Anisotropic fourth-order diffusion regularization for multiframe super-resolution reconstruction

A novel rcgularization-based approach is presented for super-resolution reconstruction in order to achieve good tradeoff between noise removal and edge preservation. The method is developed by using L1 norm as data fidelity term and anisotropic fourth-order diffusion model as a regularization item to constrain the smoothness of the reconstructed images. To evaluate and prove the performance of the proposed method, series of experiments and comparisons with some existing methods including bi-cubic interpolation method and bilateral total variation method are carried out. Numerical results on synthetic data show that the PSNR improvement of the proposed method is approximately 1.0906 dB on average compared to bilateral total variation method, and the results on real videos indicate that the proposed algorithm is also effective in terms of removing visual artifacts and preserving edges in restored images.

Super-resolution reconstruction for license plate images of moving vehicles

A novel reconstruction method to improve the recognition of license plate texts of moving vehicles in real traffic videos is proposed, which fuses complimentary information among low resolution （LR） images to yield a high resolution （HR） image. Based on the regularization super-resolution （SR） reconstruction schemes, this paper first introduces a residual gradient （RG） term as a new regularization term to improve the quality of the reconstructed image. Moreover, L1 norm is used to measure the residual data （RD） term and the RG term in order to improve the robustness of the proposed method. Finally, the steepest descent method is exploited to solve the energy functional. Simulated and real acquired video sequence experiments show the effectiveness and practicability of the proposed method and demonstrate its superiority over the bi-cubic interpolation and discontinuity adaptive Markov random field （DAMRF） SR method in both signal to noise ratios （SNR） and visual effects.

A Hybrid Regularization-Based Multi-Frame Super-Resolution Using Bayesian Framework

The prime purpose for the image reconstruction of a multi-frame super-resolution is to reconstruct a higher-resolution image through incorporating the knowledge obtained from a series of relevant low-resolution images,which is useful in numerousfields.Nevertheless,super-resolution image reconstruction methods are usually damaged by undesirable restorative artifacts,which include blurring distortion,noises,and stair-casing effects.Consequently,it is always challenging to achieve balancing between image smoothness and preservation of the edges inside the image.In this research work,we seek to increase the effectiveness of multi-frame super-resolution image reconstruction by increasing the visual information and improving the automated machine perception,which improves human analysis and interpretation processes.Accordingly,we propose a new approach to the image reconstruction of multi-frame super-resolution,so that it is created through the use of the regularization framework.In the proposed approach,the bilateral edge preserving and bilateral total variation regularizations are employed to approximate a high-resolution image generated from a sequence of corresponding images with low-resolution to protect significant features of an image,including sharp image edges and texture details while preventing artifacts.The experimental results of the synthesized image demonstrate that the new proposed approach has improved efficacy both visually and numerically more than other approaches.

Single frame super-resolution reconstruction based on sparse representation

In order to effectively improve the quality of recovered images, a single frame super-resolution reconstruction method based on sparse representation is proposed. The combination method of local orientation estimation-based image patch clustering and principal component analysis is used to obtain a series of geometric dictionaries of different orientations in the dictionary learning process. Subsequently, the dictionary of the nearest orientation is adaptively assigned to each of the input patches that need to be represented in the sparse coding process. Moreover, the consistency of gradients is further incorporated into the basic framework to make more substantial progress in preserving more fine edges and producing sharper results. Two groups of experiments on different types of natural images indicate that the proposed method outperforms some state-of- the-art counterparts in terms of both numerical indicators and visual quality.

Super-resolution reconstruction of synthetic-aperture radar image using adaptive-threshold singular value decomposition technique

A super-resolution reconstruction approach of （SVD） technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. First, radar imaging model and super-resolution reconstruction mechanism were outlined. Then, the adaptive-threshold SVD super-resolution algorithm, and its two key aspects, namely the determination method of point spread function （PSF） matrix T and the selection scheme of singular value threshold, were presented. Finally, the super-resolution algorithm was demonstrated successfully using the measured synthetic-aperture radar （SAR） images, and a Monte Carlo assessment was carried out to evaluate the performance of the algorithm by using the input/output signal-to-noise ratio （SNR）. Five versions of SVD algorithms, namely 1 ） using all singular values, 2） using the top 80% singular values, 3） using the top 50% singular values, 4） using the top 20% singular values and 5） using singular values s such that S2≥/max（s2）/rinsNR were tested. The experimental results indicate that when the singular value threshold is set as Smax/（rinSNR）1/2, the super-resolution algorithm provides a good compromise between too much noise and too much bias and has good reconstruction results.

