Super Star Learning Platform is a learning platform which meets the needs of interactive teaching mode both in and out of the classroom.This paper analyzes the advantages of interactive teaching strategies and the exi...Super Star Learning Platform is a learning platform which meets the needs of interactive teaching mode both in and out of the classroom.This paper analyzes the advantages of interactive teaching strategies and the existing problems to be solved.Super Star Learning Platform can effectively improve teaching efficiency by enhancing the interaction between teachers and students and motivating students’interest in learning.展开更多
The images captured by different observation station have different resolutions.The Helioseismic and Magnetic Imager(HMI:a part of the NASA Solar Dynamics Observatory SDO)has low-precision but wide coverage.And the Go...The images captured by different observation station have different resolutions.The Helioseismic and Magnetic Imager(HMI:a part of the NASA Solar Dynamics Observatory SDO)has low-precision but wide coverage.And the Goode Solar Telescope(GST,formerly known as the New Solar Telescope)at Big Bear Solar Observatory(BBSO)solar images has high precision but small coverage.The super-resolution can make the captured images become clearer,so it is wildly used in solar image processing.The traditional super-resolution methods,such as interpolation,often use single image’s feature to improve the image’s quality.The methods based on deep learning-based super-resolution image reconstruction algorithms have better quality,but small-scale features often become ambiguous.To solve this problem,a transitional amplification network structure is proposed.The network can use the two types images relationship to make the images clear.By adding a transition image with almost no difference between the source image and the target image,the transitional amplification training procedure includes three parts:transition image acquisition,transition network training with source images and transition images,and amplification network training with transition images and target images.In addition,the traditional evaluation indicators based on structural similarity(SSIM)and peak signal-to-noise ratio(PSNR)calculate the difference in pixel values and perform poorly in cross-type image reconstruction.The method based on feature matching can effectively evaluate the similarity and clarity of features.The experimental results show that the quality index of the reconstructed image is consistent with the visual effect.展开更多
Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection de...Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection detection, and recognition. Recently, deep learning techniques have emerged and blossomed, producing " the state-of-the-art” in many domains. Due to their capability in feature extraction and mapping, it is very helpful to predict high-frequency details lost in low-resolution images. In this paper, we give an overview of recent advances in deep learning-based models and methods that have been applied to single image super-resolution tasks. We also summarize, compare and discuss various models from the past and present for comprehensive understanding and finally provide open problems and possible directions for future research.展开更多
Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artif...Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.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
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
近年来,深度强化学习在复杂决策和控制任务中得到了广泛应用,并在游戏AI领域展现了卓越性能。基于双重深度Q网络的方法,提出一种通过智能体与Super Mario Bros环境的持续交互、逐步学习并优化游戏策略。首先,利用gym-super-mario-bros...近年来,深度强化学习在复杂决策和控制任务中得到了广泛应用,并在游戏AI领域展现了卓越性能。基于双重深度Q网络的方法,提出一种通过智能体与Super Mario Bros环境的持续交互、逐步学习并优化游戏策略。首先,利用gym-super-mario-bros框架构建训练环境,并通过帧跳、灰度转换和图像缩放等技术提升训练效率。其次,智能体采用DDQN架构结合卷积神经网络进行特征提取,并通过经验回放和目标网络减少Q值波动。最后,通过衰减的epsilon-greedy策略平衡探索与利用。实验结果表明,该方法能有效提升智能体表现。展开更多
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
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
文摘Super Star Learning Platform is a learning platform which meets the needs of interactive teaching mode both in and out of the classroom.This paper analyzes the advantages of interactive teaching strategies and the existing problems to be solved.Super Star Learning Platform can effectively improve teaching efficiency by enhancing the interaction between teachers and students and motivating students’interest in learning.
基金This work was supported in part by CAS Key Laboratory of Solar Activity,National Astronomical Observatories Commission for Collaborating Research Program(CRP)(No:KLSA202114)National Science Foundation Project of P.R.China under Grant No.61701554+2 种基金the cross-discipline research project of Minzu University of China(2020MDJC08)State Language Commission Key Project(ZDl135-39)Promotion plan for young teachers scientific research ability of Minzu University of China,MUC 111 Project,First class courses(Digital Image Processing KC2066).
文摘The images captured by different observation station have different resolutions.The Helioseismic and Magnetic Imager(HMI:a part of the NASA Solar Dynamics Observatory SDO)has low-precision but wide coverage.And the Goode Solar Telescope(GST,formerly known as the New Solar Telescope)at Big Bear Solar Observatory(BBSO)solar images has high precision but small coverage.The super-resolution can make the captured images become clearer,so it is wildly used in solar image processing.The traditional super-resolution methods,such as interpolation,often use single image’s feature to improve the image’s quality.The methods based on deep learning-based super-resolution image reconstruction algorithms have better quality,but small-scale features often become ambiguous.To solve this problem,a transitional amplification network structure is proposed.The network can use the two types images relationship to make the images clear.By adding a transition image with almost no difference between the source image and the target image,the transitional amplification training procedure includes three parts:transition image acquisition,transition network training with source images and transition images,and amplification network training with transition images and target images.In addition,the traditional evaluation indicators based on structural similarity(SSIM)and peak signal-to-noise ratio(PSNR)calculate the difference in pixel values and perform poorly in cross-type image reconstruction.The method based on feature matching can effectively evaluate the similarity and clarity of features.The experimental results show that the quality index of the reconstructed image is consistent with the visual effect.
基金the support from the Shanxi Hundred People Plan of China
文摘Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection detection, and recognition. Recently, deep learning techniques have emerged and blossomed, producing " the state-of-the-art” in many domains. Due to their capability in feature extraction and mapping, it is very helpful to predict high-frequency details lost in low-resolution images. In this paper, we give an overview of recent advances in deep learning-based models and methods that have been applied to single image super-resolution tasks. We also summarize, compare and discuss various models from the past and present for comprehensive understanding and finally provide open problems and possible directions for future research.
基金supported by China Postdoctoral Science Foundation(2015M582355)the Doctor Scientific Research Start Project from Hubei University of Science and Technology(BK1418)National Natural Science Foundation of China(61271256)
文摘Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.
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.
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.
文摘近年来,深度强化学习在复杂决策和控制任务中得到了广泛应用,并在游戏AI领域展现了卓越性能。基于双重深度Q网络的方法,提出一种通过智能体与Super Mario Bros环境的持续交互、逐步学习并优化游戏策略。首先,利用gym-super-mario-bros框架构建训练环境,并通过帧跳、灰度转换和图像缩放等技术提升训练效率。其次,智能体采用DDQN架构结合卷积神经网络进行特征提取,并通过经验回放和目标网络减少Q值波动。最后,通过衰减的epsilon-greedy策略平衡探索与利用。实验结果表明,该方法能有效提升智能体表现。
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.
