Single image super resolution(SISR)techniques produce images of high resolution(HR)as output from input images of low resolution(LR).Motivated by the effectiveness of deep learning methods,we provide a framework based...Single image super resolution(SISR)techniques produce images of high resolution(HR)as output from input images of low resolution(LR).Motivated by the effectiveness of deep learning methods,we provide a framework based on deep learning to achieve super resolution(SR)by utilizing deep singular-residual neural network(DSRNN)in training phase.Residuals are obtained from the difference between HR and LR images to generate LR-residual example pairs.Singular value decomposition(SVD)is applied to each LR-residual image pair to decompose into subbands of low and high frequency components.Later,DSRNN is trained on these subbands through input and output channels by optimizing the weights and biases of the network.With fewer layers in DSRNN,the influence of exploding gradients is reduced.This speeds up the learning process and also improves accuracy by using skip connections.The trained DSRNN parameters yield residuals to recover the HR subbands in the testing phase.Experimental analysis shows that the proposed method results in superior performance to existingmethods in terms of subjective quality.Extensive testing results on popular benchmark datasets such as set5,set14,and urban100 for a scaling factor of 4 show the effectiveness of the proposed method across different qualitative evaluation metrics.展开更多
In the process of geothermal exploitation and utilization, the reinjection amount of used geothermal water in super-deep and porous reservoir is small and significantly decreases over time. This has been a worldwide p...In the process of geothermal exploitation and utilization, the reinjection amount of used geothermal water in super-deep and porous reservoir is small and significantly decreases over time. This has been a worldwide problem, which greatly restricts the exploitation and utilization of geothermal resources. Based on a large amount of experiments and researches, the reinjection research on the tail water of Xianyang No.2 well, which is carried out by combining the application of hydrogeochemical simulation, clogging mechanism research and the reinjection experiment, has achieved breakthrough results. The clogging mechanism and indoor simulation experiment results show: Factors affecting the tail water reinjection of Xianyang No.2 well mainly include chemical clogging, suspended solids clogging, gas clogging, microbial clogging and composite clogging, yet the effect of particle migration on clogging has not been found; in the process of reinjection, chemical clogging was mainly caused by carbonates(mainly calcite), silicates(mainly chalcedony), and a small amount of iron minerals, and the clogging aggravated when the temperature rose; suspended solids clogging also aggravated when the temperature rose, which showed that particles formed by chemical reaction had a certain proportion in suspended solids.展开更多
High-resolution medical images have important medical value,but are difficult to obtain directly.Limited by hardware equipment and patient’s physical condition,the resolution of directly acquired medical images is of...High-resolution medical images have important medical value,but are difficult to obtain directly.Limited by hardware equipment and patient’s physical condition,the resolution of directly acquired medical images is often not high.Therefore,many researchers have thought of using super-resolution algorithms for secondary processing to obtain high-resolution medical images.However,current super-resolution algorithms only work on a single scale,and multiple networks need to be trained when super-resolution images of different scales are needed.This definitely raises the cost of acquiring high-resolution medical images.Thus,we propose a multi-scale superresolution algorithm using meta-learning.The algorithm combines a metalearning approach with an enhanced depth of residual super-resolution network to design a meta-upscale module.The meta-upscale module utilizes the weight prediction property of meta-learning and is able to perform the super-resolution task of medical images at any scale.Meanwhile,we design a non-integer mapping relation for super-resolution,which allows the network to be trained under non-integer magnification requirements.Compared to the state-of-the-art single-image super-resolution algorithm on computed tomography images of the pelvic region.The meta-learning multiscale superresolution algorithm obtained a surpassing of about 2%at a smaller model volume.Testing on different parts proves the high generalizability of our algorithm.Multi-scale super-resolution algorithms using meta-learning can compensate for hardware device defects and reduce secondary harm to patients while obtaining high-resolution medical images.It can be of great use in imaging related fields.展开更多