Image super-resolution reconstruction based on sparse representation and residual compensation

A super-resolution reconstruction algorithm is proposed. The algorithm is based on the idea of the sparse representation of signals, by using the fact that the sparsest representation of a sig- nal is unique as the constraint of the patched-based reconstruction, and compensating residual errors of the reconstruction results both locally and globally to solve the distortion problem in patch-based reconstruction algorithms. Three reconstruction algorithms are compared. The results show that the images reconstructed with the new algorithm have the best quality.

Super-resolution image reconstruction based on three-step-training neural networks

A new method of super-resolution image reconstruction is proposed, which uses a three-step-training error backpropagation neural network （BPNN） to realize the super-resolution reconstruction （SRR） of satellite image. The method is based on BPNN. First, three groups learning samples with different resolutions are obtained according to image observation model, and then vector mappings are respectively used to those three group learning samples to speed up the convergence of BPNN, at last, three times consecutive training are carried on the BPNN. Training samples used in each step are of higher resolution than those used in the previous steps, so the increasing weights store a great amount of information for SRR, and network performance and generalization ability are improved greatly. Simulation and generalization tests are carried on the well-trained three-step-training NN respectively, and the reconstruction results with higher resolution images verify the effectiveness and validity of this method.

Multi-channel fast super-resolution image reconstruction based on matrix observation model

A multi-channel fast super-resolution image reconstruction algorithm based on matrix observation model is proposed in the paper,which consists of three steps to avoid the computational complexity: a single image SR reconstruction step,a registration step and a wavelet-based image fusion. This algorithm decomposes two large matrixes to the tensor product of two little matrixes and uses the natural isomorphism between matrix space and vector space to transform cost function based on matrix-vector products model to matrix form. Furthermore,we prove that the regularization part can be transformed to the matrix formed. The conjugate-gradient method is used to solve this new model. Finally,the wavelet fusion is used to integrate all the registered highresolution images obtained from the single image SR reconstruction step. The proposed algorithm reduces the storage requirement and the calculating complexity,and can be applied to large-dimension low-resolution images.

A NOVEL METHOD TO REALIZE COMPRESSED VIDEO SUPER-RESOLUTION RECONSTRUCTION

This letter proposes a novel method of compressed video super-resolution reconstruction based on MAP-POCS (Maximum Posterior Probability-Projection Onto Convex Set). At first assuming the high-resolution model subject to Poisson-Markov distribution, then constructing the projecting convex based on MAP. According to the characteristics of compressed video, two different convexes are constructed based on integrating the inter-frame and intra-frame information in the wavelet-domain. The results of the experiment demonstrate that the new method not only outperforms the traditional algorithms on the aspects of PSNR (Peak Signal-to-Noise Ratio), MSE (Mean Square Error) and reconstruction vision effect, but also has the advantages of rapid convergence and easy extension.

Super-resolution reconstruction based on CNN:A case study of Jilin-1 multispectral data

MS or MS+PAN is usually applied separately in convolutional neural network(CNN)resolution reconstruction to obtain high-resolution MS images,but the difference between the two datasets is rarely studied.This paper introduced a dual-channel network and took MS and MS+PAN of Jilin-1 spectrum satellites as two datasets to evaluate the performance of CNN resolution reconstruction,and analyzed the difference with bicubic and GS methods.The result of CNN reconstruction shows that MS+PAN dataset performed better than MS,with about 6%improvement in spatial and spectral components,and the overall quality of MS+PAN dataset was slightly higher than that of MS dataset,with QNR from 0.9559 to 0.9584.The bicubic performed best in spectral components with the quality value of 0.017,and GS performed best in spatial components with the quality values of 0.0443.CNN showed similar performance in spectral and spatial components with the two traditional methods and achieved the best overall quality with QNR value of 0.9584.

