Underwater target detecting is an important technique for the development of the ocean engineering and exploration also a significant task of the ocean detecting. It plays a substantial role not only for the civil economy but also for the national security. The formation of the super-resolution underwater image is significant topic in ocean detecting field. In order to enhance the visual quality of images obtained by underwater imaging systems, super resolution (SR) reconstruction is introduced, including single-frame and multi-frame SR algorithms. Real-world images often contain singularities such as edges and high-frequency textured regions. As a result, these methods suffer from various edge-related visual artifacts such as ringing, aliasing, jagging, and blurring we mainly focus on super-resolution from single low resolution input image. The goal of single image super-resolution is to estimate a high resolution image from a low resolution input. In this paper, we propose a new high-quality and efficient single-image upscaling technique.

Super-resolution (SR) has become more vital, because of its capability to generate high-quality ultra-high definition (UHD) high-resolution (HR) images from low-resolution (LR) input images. Conventional SR methods entail high computational complexity, which makes them difficult to be implemented for up-scaling of full-high-definition input images into UHD-resolution images. Nevertheless, our previous super-interpolation (SI) method showed a good compromise between Peak-Signal-to-Noise Ratio (PSNR) performances and computational complexity. However, since SI only utilizes simple linear mappings, it may fail to precisely reconstruct HR patches with complex texture. In this paper, we present a novel SR method, which inherits the large-to-small patch conversion scheme from SI but uses global regression based on local linear mappings (GLM). Thus, our new SR method is called GLM-SI. In GLM-SI, each LR input patch is divided into 25 overlapped subpatches. Next, based on the local properties of these subpatches, 25 different local linear mappings are applied to the current LR input patch to generate 25 HR patch candidates, which are then regressed into one final HR patch using a global regressor. The local linear mappings are learned cluster-wise in our off-line training phase. The main contribution of this paper is as follows: Previously, linear-mapping-based conventional SR methods, including SI only used one simple yet coarse linear mapping to each patch to reconstruct its HR version. On the contrary, for each LR input patch, our GLM-SI is the first to apply a combination of multiple local linear mappings, where each local linear mapping is found according to local properties of the current LR patch. Therefore, it can better approximate nonlinear LR-to-HR mappings for HR patches with complex texture. Experiment results show that the proposed GLM-SI method outperforms most of the state-of-the-art methods, and shows comparable PSNR performance with much lower computational complexity when compared with a super-resolution method based on convolutional neural nets (SRCNN15). Compared with the previous SI method that is limited with a scale factor of 2, GLM-SI shows superior performance with average 0.79 dB higher in PSNR, and can be used for scale factors of 3 or higher.

Super-resolution (SR) reconstruction is a technique to yield a higher resolution (HR) image from aliasing low resolution (LR) ones. An LR image is upsampled as the initialization, and then iteratively corrected in comparison with the other LR images. As the solution satisfying the SR constraints is non-unique, it is impossible to recover the original HR details completely by SR techniques. The solution reconstructed is sensitive to the starting point, especially when LR observations are insufficient, and may converge to a local optimum point. SR images reconstructed with different initializations may diverge in different ways from the true HR image. The influence of the initial HR estimate has not been sufficiently addressed so far by existing SR methods. We will explore this initial image selection issue to improve the performance of SR reconstruction.

A new multi-frame image super resolution (SR) algorithm via Bayesian modeling with natural image prior modeled by fields of experts (FoE) is proposed. Multi-frame SR can be used to obtain a high resolution (HR) image from a set of degraded low resolution (LR) images without changing any hardware device. However, SR is well known to be an ill-posed problem. So state-of-the-art solutions usually formulate the problem with Bayesian modeling techniques, which infer the HR image based on not only the LR input images but also on prior information about the HR image. Current Bayesian SR approaches typically use simple prior models such as L1 norm, TV prior and Laplacian prior, which cannot exploit the statistics of natural scenes well. In this paper, a Bayesian multi-frame image SR approach using a FOE model as the prior for natural images is presented. The Maximum a Posteriori (MAP) framework is used for estimating the HR image. The proposed method cannot only capture the statistics of natural images well, but also require less computational power than the other Bayesian modelling methods such as Sampling methods and Approximate inference. The proposed method shows superior or comparable results to the state-of-art multi-frame SR methods.