Deep learning techniques have significantly improved image restoration tasks in recent years.As a crucial compo-nent of deep learning,the loss function plays a key role in network optimization and performance enhancem...Deep learning techniques have significantly improved image restoration tasks in recent years.As a crucial compo-nent of deep learning,the loss function plays a key role in network optimization and performance enhancement.However,the currently prevalent loss functions assign equal weight to each pixel point during loss calculation,which hampers the ability to reflect the roles of different pixel points and fails to exploit the image’s characteristics fully.To address this issue,this study proposes an asymmetric loss function based on the image and data characteristics of the image recovery task.This novel loss function can adjust the weight of the reconstruction loss based on the grey value of different pixel points,thereby effectively optimizing the network training by differentially utilizing the grey information from the original image.Specifically,we calculate a weight factor for each pixel point based on its grey value and combine it with the reconstruction loss to create a new loss function.This ensures that pixel points with smaller grey values receive greater attention,improving network recovery.In order to verify the effectiveness of the proposed asymmetric loss function,we conducted experimental tests in the image super-resolution task.The experimental results show that the model with the introduction of asymmetric loss weights improves all the indexes of the processing results without increasing the training time.In the typical super-resolution network SRCNN,by introducing asymmetric weights,it is possible to improve the peak signal-to-noise ratio(PSNR)by up to about 0.5%,the structural similarity index(SSIM)by up to about 0.3%,and reduce the root-mean-square error(RMSE)by up to about 1.7%with essentially no increase in training time.In addition,we also further tested the performance of the proposed method in the denoising task to verify the potential applicability of the method in the image restoration task.展开更多
Purpose: To detect small diagnostic signals such as lung nodules in chest radiographs, radiologists magnify a region-of-interest using linear interpolation methods. However, such methods tend to generate over-smoothed...Purpose: To detect small diagnostic signals such as lung nodules in chest radiographs, radiologists magnify a region-of-interest using linear interpolation methods. However, such methods tend to generate over-smoothed images with artifacts that can make interpretation difficult. The purpose of this study was to investigate the effectiveness of super-resolution methods for improving the image quality of magnified chest radiographs. Materials and Methods: A total of 247 chest X-rays were sampled from the JSRT database, then divided into 93 training cases with non-nodules and 154 test cases with lung nodules. We first trained two types of super-resolution methods, sparse-coding super-resolution (ScSR) and super-resolution convolutional neural network (SRCNN). With the trained super-resolution methods, the high-resolution image was then reconstructed using the super-resolution methods from a low-resolution image that was down-sampled from the original test image. We compared the image quality of the super-resolution methods and the linear interpolations (nearest neighbor and bilinear interpolations). For quantitative evaluation, we measured two image quality metrics: peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). For comparative evaluation of the super-resolution methods, we measured the computation time per image. Results: The PSNRs and SSIMs for the ScSR and the SRCNN schemes were significantly higher than those of the linear interpolation methods (p p p Conclusion: Super-resolution methods provide significantly better image quality than linear interpolation methods for magnified chest radiograph images. Of the two tested schemes, the SRCNN scheme processed the images fastest;thus, SRCNN could be clinically superior for processing radiographs in terms of both image quality and processing speed.展开更多
针对现有超分辨率重建网络具有较高的计算复杂度和存在大量内存消耗的问题,提出了一种基于Transformer-CNN的轻量级图像超分辨率重建网络,使超分辨率重建网络更适合应用于移动平台等嵌入式终端。首先,提出了一个基于Transformer-CNN的...针对现有超分辨率重建网络具有较高的计算复杂度和存在大量内存消耗的问题,提出了一种基于Transformer-CNN的轻量级图像超分辨率重建网络,使超分辨率重建网络更适合应用于移动平台等嵌入式终端。首先,提出了一个基于Transformer-CNN的混合模块,从而增强网络捕获局部−全局深度特征的能力;其次,提出了一个改进的倒置残差块来特别关注高频区域的特征,以提升特征提取能力和减少推理时间;最后,在探索激活函数的最佳选择后,采用GELU(Gaussian Error Linear Unit)激活函数来进一步提高网络性能。实验结果表明,所提网络可以在图像超分辨率性能和网络复杂度之间取得很好的平衡,而且在基准数据集Urban100上4倍超分辨率的推理速度达到91 frame/s,比优秀网络SwinIR(Image Restoration using Swin transformer)快11倍,表明所提网络能够高效地重建图像的纹理和细节,并减少大量的推理时间。展开更多
