Image Super-resolution Reconstruction Method Research Articles

Target Image Processing based on Super-resolution Reconstruction and Machine Learning Algorithm

This article proposes a target image processing method based on super-resolution reconstruction and machine learning algorithms, which solves the low-resolution problem in medical images during imaging. This method uses nonlocal autoregressive learning based on a medical image super-resolution reconstruction method. The autoregressive model is introduced into the sparse representation-based medical image super-resolution reconstruction model by utilizing medical image data inherent nonlocal similarity characteristics. At the same time, a clustering algorithm is used to obtain a classification dictionary, improving experimental efficiency. The experimental results show that ten randomly selected CT/MR images are used as test images, and each image's peak signal-to-noise ratio and structural similarity values are calculated separately. Compared with other methods, the method proposed in this paper is significantly better and can achieve ideal results, with the highest value being 31.49. This method demonstrates the feasibility of using super-resolution reconstruction and machine learning algorithms in medical image resolution.

Super-resolution reconstruction method of the optical synthetic aperture image using generative adversarial network

Abstract In order to solve the contradiction between large aperture elements and high-resolution images, in this study, we propose an improved image-resolution method based on generative adversarial network (GAN). First, we analyze the imaging principle of the optical synthetic aperture. Further, we improve a super-resolution GAN; especially, this network uses a multi-scale convolutional cascade to obtain global features of the image, and a multi-scale receptive field block and residual in residual dense block are built to obtain image details. In addition, this study uses the Mish function as the activation function of the discriminator to solve the problems of neuron extreme, gradient explosion, and poor generalization ability of the model. Through simulation, the results show that the proposed method can achieve a peak signal-to-noise ratio (PSNR) of 30 dB compared with traditional image super-resolution reconstruction methods for synthetic aperture image. The method proposed has an improvement of 2 dB in the PSNR and 0.016 in structure similarity index measure compared with the original super-resolution GAN. Therefore, this method can effectively reduce the image distortion and improve the quality of image reconstruction.

Retracted: Image Super-Resolution Reconstruction Method for Lung Cancer CT-Scanned Images Based on Neural Network.

[This retracts the article DOI: 10.1155/2022/3543531.].

Large-field Astronomical Image Restoration and Superresolution Reconstruction using Deep Learning

The existing astronomical image restoration and superresolution reconstruction methods have problems such as low efficiency and poor results when dealing with images possessing large fields of view. Furthermore, these methods typically only handle fixed-size images and require step-by-step processing, which is inconvenient. In this paper, a neural network called Res&RecNet is proposed for the restoration and superresolution reconstruction of astronomical images with large fields of view for direct imaging instruments. This network performs feature extraction, feature correction, and progressive generation to achieve image restoration and superresolution reconstruction. The network is constructed using fully convolutional layers, allowing it to handle images of any size. The network can be trained using small samples and can perform image restoration and superresolution reconstruction in an end-to-end manner, resulting in high efficiency. Experimental results show that the network is highly effective in terms of processing astronomical images with complex scenes, generating image restoration results that improve the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) by 4.69 (dB)/0.073 and superresolution reconstruction results that improve the PSNR and SSIM by 1.97 (dB)/0.077 over those of the best existing algorithms, respectively.

Three-dimensional super-resolution range-gated imaging based on Gaussian-range-intensity model.

Current range-gated imaging methods based on triangular or trapezoidal models face significant limitations in terms of the accuracy and precision of three-dimensional (3D) reconstruction. Here, we establish a range-gated 3D super-resolution image reconstruction method based on a Gaussian-range-intensity model. A denoised optimization method for image preprocessing is established to improve the distance accuracy of the reconstruction. The experimental results show that the model can reduce the error of target distance by 64% and possess the reconstruction of multiple kinds of targets with a distance resolution of 1.5cm and lower noise, realizing better reconstruction results compared with the existing range-gated 3D imaging techniques.

A Lightweight Low-dose PET Image Super-resolution Reconstruction Method based on Convolutional Neural Network.

PET imaging is one of the most widely used neurological disease screening and diagnosis techniques. Since PET involves the radiation and tolerance of different people, the improvement that has always been focused on is to cut down radiation, in the meantime, ensuring that the generated images with low-dose tracer and generated images with standard-dose tracer have the same details of images. We propose a lightweight low-dose PET super-resolution network (SRPET-Net) based on a convolutional neural network. In this research, We propose a method for accurately recovering highresolution (HR) PET images from low-resolution (LR) PET images. The network learns the details and structure of the image between low-dose PET images and standard-dose PET images and, afterward, reconstructs the PET image by the trained network model. The experiments indicate that the SRPET-Net can achieve a superior peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) values. Moreover, our method has less memory consumption and lower computational cost. In our follow-up work, the technology can be applied to medical imaging in many different directions.