Variational regularization method of solving the Cauchy problem for Laplace's equation: Innovation of the Grad–Shafranov(GS) reconstruction

The simplified linear model of Grad-Shafranov （GS） reconstruction can be reformulated into an inverse boundary value problem of Laplace＇s equation. Therefore, in this paper we focus on the method of solving the inverse boundary value problem of Laplace＇s equation. In the first place, the variational regularization method is used to deal with the ill- posedness of the Cauchy problem for Laplace＇s equation. Then, the ＇L-Curve＇ principle is suggested to be adopted in choosing the optimal regularization parameter. Finally, a numerical experiment is implemented with a section of Neumann and Dirichlet boundary conditions with observation errors. The results well converge to the exact solution of the problem, which proves the efficiency and robustness of the proposed method. When the order of observation error δ is 10-1, the order of the approximate result error can reach 10-3.

Transformer and GAN-Based Super-Resolution Reconstruction Network for Medical Images

Super-resolution reconstruction in medical imaging has become more demanding due to the necessity of obtaining high-quality images with minimal radiation dose,such as in low-field magnetic resonance imaging(MRI).However,image super-resolution reconstruction remains a difficult task because of the complexity and high textual requirements for diagnosis purpose.In this paper,we offer a deep learning based strategy for reconstructing medical images from low resolutions utilizing Transformer and generative adversarial networks(T-GANs).The integrated system can extract more precise texture information and focus more on important locations through global image matching after successfully inserting Transformer into the generative adversarial network for picture reconstruction.Furthermore,we weighted the combination of content loss,adversarial loss,and adversarial feature loss as the final multi-task loss function during the training of our proposed model T-GAN.In comparison to established measures like peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM),our suggested T-GAN achieves optimal performance and recovers more texture features in super-resolution reconstruction of MRI scanned images of the knees and belly.

Deep-learning-based methods for super-resolution fluorescence microscopy

The algorithm used for reconstruction or resolution enhancement is one of the factors affectingthe quality of super-resolution images obtained by fluorescence microscopy.Deep-learning-basedalgorithms have achieved stateof-the-art performance in super-resolution fluorescence micros-copy and are becoming increasingly attractive.We firstly introduce commonly-used deep learningmodels,and then review the latest applications in terms of the net work architectures,the trainingdata and the loss functions.Additionally,we discuss the challenges and limits when using deeplearning to analyze the fluorescence microscopic data,and suggest ways to improve the reliability and robustness of deep learning applications.

Source reconstruction for bioluminescence tomography via L_(1/2)regularization

Bioluminescence tomography(BLT)is an important noninvasive optical molecular imaging modality in preclinical research.To improve the image quality,reconstruction algorithms have to deal with the inherent ill-posedness of BLT inverse problem.The sparse characteristic of bioluminescent sources in spatial distribution has been widely explored in BLT and many L1-regularized methods have been investigated due to the sparsity-inducing properties of L1 norm.In this paper,we present a reconstruction method based on L_(1/2) regularization to enhance sparsity of BLT solution and solve the nonconvex L_(1/2) norm problem by converting it to a series of weighted L1 homotopy minimization problems with iteratively updated weights.To assess the performance of the proposed reconstruction algorithm,simulations on a heterogeneous mouse model are designed to compare it with three representative sparse reconstruction algorithms,including the weighted interior-point,L1 homotopy,and the Stagewise Orthogonal Matching Pursuit algorithm.Simulation results show that the proposed method yield stable reconstruction results under different noise levels.Quantitative comparison results demonstrate that the proposed algorithm outperforms the competitor algorithms in location accuracy,multiple-source resolving and image quality.

Electrical Impedance Tomography Image Reconstruction Using Iterative Lavrentiev and L-Curve-Based Regularization Algorithm

Electrical impedance tomography (EIT) is a technique for determining the electrical conductivity and permittivity distribution inside a medium from measurements made on its surface. The impedance distribution reconstruction in EIT is a nonlinear inverse problem that requires the use of a regularization method. The generalized Tikhonov regularization methods are often used in solving inverse problems. However, for EIT image reconstruction, the generalized Tikhonov regularization methods may lose the boundary information due to its smoothing operation. In this paper, we propose an iterative Lavrentiev regularization and L-curve-based algorithm to reconstruct EIT images. The regularization parameter should be carefully chosen, but it is often heuristically selected in the conventional regularization-based reconstruction algorithms. So, an L-curve-based optimization algorithm is used for selecting the Lavrentiev regularization parameter. Numerical analysis and simulation results are performed to illustrate EIT image reconstruction. It is shown that choosing the appropriate regularization parameter plays an important role in reconstructing EIT images.