文摘Single image super resolution(SISR)techniques produce images of high resolution(HR)as output from input images of low resolution(LR).Motivated by the effectiveness of deep learning methods,we provide a framework based on deep learning to achieve super resolution(SR)by utilizing deep singular-residual neural network(DSRNN)in training phase.Residuals are obtained from the difference between HR and LR images to generate LR-residual example pairs.Singular value decomposition(SVD)is applied to each LR-residual image pair to decompose into subbands of low and high frequency components.Later,DSRNN is trained on these subbands through input and output channels by optimizing the weights and biases of the network.With fewer layers in DSRNN,the influence of exploding gradients is reduced.This speeds up the learning process and also improves accuracy by using skip connections.The trained DSRNN parameters yield residuals to recover the HR subbands in the testing phase.Experimental analysis shows that the proposed method results in superior performance to existingmethods in terms of subjective quality.Extensive testing results on popular benchmark datasets such as set5,set14,and urban100 for a scaling factor of 4 show the effectiveness of the proposed method across different qualitative evaluation metrics.
基金funded by National Science Foundation Project in 2015 (No.41472221)
文摘In the process of geothermal exploitation and utilization, the reinjection amount of used geothermal water in super-deep and porous reservoir is small and significantly decreases over time. This has been a worldwide problem, which greatly restricts the exploitation and utilization of geothermal resources. Based on a large amount of experiments and researches, the reinjection research on the tail water of Xianyang No.2 well, which is carried out by combining the application of hydrogeochemical simulation, clogging mechanism research and the reinjection experiment, has achieved breakthrough results. The clogging mechanism and indoor simulation experiment results show: Factors affecting the tail water reinjection of Xianyang No.2 well mainly include chemical clogging, suspended solids clogging, gas clogging, microbial clogging and composite clogging, yet the effect of particle migration on clogging has not been found; in the process of reinjection, chemical clogging was mainly caused by carbonates(mainly calcite), silicates(mainly chalcedony), and a small amount of iron minerals, and the clogging aggravated when the temperature rose; suspended solids clogging also aggravated when the temperature rose, which showed that particles formed by chemical reaction had a certain proportion in suspended solids.
基金supported by the National Science Foundation for Young Scientists of China(Grant No.61806060)2019-2021,and the Natural Science Foundation of Heilongjiang Province(LH2019F024)+1 种基金China,2019-2021.We also acknowledge support fromthe Basic andApplied Basic Research Foundation of Guangdong Province(2021A1515220140)the Youth Innovation Project of Sun Yat-sen University Cancer Center(QNYCPY32).
文摘High-resolution medical images have important medical value,but are difficult to obtain directly.Limited by hardware equipment and patient’s physical condition,the resolution of directly acquired medical images is often not high.Therefore,many researchers have thought of using super-resolution algorithms for secondary processing to obtain high-resolution medical images.However,current super-resolution algorithms only work on a single scale,and multiple networks need to be trained when super-resolution images of different scales are needed.This definitely raises the cost of acquiring high-resolution medical images.Thus,we propose a multi-scale superresolution algorithm using meta-learning.The algorithm combines a metalearning approach with an enhanced depth of residual super-resolution network to design a meta-upscale module.The meta-upscale module utilizes the weight prediction property of meta-learning and is able to perform the super-resolution task of medical images at any scale.Meanwhile,we design a non-integer mapping relation for super-resolution,which allows the network to be trained under non-integer magnification requirements.Compared to the state-of-the-art single-image super-resolution algorithm on computed tomography images of the pelvic region.The meta-learning multiscale superresolution algorithm obtained a surpassing of about 2%at a smaller model volume.Testing on different parts proves the high generalizability of our algorithm.Multi-scale super-resolution algorithms using meta-learning can compensate for hardware device defects and reduce secondary harm to patients while obtaining high-resolution medical images.It can be of great use in imaging related fields.