Improved Thermal Infrared Image Super-Resolution Reconstruction Method Base on Multimodal Sensor Fusion.

When traditional super-resolution reconstruction methods are applied to infrared thermal images, they often ignore the problem of poor image quality caused by the imaging mechanism, which makes it difficult to obtain high-quality reconstruction results even with the training of simulated degraded inverse processes. To address these issues, we proposed a thermal infrared image super-resolution reconstruction method based on multimodal sensor fusion, aiming to enhance the resolution of thermal infrared images and rely on multimodal sensor information to reconstruct high-frequency details in the images, thereby overcoming the limitations of imaging mechanisms. First, we designed a novel super-resolution reconstruction network, which consisted of primary feature encoding, super-resolution reconstruction, and high-frequency detail fusion subnetwork, to enhance the resolution of thermal infrared images and rely on multimodal sensor information to reconstruct high-frequency details in the images, thereby overcoming limitations of imaging mechanisms. We designed hierarchical dilated distillation modules and a cross-attention transformation module to extract and transmit image features, enhancing the network's ability to express complex patterns. Then, we proposed a hybrid loss function to guide the network in extracting salient features from thermal infrared images and reference images while maintaining accurate thermal information. Finally, we proposed a learning strategy to ensure the high-quality super-resolution reconstruction performance of the network, even in the absence of reference images. Extensive experimental results show that the proposed method exhibits superior reconstruction image quality compared to other contrastive methods, demonstrating its effectiveness.

Lucy Richardson and Mean Modified Wiener Filter for Construction of Super-Resolution Image

The ultimate goal of the Super-Resolution (SR) technique is to generate the High-Resolution (HR) image by combining the corresponding images with Low-Resolution (LR), which is utilized for different applications such as surveillance, remote sensing, medical diagnosis, etc. The original HR image may be corrupted due to various causes such as warping, blurring, and noise addition. SR image reconstruction methods are frequently plagued by obtrusive restorative artifacts such as noise, stair casing effect, and blurring. Thus, striking a balance between smoothness and edge retention is never easy. By enhancing the visual information and autonomous machine perception, this work presented research to improve the effectiveness of SR image reconstruction The reference image is obtained from DIV2K and BSD 100 dataset, these reference LR image is converted as composed LR image using the proposed Lucy Richardson and Modified Mean Wiener (LR-MMWF) Filters. The possessed LR image is provided as input for the stage of bicubic interpolation. Afterward, the initial HR image is obtained as output from the interpolation stage which is given as input for the SR model consisting of fidelity term to decrease residual between the projected HR image and detected LR image. At last, a model based on Bilateral Total Variation (BTV) prior is utilized to improve the stability of the HR image by refining the quality of the image. The results obtained from the performance analysis show that the proposed LR-MMW filter attained better PSNR and Structural Similarity (SSIM) than the existing filters. The results obtained from the experiments show that the proposed LR-MMW filter achieved better performance and provides a higher PSNR value of 31.65dB whereas the Filter-Net and 1D,2D CNN filter achieved PSNR values of 28.95dB and 31.63dB respectively.

DKFD: Optimizing Common Pediatric Dermatoses Detection with Novel Loss Function and Post-Processing

