Existing lithospheric velocity models exhibit similar structures typically associated with the first-order tectonic features,with dissimilarities due to different data and methods used in model generation.The quantifi...Existing lithospheric velocity models exhibit similar structures typically associated with the first-order tectonic features,with dissimilarities due to different data and methods used in model generation.The quantification of model structural similarity can help in interpreting the geophysical properties of Earth's interior and establishing unified models crucial in natural hazard assessment and resource exploration.Here we employ the complex wavelet structural similarity index measure(CW-SSIM)active in computer image processing to analyze the structural similarity of four lithospheric velocity models of Chinese mainland published in the past decade.We take advantage of this method in its multiscale definition and insensitivity to slight geometrical distortion like translation and scaling,which is particularly crucial in the structural similarity analysis of velocity models accounting for uncertainty and resolution.Our results show that the CW-SSIM values vary in different model pairs,horizontal locations,and depths.While variations in the inter-model CW-SSIM are partly owing to different databases in the model generation,the difference of tomography methods may significantly impact the similar structural features of models,such as the low similarities between the full-wave based FWEA18 and other three models in northeastern China.We finally suggest potential solutions for the next generation of tomographic modeling in different areas according to corresponding structural similarities of existing models.展开更多
It is well-known that classical quality measures,such as Mean Squared Error(MSE),Weighted Mean Squared Error(WMSE)or Peak Signal-to-Noise Ratio(PSNR),are not always corresponding with visual observations.Structural si...It is well-known that classical quality measures,such as Mean Squared Error(MSE),Weighted Mean Squared Error(WMSE)or Peak Signal-to-Noise Ratio(PSNR),are not always corresponding with visual observations.Structural similarity based image quality assessment was proposed under the assumption that the Human Visual System(HVS)is highly adapted for extracting structural information from an image.While the demand on high color quality increases in the media industry,color loss will make the visual quality different.In this paper,we proposed an improved quality assessment(QA)method by adding color comparison into the structural similarity(SSIM)measurement system for evaluating color image quality.Then we divided the task of similarity measurement into four comparisons:luminance,contrast,structure,and color.Experimental results show that the predicted quality scores of the proposed method are more effective and consistent with visual quality than the classical methods using five different distortion types of color image sets.展开更多
Automatic segmentation of ischemic stroke lesions from computed tomography(CT)images is of great significance for identifying and curing this life-threatening condition.However,in addition to the problem of low image ...Automatic segmentation of ischemic stroke lesions from computed tomography(CT)images is of great significance for identifying and curing this life-threatening condition.However,in addition to the problem of low image contrast,it is also challenged by the complex changes in the appearance of the stroke area and the difficulty in obtaining image data.Considering that it is difficult to obtain stroke data and labels,a data enhancement algorithm for one-shot medical image segmentation based on data augmentation using learned transformation was proposed to increase the number of data sets for more accurate segmentation.A deep convolutional neural network based algorithm for stroke lesion segmentation,called structural similarity with light U-structure(USSL)Net,was proposed.We embedded a convolution module that combines switchable normalization,multi-scale convolution and dilated convolution in the network for better segmentation performance.Besides,considering the strong structural similarity between multi-modal stroke CT images,the USSL Net uses the correlation maximized structural similarity loss(SSL)function as the loss function to learn the varying shapes of the lesions.The experimental results show that our framework has achieved results in the following aspects.First,the data obtained by adding our data enhancement algorithm is better than the data directly segmented from the multi-modal image.Second,the performance of our network model is better than that of other models for stroke segmentation tasks.Third,the way SSL functioned as a loss function is more helpful to the improvement of segmentation accuracy than the cross-entropy loss function.展开更多
Objective video quality assessment plays a very important role in multimedia signal processing. Several extensions of the structural similarity （SSIM） index could not predict the quality of the video sequence effect...Objective video quality assessment plays a very important role in multimedia signal processing. Several extensions of the structural similarity （SSIM） index could not predict the quality of the video sequence effectively. In this paper we propose a structural similarity quality metric for videos based on a spatial-temporal visual attention model. This model acquires the motion attended region and the distortion attended region by computing the motion features and the distortion contrast. It mimics the visual attention shifting between the two attended regions and takes the burst of error into account by introducing the non-linear weighting fimctions to give a much higher weighting factor to the extremely damaged frames. The proposed metric based on the model renders the final object quality rating of the whole video sequence and is validated using the 50 Hz video sequences of Video Quality Experts Group Phase I test database.展开更多