基金supported by the National Natural Science Foundation of China(62201618).
文摘Deep learning techniques have significantly improved image restoration tasks in recent years.As a crucial compo-nent of deep learning,the loss function plays a key role in network optimization and performance enhancement.However,the currently prevalent loss functions assign equal weight to each pixel point during loss calculation,which hampers the ability to reflect the roles of different pixel points and fails to exploit the image’s characteristics fully.To address this issue,this study proposes an asymmetric loss function based on the image and data characteristics of the image recovery task.This novel loss function can adjust the weight of the reconstruction loss based on the grey value of different pixel points,thereby effectively optimizing the network training by differentially utilizing the grey information from the original image.Specifically,we calculate a weight factor for each pixel point based on its grey value and combine it with the reconstruction loss to create a new loss function.This ensures that pixel points with smaller grey values receive greater attention,improving network recovery.In order to verify the effectiveness of the proposed asymmetric loss function,we conducted experimental tests in the image super-resolution task.The experimental results show that the model with the introduction of asymmetric loss weights improves all the indexes of the processing results without increasing the training time.In the typical super-resolution network SRCNN,by introducing asymmetric weights,it is possible to improve the peak signal-to-noise ratio(PSNR)by up to about 0.5%,the structural similarity index(SSIM)by up to about 0.3%,and reduce the root-mean-square error(RMSE)by up to about 1.7%with essentially no increase in training time.In addition,we also further tested the performance of the proposed method in the denoising task to verify the potential applicability of the method in the image restoration task.
文摘Purpose: To detect small diagnostic signals such as lung nodules in chest radiographs, radiologists magnify a region-of-interest using linear interpolation methods. However, such methods tend to generate over-smoothed images with artifacts that can make interpretation difficult. The purpose of this study was to investigate the effectiveness of super-resolution methods for improving the image quality of magnified chest radiographs. Materials and Methods: A total of 247 chest X-rays were sampled from the JSRT database, then divided into 93 training cases with non-nodules and 154 test cases with lung nodules. We first trained two types of super-resolution methods, sparse-coding super-resolution (ScSR) and super-resolution convolutional neural network (SRCNN). With the trained super-resolution methods, the high-resolution image was then reconstructed using the super-resolution methods from a low-resolution image that was down-sampled from the original test image. We compared the image quality of the super-resolution methods and the linear interpolations (nearest neighbor and bilinear interpolations). For quantitative evaluation, we measured two image quality metrics: peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). For comparative evaluation of the super-resolution methods, we measured the computation time per image. Results: The PSNRs and SSIMs for the ScSR and the SRCNN schemes were significantly higher than those of the linear interpolation methods (p p p Conclusion: Super-resolution methods provide significantly better image quality than linear interpolation methods for magnified chest radiograph images. Of the two tested schemes, the SRCNN scheme processed the images fastest;thus, SRCNN could be clinically superior for processing radiographs in terms of both image quality and processing speed.
文摘针对现有超分辨率重建网络具有较高的计算复杂度和存在大量内存消耗的问题,提出了一种基于Transformer-CNN的轻量级图像超分辨率重建网络,使超分辨率重建网络更适合应用于移动平台等嵌入式终端。首先,提出了一个基于Transformer-CNN的混合模块,从而增强网络捕获局部−全局深度特征的能力;其次,提出了一个改进的倒置残差块来特别关注高频区域的特征,以提升特征提取能力和减少推理时间;最后,在探索激活函数的最佳选择后,采用GELU(Gaussian Error Linear Unit)激活函数来进一步提高网络性能。实验结果表明,所提网络可以在图像超分辨率性能和网络复杂度之间取得很好的平衡,而且在基准数据集Urban100上4倍超分辨率的推理速度达到91 frame/s,比优秀网络SwinIR(Image Restoration using Swin transformer)快11倍,表明所提网络能够高效地重建图像的纹理和细节,并减少大量的推理时间。