Sparse representation-based single image super-resolution (SISR) methods use a coupled overcomplete dictionary trained from high-resolution images/image patches. Since remote sensing (RS) satellites capture images of large areas, these images usually have poor spatial resolution and obtaining an effective dictionary as such would be very challenging. Moreover, traditional patch-based sparse representation models for reconstruction tend to give unstable sparse solution and produce visual artefact in the recovered images. To mitigate these problems, in this article, we have proposed an adaptive joint sparse representation-based SISR method that is dependent only on the input low-resolution image for dictionary training and sparse reconstruction. The new model combines patch-based local sparsity and group sparse representation-based nonlocal sparsity in a single framework, which helps in stabilizing the sparse solution and improve the SISR results. The experimental results are evaluated both visually and quantitatively for several RGB and multispectral RS datasets, where the proposed method shows improvements in peak signal-to-noise ratio by 1–4 dB and 2–3 dB over the state-of-the-art sparse representation- and deep learning-based SR methods, respectively. Land cover classification applied on the super-resolved images further validate the advantages of the proposed method. Finally, for practical RS applications, we have performed parallel implementation in general purpose graphics processing units and achieved significant speed ups (30–40×) in the execution time.

Resolution enhancement (RE) schemes (which are not based on wavelets) suffer from the drawback of losing high-frequency contents (which results in blurring). The discrete-wavelet-transform-based (DWT) RE scheme generates artifacts (due to a DWT shift-variant property). A wavelet-domain approach based on dual-tree complex wavelet transform (DT-CWT) and nonlocal means (NLM) is proposed for RE of the satellite images. A satellite input image is decomposed by DT-CWT (which is nearly shift invariant) to obtain high-frequency subbands. The high-frequency subbands and the low-resolution (LR) input image are interpolated using the Lanczos interpolator. The high-frequency subbands are passed through an NLM filter to cater for the artifacts generated by DT-CWT (despite of its nearly shift invariance). The filtered high-frequency subbands and the LR input image are combined using inverse DT-CWT to obtain a resolution-enhanced image. Objective and subjective analyses reveal superiority of the proposed technique over the conventional and state-of-the-art RE techniques.

Image super-resolution (SR) reconstruction technology can improve the quality of low-resolution (LR) images. There are many available deep learning networks different from traditional machine learning algorithms. However, these networks are usually prone to poor performance on complex computation, vanishing gradients, and loss of useful information. In this work, we propose a sub-pixel convolutional neural network (SPCNN) for image SR reconstruction. First, to reduce the strong correlation, the RGB mode was translated into YCbCr mode, and the Y channel data was chosen as the input LR image. Meanwhile, the LR image was chosen as the network input to reduce computation instead of the interpolation reconstructed image as used in the super-resolution convolutional neural network (SRCNN). Then, two convolution layers were built to obtain more features, and four non-linear mapping layers were used to achieve different level features. Furthermore, the residual network was introduced to transfer the feature information from the lower layer to the higher layer to avoid the gradient explosion or vanishing gradient phenomenon. Finally, the sub-pixel convolution layer based on up-sampling was designed to reduce the reconstruction time. Experiments on three different data sets proved that the proposed SPCNN performs superiorly to the Bicubic, sparsity constraint super-resolution (SCSR), anchored neighborhood regression (ANR), and SRCNN methods on reconstruction precision and time consumption.

Remote sensing images have been widely used in many scenarios. However, it is difficult to obtain high-resolution images from remote sensing images with the limitations of the sensors. The Zero-Shot Super-Resolution (ZSSR) method constructs the training set only by the input image itself, improving the performance while the blur kernels are unknown. The improvement is limited due to the limited information of the input image itself. In this paper, an enhanced zero-shot super-resolution is proposed to solve the problem of super-resolution(SR) reconstruction when the fuzzy kernel is unknown by downsampling the enhanced images of Content Adaptive Resampler(CAR) network to build the training set, and introducing the Convolutional Block Attention Module (CBAM) and the residual module to expand the network scale and optimizing the network structure. Experimental results on UCMerced_LandUses and other datasets show that, compared with ZSSR, the proposed method has better super-resolution reconstruction results in terms of image detail and image quality.

Super resolution imaging is to get high quality picture details either from multiple input images or from a single image. Currently researchers have developed several super resolution techniques to improve image quality. With evolution of broadband wireless technology and mobile device industry, the Mobile image processing has attracted researchers concern towards itself. In this paper we proposed a framework which focuses on utilizing Mobile Cloud Computing platform for the use of super resolution algorithms. Both super resolution imaging and mobile cloud computing are the most spotlighted research areas nowadays, so we intend to merge them in a way that researchers can get benefit from both of them. Super resolution algorithms (POCS, IBP, MAP, etc) are executed on the Cloud server, the mobile user will only to send the request (low resolution input images) to the cloud server, which will process his request accordingly and then send the high resolution image to the mobile user. The experimental results performed show the realization of our proposed framework.

Medical image super-resolution reconstruction algorithms based on deep learning: A survey