Joint inversion is one of the most effective methods for reducing non-uniqueness for geophysical inversion.The current joint inversion methods can be divided into the structural consistency constraint and petrophysica...Joint inversion is one of the most effective methods for reducing non-uniqueness for geophysical inversion.The current joint inversion methods can be divided into the structural consistency constraint and petrophysical consistency constraint methods,which are mutually independent.Currently,there is a need for joint inversion methods that can comprehensively consider the structural consistency constraints and petrophysical consistency constraints.This paper develops the structural similarity index(SSIM)as a new structural and petrophysical consistency constraint for the joint inversion of gravity and vertical gradient data.The SSIM constraint is in the form of a fraction,which may have analytical singularities.Therefore,converting the fractional form to the subtractive form can solve the problem of analytic singularity and finally form a modified structural consistency index of the joint inversion,which enhances the stability of the SSIM constraint applied to the joint inversion.Compared to the reconstructed results from the cross-gradient inversion,the proposed method presents good performance and stability.The SSIM algorithm is a new joint inversion method for petrophysical and structural constraints.It can promote the consistency of the recovered models from the distribution and the structure of the physical property values.Then,applications to synthetic data illustrate that the algorithm proposed in this paper can well process the synthetic data and acquire good reconstructed results.展开更多
An image denoising method based on curvelet within the framework of non-local means(NLM) is proposed in this paper. We use Structural Similarity(SSIM) to compute the value of SSIM between the reference patch and its s...An image denoising method based on curvelet within the framework of non-local means(NLM) is proposed in this paper. We use Structural Similarity(SSIM) to compute the value of SSIM between the reference patch and its similar versions, and remove the dissimilar pixels. Besides, the curvelet is adopted to adjust the coefficients of these patches with low SSIM. Experiments show that the proposed method has the capacity to denoise effectively, improves the peak signal-to-noise ratio of the image, and keeps better visual result in edges information reservation as well.展开更多
Graph similarity learning aims to calculate the similarity between pairs of graphs.Existing unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph aug...Graph similarity learning aims to calculate the similarity between pairs of graphs.Existing unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph augmentation strategies,which can harm the semantic and structural information of graphs and overlook the rich structural information present in subgraphs.To address these issues,we propose a graph similarity learning model based on learnable augmentation and multi-level contrastive learning.First,to tackle the problem of random augmentation disrupting the semantics and structure of the graph,we design a learnable augmentation method to selectively choose nodes and edges within the graph.To enhance contrastive levels,we employ a biased random walk method to generate corresponding subgraphs,enriching the contrastive hierarchy.Second,to solve the issue of previous work not considering multi-level contrastive learning,we utilize graph convolutional networks to learn node representations of augmented views and the original graph and calculate the interaction information between the attribute-augmented and structure-augmented views and the original graph.The goal is to maximize node consistency between different views and learn node matching between different graphs,resulting in node-level representations for each graph.Subgraph representations are then obtained through pooling operations,and we conduct contrastive learning utilizing both node and subgraph representations.Finally,the graph similarity score is computed according to different downstream tasks.We conducted three sets of experiments across eight datasets,and the results demonstrate that the proposed model effectively mitigates the issues of random augmentation damaging the original graph’s semantics and structure,as well as the insufficiency of contrastive levels.Additionally,the model achieves the best overall performance.展开更多
This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to imp...This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to improve the natural appearance of reconstructed images.Deep learning-based super-resolution(SR)algorithms reconstruct high-resolution images from low-resolution inputs,offering a practical means to enhance image quality without requiring superior imaging hardware,which is particularly important in medical applications where diagnostic accuracy is critical.Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity,visual artefacts may persist,making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction.Our research shows on two models—SR and Invertible Rescaling Neural Network(IRN)—trained on multiple benchmark datasets that the function LSSIMN significantly contributes to the visual quality,preserving the structural fidelity on the reference datasets.The quantitative analysis of results while incorporating LSSIMN shows that including this loss function component has a mean 2.88%impact on the improvement of the final structural similarity of the reconstructed images in the validation set,in comparison to leaving it out and 0.218%in comparison when this component is non-normalised.展开更多