TranSR-Ne RF:Super-resolution neural radiance field for reconstruction and rendering of weak and repetitive texture of aviation damaged functional surface

In order to reconstruct and render the weak and repetitive texture of the damaged functional surface of aviation,an improved neural radiance field,named TranSR-NeRF,is proposed.In this paper,a data acquisition system was designed and built.The acquired images generated initial point clouds through TransMVSNet.Meanwhile,after extracting features from the images through the improved SE-ConvNeXt network,the extracted features were aligned and fused with the initial point cloud to generate high-quality neural point cloud.After ray-tracing and sampling of the neural point cloud,the ResMLP neural network designed in this paper was used to regress the volume density and radiance under a given viewing angle,which introduced spatial coordinate and relative positional encoding.The reconstruction and rendering of arbitrary-scale super-resolution of damaged functional surface is realized.In this paper,the influence of illumination conditions and background environment on the model performance is also studied through experiments,and the comparison and ablation experiments for the improved methods proposed in this paper is conducted.The experimental results show that the improved model has good effect.Finally,the application experiment of object detection task is carried out,and the experimental results show that the model has good practicability.

Reconstruction of impact force of mechanical press in time domain

To overcome the difficulty in directly measuring the impact force of a mechanical press, the inverse theory is employed to reconstruct the impact force from the corresponding response data in time domain. The nature of ill-posedness of impact force reconstruction is explored through singular value decomposition （SVD） and the Tikhonov regularization is utilized to deal with the ill-posedness, in which the optimal parameter is chosen in light of the L-curve criterion and the generalized cross- validation （GCV）. The experimentally measured strain responses of upper and lower dies of the press are chosen as source data for impact force reconstruction, and the corresponding numerical results are compared with the experimental measurements, which verifies the effectiveness of the reconstruction method.

AN IMPROVED SPARSITY ADAPTIVE MATCHING PURSUIT ALGORITHM FOR COMPRESSIVE SENSING BASED ON REGULARIZED BACKTRACKING

Sparsity Adaptive Matching Pursuit (SAMP) algorithm is a widely used reconstruction algorithm for compressive sensing in the case that the sparsity is unknown. In order to match the sparsity more accurately, we presented an improved SAMP algorithm based on Regularized Backtracking (SAMP-RB). By adapting a regularized backtracking step to SAMP algorithm in each iteration stage, the proposed algorithm can flexibly remove the inappropriate atoms. The experimental results show that SAMP-RB reconstruction algorithm greatly improves SAMP algorithm both in reconstruction quality and computational time. It has better reconstruction efficiency than most of the available matching pursuit algorithms.

Research on the Application of Super Resolution Reconstruction Algorithm for Underwater Image

Underwater imaging is widely used in ocean,river and lake exploration,but it is affected by properties of water and the optics.In order to solve the lower-resolution underwater image formed by the influence of water and light,the image super-resolution reconstruction technique is applied to the underwater image processing.This paper addresses the problem of generating super-resolution underwater images by convolutional neural network framework technology.We research the degradation model of underwater images,and analyze the lower-resolution factors of underwater images in different situations,and compare different traditional super-resolution image reconstruction algorithms.We further show that the algorithm of super-resolution using deep convolution networks(SRCNN)which applied to super-resolution underwater images achieves good results.

Single color image super-resolution using sparse representation and color constraint

Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm(e.g.,L1 or L2).These methods have limited ability to keep image texture detail to some extent and are easy to cause the problem of blurring details and color artifacts in color reconstructed images.This paper presents a color super-resolution reconstruction method combining the L2/3 sparse regularization model with color channel constraints.The method converts the low-resolution color image from RGB to YCbCr.The L2/3 sparse regularization model is designed to reconstruct the brightness channel of the input low-resolution color image.Then the color channel-constraint method is adopted to remove artifacts of the reconstructed highresolution image.The method not only ensures the reconstruction quality of the color image details,but also improves the removal ability of color artifacts.The experimental results on natural images validate that our method has improved both subjective and objective evaluation.