Using appropriate classification and recognition technology can help physicians make clinical diagnoses and decisions more effectively as a result of the ongoing development of artificial intelligence technology in the medical field. There are currently a number of issues with the detection of common pediatric dermatoses, including the challenge of image collection, the low resolution of some collected images, the intra-class variability and inter-class similarity of disease symptoms, and the mixing of disease symptom detection results. To resolve these problems, we first introduced the Random Online Data Augmentation and Selective Image Super-Resolution Reconstruction (RDA-SSR) method, which successfully avoids overfitting in training, to address the issue of the small dataset and low resolution of collected images, increase the number of images, and improve the image quality. Second, for the issue of an imbalance between difficult and simple samples, which is brought on by the variation within and between classes of disease signs during distinct disease phases. By increasing the loss contribution of hard samples for classification on the basis of the cross-entropy, we propose the DK_Loss loss function for two-stage object detection, allowing the model to concentrate more on the learning of hard samples. Third, in order to reduce redundancy and improve detection precision, we propose the Fliter_nms post-processing method for the intermingling of detection results based on the NMS algorithm. We created the CPD-10 image dataset for common pediatric dermatoses and used the Faster R-CNN network training findings as a benchmark. The experimental results show that the RDA-SSR technique, while needing a similar collection of parameters, can improve mAP by more than 4%. Furthermore, experiments were conducted over the CPD-10 dataset and PASCAL VOC2007 dataset to evaluate the effectiveness of DK_Loss over the two-stage object detection algorithm, and the results of cross-entropy loss-function-based training are used as baselines. The findings demonstrated that, with DK_Loss taken into account, its mAP is 1–2% above the baseline. Furthermore, the experiments confirmed that the Fliter_nms post-processing method can also improve model precision.

Semi-supervised super-resolution of diffusion-weighted images based on multiple references.

Spatial resolution of diffusion tensor images is usually compromised to accelerate the acquisitions, and the state-of-the-art (SOTA) image super-resolution (SR) reconstruction methods are commonly based on supervised learning models. Considering that matched low-resolution (LR) and high-resolution (HR) diffusion-weighted (DW) image pairs are not readily available, we propose a semi-supervised DW image SR reconstruction method based on multiple references (MRSR) extracted from other subjects. In MRSR, the prior information of multiple HR reference images is migrated into a residual-like network to assist SR reconstruction of DW images, and a CycleGAN-based semi-supervised strategy is used to train the network with 30% matched and 70% unmatched LR-HR image pairs. We evaluate the performance of the MRSR by comparing against SOTA methods on an HCP dataset in terms of the quality of reconstructed DW images and diffusion metrics. MRSR achieves the best performance, with the mean PSNR/SSIM of DW images being improved by at least 14.3%/28.8% and 1%/1.4% respectively relative to SOTA unsupervised and supervised learning methods, and with the fiber orientations deviating from the ground truth by about 6.28° on average, the RMSEs of fractional anisotropy, mean diffusivity, axial diffusivity and radial diffusivity being 3.0%, 4.6%, 5.7% and 4.5% respectively relative to the ground truth. We validate the effectiveness of the proposed network structure, multiple-reference and CycleGAN-based semi-supervised learning strategies for SR reconstruction of diffusion tensor images through the ablation studies. The proposed method allows us to achieve SR reconstruction for diffusion tensor images with a limited number of matched image pairs.

Comparative Analysis the Super-Resolution Image Generation Performance Based on BigGAN and VQ-VAE-2

Super-resolution image reconstruction has always been a popular research direction in the field of computer vision, which aims to recover high-resolution clear images from low-resolution images. Traditional super-resolution reconstruction algorithms mainly rely on the construction of constraints and the accuracy of registration between images to achieve the reconstruction effect, but their accuracy cannot meet the needs of practical applications with large multiples. Thanks to the rapid development of deep learning field, super-resolution image reconstruction based on deep learning has become the mainstream, and has achieved great success in reconstruction accuracy and speed. According to the different generative models used, the existing super-resolution image reconstruction methods mainly include two categories: GAN-based and VAEs-based. To quantitatively compare the limits of the two approaches' performance, this study selects two representative algorithms, BigGAN and VQ-VAE-2, and introduces the theoretical details and training process of these two methods, respectively. Furthermore, the reconstruction results of BigGAN and VQ-VAE-2 are further compared. Finally, this paper discusses the future development trend of super-resolution picture reconstruction with the current potential problems of BigGAN and VQ-VAE-2.

Image Super-Resolution Reconstruction Based on Residual Convolution and Double Attention Mechanism

Currently, single-image super-resolution reconstruction based on deep learning has achieved good results. To address the problems that most networks will have long training time, weak image learning ability and not fully utilizing the high frequency information of images, an image super-resolution reconstruction method based on residual convolution and double attention mechanism is proposed. The model performs deep feature extraction of the image by cascading deep convolutional networks, introduces local residual blocks to solve the model degradation brought by too many network parameters, and embeds the dual attention mechanism module in the residual blocks for adaptive calibration to adjust the feature map weights of each channel and the spatial correlation between features, so as to obtain deep texture detail information and reconstruct the feature image by sub-pixel convolutional layers to up sampling to reconstruct the high-resolution image. In the test sets of Set5 and Set14, peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) are used as evaluation indexes, while comparing SRCNN, FSRCNN and VDSR methods all reconstructed images with better results. The experimental results show that the method can effectively improve the utilization of high-frequency feature information and can increase the reconstruction capability of the images to a certain extent.

