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.

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.

Estimation-free spatial-domain image reconstruction of structured illumination microscopy

Structured illumination microscopy(SIM)achieves super-resolution(SR)by modulating the high-frequency information of the sample into the passband of the optical system and subsequent image reconstruction.The traditional Wiener-filtering-based reconstruction algorithm operates in the Fourier domain,it requires prior knowledge of the sinusoidal illumination patterns which makes the time-consuming procedure of parameter estimation to raw datasets necessary,besides,the parameter estimation is sensitive to noise or aberration-induced pattern distortion which leads to reconstruction artifacts.Here,we propose a spatial-domain image reconstruction method that does not require parameter estimation but calculates patterns from raw datasets,and a reconstructed image can be obtained just by calculating the spatial covariance of differential calculated patterns and differential filtered datasets(the notch filtering operation is performed to the raw datasets for attenuating and compensating the optical transfer function(OTF)).Experiments on reconstructing raw datasets including nonbiological,biological,and simulated samples demonstrate that our method has SR capability,high reconstruction speed,and high robustness to aberration and noise.

PSMFNet:Lightweight Partial Separation and Multiscale Fusion Network for Image Super-Resolution

The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)research.However,the high computational demands of most SR techniques hinder their applicability to edge devices,despite their satisfactory reconstruction performance.These methods commonly use standard convolutions,which increase the convolutional operation cost of the model.In this paper,a lightweight Partial Separation and Multiscale Fusion Network(PSMFNet)is proposed to alleviate this problem.Specifically,this paper introduces partial convolution(PConv),which reduces the redundant convolution operations throughout the model by separating some of the features of an image while retaining features useful for image reconstruction.Additionally,it is worth noting that the existing methods have not fully utilized the rich feature information,leading to information loss,which reduces the ability to learn feature representations.Inspired by self-attention,this paper develops a multiscale feature fusion block(MFFB),which can better utilize the non-local features of an image.MFFB can learn long-range dependencies from the spatial dimension and extract features from the channel dimension,thereby obtaining more comprehensive and rich feature information.As the role of the MFFB is to capture rich global features,this paper further introduces an efficient inverted residual block(EIRB)to supplement the local feature extraction ability of PSMFNet.A comprehensive analysis of the experimental results shows that PSMFNet maintains a better performance with fewer parameters than the state-of-the-art models.

Pyramid Separable Channel Attention Network for Single Image Super-Resolution

Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has significant research value and is widely used in fields such as medical imaging,satellite image processing,and security surveillance.Despite significant progress in existing research,challenges remain in reconstructing clear and complex texture details,with issues such as edge blurring and artifacts still present.The visual perception effect still needs further enhancement.Therefore,this study proposes a Pyramid Separable Channel Attention Network(PSCAN)for the SISR task.Thismethod designs a convolutional backbone network composed of Pyramid Separable Channel Attention blocks to effectively extract and fuse multi-scale features.This expands the model’s receptive field,reduces resolution loss,and enhances the model’s ability to reconstruct texture details.Additionally,an innovative artifact loss function is designed to better distinguish between artifacts and real edge details,reducing artifacts in the reconstructed images.We conducted comprehensive ablation and comparative experiments on the Arabidopsis root image dataset and several public datasets.The experimental results show that the proposed PSCAN method achieves the best-known performance in both subjective visual effects and objective evaluation metrics,with improvements of 0.84 in Peak Signal-to-Noise Ratio(PSNR)and 0.017 in Structural Similarity Index(SSIM).This demonstrates that the method can effectively preserve high-frequency texture details,reduce artifacts,and have good generalization performance.

Multi-prior physics-enhanced neural network enables pixel super-resolution and twin-imagefree phase retrieval from single-shot hologram

Digital in-line holographic microscopy(DIHM)is a widely used interference technique for real-time reconstruction of living cells’morphological information with large space-bandwidth product and compact setup.However,the need for a larger pixel size of detector to improve imaging photosensitivity,field-of-view,and signal-to-noise ratio often leads to the loss of sub-pixel information and limited pixel resolution.Additionally,the twin-image appearing in the reconstruction severely degrades the quality of the reconstructed image.The deep learning(DL)approach has emerged as a powerful tool for phase retrieval in DIHM,effectively addressing these challenges.However,most DL-based strategies are datadriven or end-to-end net approaches,suffering from excessive data dependency and limited generalization ability.Herein,a novel multi-prior physics-enhanced neural network with pixel super-resolution(MPPN-PSR)for phase retrieval of DIHM is proposed.It encapsulates the physical model prior,sparsity prior and deep image prior in an untrained deep neural network.The effectiveness and feasibility of MPPN-PSR are demonstrated by comparing it with other traditional and learning-based phase retrieval methods.With the capabilities of pixel super-resolution,twin-image elimination and high-throughput jointly from a single-shot intensity measurement,the proposed DIHM approach is expected to be widely adopted in biomedical workflow and industrial measurement.

Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction

Photoacoustic imaging(PAI)is a noninvasive emerging imaging method based on the photoacoustic effect,which provides necessary assistance for medical diagnosis.It has the characteristics of large imaging depth and high contrast.However,limited by the equipment cost and reconstruction time requirements,the existing PAI systems distributed with annular array transducers are difficult to take into account both the image quality and the imaging speed.In this paper,a triple-path feature transform network(TFT-Net)for ring-array photoacoustic tomography is proposed to enhance the imaging quality from limited-view and sparse measurement data.Specifically,the network combines the raw photoacoustic pressure signals and conventional linear reconstruction images as input data,and takes the photoacoustic physical model as a prior information to guide the reconstruction process.In addition,to enhance the ability of extracting signal features,the residual block and squeeze and excitation block are introduced into the TFT-Net.For further efficient reconstruction,the final output of photoacoustic signals uses‘filter-then-upsample’operation with a pixel-shuffle multiplexer and a max out module.Experiment results on simulated and in-vivo data demonstrate that the constructed TFT-Net can restore the target boundary clearly,reduce background noise,and realize fast and high-quality photoacoustic image reconstruction of limited view with sparse sampling.

Accelerating SAGE algorithm in PET image reconstruction by rescaled block-iterative method

A new method to accelerate the convergent rate of the space-alternatinggeneralized expectation-maximization (SAGE) algorithm is proposed. The new rescaled block-iterativeSAGE (RBI-SAGE) algorithm combines the RBI algorithm with the SAGE algorithm for PET imagereconstruction. In the new approach, the projection data is partitioned into disjoint blocks; eachiteration step involves only one of these blocks. SAGE updates the parameters sequentially in eachblock. In experiments, the RBI-SAGE algorithm and classical SAGE algorithm are compared in theapplication on positron emission tomography (PET) image reconstruction. Simulation results show thatRBI-SAGE has better performance than SAGE in both convergence and image quality.

Training image analysis for three-dimensional reconstruction of porous media

In order to obtain a better sandstone three-dimensional （3D） reconstruction result which is more similar to the original sample, an algorithm based on stationarity for a two-dimensional （2D） training image is proposed. The second-order statistics based on texture features are analyzed to evaluate the scale stationarity of the training image. The multiple-point statistics of the training image are applied to obtain the multiple-point statistics stationarity estimation by the multi-point density function. The results show that the reconstructed 3D structures are closer to reality when the training image has better scale stationarity and multiple-point statistics stationarity by the indications of local percolation probability and two-point probability. Moreover, training images with higher multiple-point statistics stationarity and lower scale stationarity are likely to obtain closer results to the real 3D structure, and vice versa. Thus, stationarity analysis of the training image has far-reaching significance in choosing a better 2D thin section image for the 3D reconstruction of porous media. Especially, high-order statistics perform better than low-order statistics.

Investigation of prior image constrained compressed sensing-based spectral X-ray CT image reconstruction

To improve spectral X-ray CT reconstructed image quality, the energy-weighted reconstructed image xbins^W and the separable paraboloidal surrogates（SPS） algorithm are proposed for the prior image constrained compressed sensing（PICCS）-based spectral X-ray CT image reconstruction. The PICCS-based image reconstruction takes advantage of the compressed sensing theory, a prior image and an optimization algorithm to improve the image quality of CT reconstructions.To evaluate the performance of the proposed method, three optimization algorithms and three prior images are employed and compared in terms of reconstruction accuracy and noise characteristics of the reconstructed images in each energy bin.The experimental simulation results show that the image xbins^W is the best as the prior image in general with respect to the three optimization algorithms; and the SPS algorithm offers the best performance for the simulated phantom with respect to the three prior images. Compared with filtered back-projection（FBP）, the PICCS via the SPS algorithm and xbins^W as the prior image can offer the noise reduction in the reconstructed images up to 80. 46%, 82. 51%, 88. 08% in each energy bin,respectively. M eanwhile, the root-mean-squared error in each energy bin is decreased by 15. 02%, 18. 15%, 34. 11% and the correlation coefficient is increased by 9. 98%, 11. 38%,15. 94%, respectively.