基金supported by the National Natural Science Foundation of China(Nos.42174063,92155307,41976046)Guangdong Provincial Key Laboratory of Geophysical High-resolution Imaging Technology under(No.2022B1212010002)Project for introduced Talents Team of Southern Marine Science and Engineering Guangdong(Guangzhou)(No.GML2019ZD0203)。
文摘Existing lithospheric velocity models exhibit similar structures typically associated with the first-order tectonic features,with dissimilarities due to different data and methods used in model generation.The quantification of model structural similarity can help in interpreting the geophysical properties of Earth's interior and establishing unified models crucial in natural hazard assessment and resource exploration.Here we employ the complex wavelet structural similarity index measure(CW-SSIM)active in computer image processing to analyze the structural similarity of four lithospheric velocity models of Chinese mainland published in the past decade.We take advantage of this method in its multiscale definition and insensitivity to slight geometrical distortion like translation and scaling,which is particularly crucial in the structural similarity analysis of velocity models accounting for uncertainty and resolution.Our results show that the CW-SSIM values vary in different model pairs,horizontal locations,and depths.While variations in the inter-model CW-SSIM are partly owing to different databases in the model generation,the difference of tomography methods may significantly impact the similar structural features of models,such as the low similarities between the full-wave based FWEA18 and other three models in northeastern China.We finally suggest potential solutions for the next generation of tomographic modeling in different areas according to corresponding structural similarities of existing models.
文摘It is well-known that classical quality measures,such as Mean Squared Error(MSE),Weighted Mean Squared Error(WMSE)or Peak Signal-to-Noise Ratio(PSNR),are not always corresponding with visual observations.Structural similarity based image quality assessment was proposed under the assumption that the Human Visual System(HVS)is highly adapted for extracting structural information from an image.While the demand on high color quality increases in the media industry,color loss will make the visual quality different.In this paper,we proposed an improved quality assessment(QA)method by adding color comparison into the structural similarity(SSIM)measurement system for evaluating color image quality.Then we divided the task of similarity measurement into four comparisons:luminance,contrast,structure,and color.Experimental results show that the predicted quality scores of the proposed method are more effective and consistent with visual quality than the classical methods using five different distortion types of color image sets.
基金the National Natural Science Foundation of China(No.61976091)。
文摘Automatic segmentation of ischemic stroke lesions from computed tomography(CT)images is of great significance for identifying and curing this life-threatening condition.However,in addition to the problem of low image contrast,it is also challenged by the complex changes in the appearance of the stroke area and the difficulty in obtaining image data.Considering that it is difficult to obtain stroke data and labels,a data enhancement algorithm for one-shot medical image segmentation based on data augmentation using learned transformation was proposed to increase the number of data sets for more accurate segmentation.A deep convolutional neural network based algorithm for stroke lesion segmentation,called structural similarity with light U-structure(USSL)Net,was proposed.We embedded a convolution module that combines switchable normalization,multi-scale convolution and dilated convolution in the network for better segmentation performance.Besides,considering the strong structural similarity between multi-modal stroke CT images,the USSL Net uses the correlation maximized structural similarity loss(SSL)function as the loss function to learn the varying shapes of the lesions.The experimental results show that our framework has achieved results in the following aspects.First,the data obtained by adding our data enhancement algorithm is better than the data directly segmented from the multi-modal image.Second,the performance of our network model is better than that of other models for stroke segmentation tasks.Third,the way SSL functioned as a loss function is more helpful to the improvement of segmentation accuracy than the cross-entropy loss function.
文摘Objective video quality assessment plays a very important role in multimedia signal processing. Several extensions of the structural similarity （SSIM） index could not predict the quality of the video sequence effectively. In this paper we propose a structural similarity quality metric for videos based on a spatial-temporal visual attention model. This model acquires the motion attended region and the distortion attended region by computing the motion features and the distortion contrast. It mimics the visual attention shifting between the two attended regions and takes the burst of error into account by introducing the non-linear weighting fimctions to give a much higher weighting factor to the extremely damaged frames. The proposed metric based on the model renders the final object quality rating of the whole video sequence and is validated using the 50 Hz video sequences of Video Quality Experts Group Phase I test database.