A visual measurement method of structural body vibration displacement combined with image deblurring

The visual vibration displacement measurement task is limited by the acquisition equipment or the acquisition environment, and there are still defects in the recognition rate. In this paper, starting from the aspect of enhancing the feature information of the input image, a visual measurement method for structural body vibration displacement is constructed combining deblurring and image feature enhancement. Aiming at problems such as blurring that may be encountered during image data acquisition, this paper designs a Multi-Scale Structural Body Image Deblurring Network (MSDNet) based on the Encoder–Decoder architecture to enhance the target feature details in the structural body image. MSDNet obtains more detailed feature information of the structural body by aggregating feature information at different scales in the Encoder–Decoder architecture. Meanwhile, this paper uses the super-resolution image reconstruction method in the Decoder stage instead of the upsampling method to better preserve the feature information of the underlying image. To verify the effectiveness of the method proposed in this paper, a variety of structural body vibration displacement image datasets were produced, and the sensor simultaneously collected structural body displacement data as standard data. The follow-up experiments can also be concluded that the image data after deblurring processing can have a better measurement accuracy of structural body vibration displacement.

Topology optimization using super-resolution image reconstruction methods

This paper proposes a new topology optimization method to obtain super-resolution images without increasing mesh refinement by using various methods. For traditional process, low-resolution (LR) images are fed into the Solid Isotropic Material with Penalization (SIMP) and Optimality Criteria (OC) methods. Here, the trained super-resolution images are added to the inner loops to reconstruct the topology and used to obtain high-resolution (HR) images from the LR images at the end of each iteration. After finishing the reconstruction process, the main topology optimization method recovers the original size images from the HR images for the next iteration. Several examples are presented to demonstrate the effectiveness of the proposed method. The final topologies provide noticeably improvement over those of typical SIMP method and create a much sharper and higher contrast images. Moreover, the proposed strategy using the super-resolution image reconstruction methods can give valuable innovation for conventional topology optimization process.

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 numerous fields. 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.

An Image Super-Resolution Reconstruction Method Based on PEGAN

In order to improve the accuracy and efficiency of super-resolution reconstruction of low-resolution images, a multi-scale and multi-stage self similar fusion image super-resolution reconstruction algorithm is proposed: firstly, the low-frequency features of the image are obtained by using the feature extraction network and used as the input of two sub networks, one of which obtains the structural feature information of low-resolution images through the coding network, Secondly, the high-frequency features are obtained through the multi-path feedforward network composed of stage feature fusion unit, in which the fusion unit fuses the features of several consecutive layers of the network and obtains effective features in an adaptive way; Finally, the residual block and the batch normalization layer unfavorable to the image super-resolution in the discriminator are removed. Spectral normalization is used in the generator and discriminator to reduce the computational overhead and stabilize the model training. The experimental results show that Our method makes the average PSNR of the reconstructed images on the two test data sets of Remo-A dataset and Remo-B dataset reach 27.95 dB and the average SSIM reach 0.771 without losing too much speed. This model draws lessons from the connection mode of dense network to strengthen the connection between network layers and connect the whole network through multipath connection, so as to make full use of the characteristics of hierarchical network, extract more high-frequency information and improve the quality of reconstruction. The texture of the reconstructed results is more real, the brightness is more accurate and more in line with the evaluation of human visual senses, which shows the effectiveness and superiority of the algorithm. It not only performs faster in reconstruction speed, but also improves the quality of reconstructed image effectively.

Research on Super-resolution Image Based on Deep Learning

Abstract Image super-resolution is a kind of important image processing technology in computer vision and image processing. It refers to the process of recovering high-resolution image from low-resolution image. It has a wide range of real-world applications, such as medical imaging, security and others. In addition to improving image perception quality, it also helps improve other computer vision tasks. Compared with traditional methods, deep learning methods show better reconstruction results in the field of image super-resolution reconstruction, and have gradually developed into the mainstream technology. This article will study the depth in the super resolution direction is important method of types of introduction, combed the main image super-resolution reconstruction method, expounds the depth study of several important super-resolution network model, the advantages and disadvantages of different algorithms and adaptive application scenarios are analyzed and compared, this paper expounds the different ways in the super resolution to liquidate, Finally, the potential problems of current image super-resolution reconstruction techniques are discussed, and the future development direction is prospected.