Model-driven CT reconstruction algorithm for nano-resolution x-ray phase contrast imaging

The low-density imaging performance of a zone plate-based nano-resolution hard x-ray computed tomography(CT)system can be significantly improved by incorporating a grating-based Lau interferometer. Due to the diffraction, however,the acquired nano-resolution phase signal may suffer splitting problem, which impedes the direct reconstruction of phase contrast CT(nPCT) images. To overcome, a new model-driven nPCT image reconstruction algorithm is developed in this study. In it, the diffraction procedure is mathematically modeled into a matrix B, from which the projections without signal splitting can be generated invertedly. Furthermore, a penalized weighted least-square model with total variation(PWLSTV) is employed to denoise these projections, from which nPCT images with high accuracy are directly reconstructed.Numerical experiments demonstrate that this new algorithm is able to work with phase projections having any splitting distances. Moreover, results also reveal that nPCT images of higher signal-to-noise-ratio(SNR) could be reconstructed from projections having larger splitting distances. In summary, a novel model-driven nPCT image reconstruction algorithm with high accuracy and robustness is verified for the Lau interferometer-based hard x-ray nano-resolution phase contrast imaging.

Image reconstruction based on total-variation minimization and alternating direction method in linear scan computed tomography

Linear scan computed tomography （LCT） is of great benefit to online industrial scanning and security inspection due to its characteristics of straight-line source trajectory and high scanning speed. However, in practical applications of LCT, there are challenges to image reconstruction due to limited-angle and insufficient data. In this paper, a new reconstruction algorithm based on total-variation （TV） minimization is developed to reconstruct images from limited-angle and insufficient data in LCT. The main idea of our approach is to reformulate a TV problem as a linear equality constrained problem where the objective function is separable, and then minimize its augmented Lagrangian function by using alternating direction method （ADM） to solve subproblems. The proposed method is robust and efficient in the task of reconstruction by showing the convergence of ADM. The numerical simulations and real data reconstructions show that the proposed reconstruction method brings reasonable performance and outperforms some previous ones when applied to an LCT imaging problem.

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 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.

An algorithm for computed tomography image reconstruction from limited-view projections

With the development of the compressive sensing theory, the image reconstruction from the projections viewed in limited angles is one of the hot problems in the research of computed tomography technology. This paper develops an iterative algorithm for image reconstruction, which can fit the most cases. This method gives an image reconstruction flow with the difference image vector, which is based on the concept that the difference image vector between the reconstructed and the reference image is sparse enough. Then the l1-norm minimization method is used to reconstruct the difference vector to recover the image for flat subjects in limited angles. The algorithm has been tested with a thin planar phantom and a real object in limited-view projection data. Moreover, all the studies showed the satisfactory results in accuracy at a rather high reconstruction speed.

Hyperspectral Image Super-Resolution Meets Deep Learning:A Survey and Perspective

Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,which is beneficial for subsequent applications.The development of deep learning has promoted significant progress in hyperspectral image super-resolution,and the powerful expression capabilities of deep neural networks make the predicted results more reliable.Recently,several latest deep learning technologies have made the hyperspectral image super-resolution method explode.However,a comprehensive review and analysis of the latest deep learning methods from the hyperspectral image super-resolution perspective is absent.To this end,in this survey,we first introduce the concept of hyperspectral image super-resolution and classify the methods from the perspectives with or without auxiliary information.Then,we review the learning-based methods in three categories,including single hyperspectral image super-resolution,panchromatic-based hyperspectral image super-resolution,and multispectral-based hyperspectral image super-resolution.Subsequently,we summarize the commonly used hyperspectral dataset,and the evaluations for some representative methods in three categories are performed qualitatively and quantitatively.Moreover,we briefly introduce several typical applications of hyperspectral image super-resolution,including ground object classification,urban change detection,and ecosystem monitoring.Finally,we provide the conclusion and challenges in existing learning-based methods,looking forward to potential future research directions.

Three-dimensional positions of scattering centers reconstruction from multiple SAR images based on radargrammetry

A method and procedure is presented to reconstruct three-dimensional(3D) positions of scattering centers from multiple synthetic aperture radar(SAR) images. Firstly, two-dimensional(2D) attribute scattering centers of targets are extracted from 2D SAR images. Secondly, similarity measure is developed based on 2D attributed scatter centers' location, type, and radargrammetry principle between multiple SAR images. By this similarity, we can associate 2D scatter centers and then obtain candidate 3D scattering centers. Thirdly, these candidate scattering centers are clustered in 3D space to reconstruct final 3D positions. Compared with presented methods, the proposed method has a capability of describing distributed scattering center, reduces false and missing 3D scattering centers, and has fewer restrictionson modeling data. Finally, results of experiments have demonstrated the effectiveness of the proposed method.

Towards novel regularization approaches to PET image reconstruction

The purpose of this study is to introduce a novel empirical iterative algorithm for medical image reconstruction, under the short name MRP-ISWLS (Median Root Prior Image Space Weighted Least Squares). Further, we assess the performance of the new algorithm by comparing it to the simultaneous version of known MRP algorithms. All algorithms are compared in terms of cross-correlation and CNRs (Contrast-to-Noise Ratios). As it turns out, MRP-ISWLS presents higher CNRs than the known algorithms for objects of different size. Also MRP-ISWLS has better noise manipulation.