基金supported by the National Key Research and Development Program(Grant No.2021YFA0716100)the National Key Research and Development Program of China Project(Grant No.2018YFC0603502)+1 种基金the Henan Youth Science Fund Program(Grant No.212300410105)the provincial key R&D and promotion special project of Henan Province(Grant No.222102320279).
文摘Joint inversion is one of the most effective methods for reducing non-uniqueness for geophysical inversion.The current joint inversion methods can be divided into the structural consistency constraint and petrophysical consistency constraint methods,which are mutually independent.Currently,there is a need for joint inversion methods that can comprehensively consider the structural consistency constraints and petrophysical consistency constraints.This paper develops the structural similarity index(SSIM)as a new structural and petrophysical consistency constraint for the joint inversion of gravity and vertical gradient data.The SSIM constraint is in the form of a fraction,which may have analytical singularities.Therefore,converting the fractional form to the subtractive form can solve the problem of analytic singularity and finally form a modified structural consistency index of the joint inversion,which enhances the stability of the SSIM constraint applied to the joint inversion.Compared to the reconstructed results from the cross-gradient inversion,the proposed method presents good performance and stability.The SSIM algorithm is a new joint inversion method for petrophysical and structural constraints.It can promote the consistency of the recovered models from the distribution and the structure of the physical property values.Then,applications to synthetic data illustrate that the algorithm proposed in this paper can well process the synthetic data and acquire good reconstructed results.
文摘An image denoising method based on curvelet within the framework of non-local means(NLM) is proposed in this paper. We use Structural Similarity(SSIM) to compute the value of SSIM between the reference patch and its similar versions, and remove the dissimilar pixels. Besides, the curvelet is adopted to adjust the coefficients of these patches with low SSIM. Experiments show that the proposed method has the capacity to denoise effectively, improves the peak signal-to-noise ratio of the image, and keeps better visual result in edges information reservation as well.
文摘Graph similarity learning aims to calculate the similarity between pairs of graphs.Existing unsupervised graph similarity learning methods based on contrastive learning encounter challenges related to random graph augmentation strategies,which can harm the semantic and structural information of graphs and overlook the rich structural information present in subgraphs.To address these issues,we propose a graph similarity learning model based on learnable augmentation and multi-level contrastive learning.First,to tackle the problem of random augmentation disrupting the semantics and structure of the graph,we design a learnable augmentation method to selectively choose nodes and edges within the graph.To enhance contrastive levels,we employ a biased random walk method to generate corresponding subgraphs,enriching the contrastive hierarchy.Second,to solve the issue of previous work not considering multi-level contrastive learning,we utilize graph convolutional networks to learn node representations of augmented views and the original graph and calculate the interaction information between the attribute-augmented and structure-augmented views and the original graph.The goal is to maximize node consistency between different views and learn node matching between different graphs,resulting in node-level representations for each graph.Subgraph representations are then obtained through pooling operations,and we conduct contrastive learning utilizing both node and subgraph representations.Finally,the graph similarity score is computed according to different downstream tasks.We conducted three sets of experiments across eight datasets,and the results demonstrate that the proposed model effectively mitigates the issues of random augmentation damaging the original graph’s semantics and structure,as well as the insufficiency of contrastive levels.Additionally,the model achieves the best overall performance.
基金support from the following institutional grant.Internal Grant Agency of the Faculty of Economics and Management,Czech University of Life Sciences Prague,grant no.2023A0004(https://iga.pef.czu.cz/,accessed on 6 June 2025).
文摘This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to improve the natural appearance of reconstructed images.Deep learning-based super-resolution(SR)algorithms reconstruct high-resolution images from low-resolution inputs,offering a practical means to enhance image quality without requiring superior imaging hardware,which is particularly important in medical applications where diagnostic accuracy is critical.Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity,visual artefacts may persist,making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction.Our research shows on two models—SR and Invertible Rescaling Neural Network(IRN)—trained on multiple benchmark datasets that the function LSSIMN significantly contributes to the visual quality,preserving the structural fidelity on the reference datasets.The quantitative analysis of results while incorporating LSSIMN shows that including this loss function component has a mean 2.88%impact on the improvement of the final structural similarity of the reconstructed images in the validation set,in comparison to leaving it out and 0.218%in comparison when this component is non-normalised.