Single Image Super-Resolution Reconstruction with Preservation of Structure and Texture Details

In recent years, deep-learning-based single image super-resolution reconstruction has achieved good performance. However, most existing methods pursue a high peak signal-to-noise ratio (PSNR), while ignoring the quality of the structure and texture details, resulting in unsatisfactory performance of the reconstruction results in terms of human subjective perception. To solve this issue, this paper proposes a structure- and texture-preserving image super-resolution reconstruction method. Specifically, two different network branches are used to extract features for image structure and texture details. A dual-coordinate direction perception attention (DCDPA) mechanism is designed to highlight structure and texture features. The attention mechanism fully considers the complementarity and directionality of multi-scale image features and effectively avoids information loss and possible distortion of image structure and texture details during image reconstruction. Additionally, a cross-fusion mechanism is designed to comprehensively utilize structure and texture information for super-resolution image reconstruction, which effectively integrates the structure and texture details extracted by the two branch networks. Extensive experiments verify the effectiveness of the proposed method and its superiority over existing methods.

Feedback attention network for cardiac magnetic resonance imaging super-resolution

Background and objectiveAtrial fibrillation (AF) is a common clinical arrhythmia with a high disability and mortality rate. Improving the resolution of atrial structure and its changes in patients with AF is very important for understanding and treating AF. MethodsAiming at the problems of previous deep learning-based image super-resolution (SR) reconstruction methods simply deepening the network, loss of upsampling information, and difficulty in the reconstruction of high-frequency information, we propose the Feedback Attention Network (FBAN) for cardiac magnetic resonance imaging (CMRI) super-resolution. The network comprises a preprocessing module, a multi-scale residual group module, an upsampling module, and a reconstruction module. The preprocessing module uses a convolutional layer to extract shallow features and dilate the number of channels of the feature map. The multi-scale residual group module adds a multi-channel network, a mixed attention mechanism, and a long and short skip connection to expand the receptive field of the feature map, improve the multiplexing of multi-scale features and strengthen the reconstruction of high-frequency information. The upsampling module adopts the sub-pixel method to upsample the feature map to the target image size. The reconstruction module consists of a convolutional layer, which is used to restore the number of channels of the feature map to the original number to obtain the reconstructed high-resolution (HR) image. ResultsFurthermore, the test results on the public dataset of CMRI show that the HR images reconstructed by the FBAN method not only have a good improvement in reconstructed edge and texture information but also have a good improvement in the peak signal-to-noise ratio (PSNR) and the structural similarity index (SSIM) objective evaluation indicators. ConclusionCompared with the local magnified image, the edge information of the FBAN method reconstructed image has been enhanced, more high-frequency information of the CMRI is restored, the texture details are less lost, and the reconstructed image is less blurry. Overall, the reconstructed image has a lighter feeling of smearing, and the visual experience is more apparent and sharper.

Spatial-spectral dual path hyperspectral image super-resolution reconstruction network based on spectral response functions

Recently, hyperspectral image (HSI) super-resolution (SR) techniques based on deep learning have been actively developed. However, most hyperspectral image super-resolution reconstruction methods usually use all spectral bands simultaneously, leading to a mismatch of spectral properties between reconstructed HSI bands. Therefore, we proposed a new method of spatial-spectral dual path residual network (SGDPRN) based on spectral response function (SRF) to address the above problem. The SGDPRN is composed of the SRF guided grouping part, the spatial-spectral feature extraction part, and the final reconstruction part. Firstly, the reconstructed features for different spectral ranges are identified separately using SRF as a guide. Then, based on the grouping results, a spatial-spectral dual-path residual block is used to explore the spatial and spectral features by the designed parallel structure simultaneously. The spatial path is designed to extract sharp edges and realistic textures, and the spectral path is designed to model inter-spectral correlations to refine spectral features. At last, the third block of SGDPRN concatenates features of all groups and finishes the reconstruction of HSISR. QUST-1 satellite images have been applied in experiments, and the results showed that SGDPRN produced a higher peak signal to noise ratio, structural similarity metric, correlation coefficient, and lower spectral angle mapper, root mean square error than the other methods. This demonstrates that our method can effectively maintain the correlation of spectral bands while improving the spatial resolution.