SAR-BM3D is one of the state of the art despeckling algorithms for SAR images. However, when tackling with high resolution SAR images, it often has an unsatisfying despeckling performance in the homogeneous smooth reg...SAR-BM3D is one of the state of the art despeckling algorithms for SAR images. However, when tackling with high resolution SAR images, it often has an unsatisfying despeckling performance in the homogeneous smooth regions, together with a high time complexity. In this paper, a novel downsampled SAR-BM3D despeckling approach combined with edge compensation is proposed. The proposed algorithm consists of two steps. First, despeckle the image which is a downsampled version of original image with SAR-BM3D. Then, compensate edges in each level when upsampling. This approach not only utilizes the good ability of feature preservation, but also improves performance of smoothing homogenous regions. When it comes to high resolution SAR images, the efficiency can be raised by six to seven times, compared to original SAR-BM3D. Experiments on simulated and real SAR images show that the proposed method reaches a high level in terms of visual quality and act more efficiently.展开更多
This paper presents a multi-face detection method for color images. The method is based on the assumption that faces are well separated from the background by skin color detection. These faces can be located by the pr...This paper presents a multi-face detection method for color images. The method is based on the assumption that faces are well separated from the background by skin color detection. These faces can be located by the proposed method which modifies the subtractive clustering. The modified clustering algorithm proposes a new definition of distance for multi-face detection, and its key parameters can be predetermined adaptively by statistical information of face objects in the image. Downsampling is employed to reduce the computation of clustering and speed up the process of the proposed method. The effectiveness of the proposed method is illustrated by three experiments.展开更多
Recently,deep learning(DL)became one of the essential tools in bioinformatics.A modified convolutional neural network(CNN)is employed in this paper for building an integratedmodel for deoxyribonucleic acid(DNA)classif...Recently,deep learning(DL)became one of the essential tools in bioinformatics.A modified convolutional neural network(CNN)is employed in this paper for building an integratedmodel for deoxyribonucleic acid(DNA)classification.In any CNN model,convolutional layers are used to extract features followed by max-pooling layers to reduce the dimensionality of features.A novel method based on downsampling and CNNs is introduced for feature reduction.The downsampling is an improved form of the existing pooling layer to obtain better classification accuracy.The two-dimensional discrete transform(2D DT)and two-dimensional random projection(2D RP)methods are applied for downsampling.They convert the high-dimensional data to low-dimensional data and transform the data to the most significant feature vectors.However,there are parameters which directly affect how a CNN model is trained.In this paper,some issues concerned with the training of CNNs have been handled.The CNNs are examined by changing some hyperparameters such as the learning rate,size of minibatch,and the number of epochs.Training and assessment of the performance of CNNs are carried out on 16S rRNA bacterial sequences.Simulation results indicate that the utilization of a CNN based on wavelet subsampling yields the best trade-off between processing time and accuracy with a learning rate equal to 0.0001,a size of minibatch equal to 64,and a number of epochs equal to 20.展开更多
Multiple description coding has recently been proposed as a joint source and channel coding to solve the problem of robust image transmission over unreliable network, and it can offer a variety of tradeoff between sig...Multiple description coding has recently been proposed as a joint source and channel coding to solve the problem of robust image transmission over unreliable network, and it can offer a variety of tradeoff between signal redundancy and transmission robustness. In this letter, a novel pre- and post-processing method with flexible redundancy insertion for polyphase downsampling multiple de- scription coding is presented. The proposed method can be implemented as pre- and post-processing to all standards for image and video communications, with obvious advantages. Simulation results show that this approach can reduce the computational complexity while provide a flexible redundancy in- sertion to make the system robust for any packet loss situation over different networks.展开更多
<strong>Background:</strong> High-resolution medical images often need to be downsampled because of the memory limitations of the hardware used for machine learning. Although various image interpolation me...<strong>Background:</strong> High-resolution medical images often need to be downsampled because of the memory limitations of the hardware used for machine learning. Although various image interpolation methods are applicable to downsampling, the effect of data preprocessing on the learning performance of convolutional neural networks (CNNs) has not been fully investigated. <strong>Methods:</strong> In this study, five different pixel interpolation algorithms (nearest neighbor, bilinear, Hamming window, bicubic, and Lanczos interpolation) were used for image downsampling to investigate their effects on the prediction accuracy of a CNN. Chest X-ray images from the NIH public dataset were examined by downsampling 10 patterns. <strong>Results:</strong> The accuracy improved with a decreasing image size, and the best accuracy was achieved at 64 × 64 pixels. Among the interpolation methods, bicubic interpolation obtained the highest accuracy, followed by the Hamming window.展开更多
Reduced-order models offer a cost-effective and accurate approach to analyzing high-dimensional combustion problems.These surrogate models are built in a data-driven manner by combining computational fluid dynamics si...Reduced-order models offer a cost-effective and accurate approach to analyzing high-dimensional combustion problems.These surrogate models are built in a data-driven manner by combining computational fluid dynamics simulations with Proper Orthogonal Decomposition(POD)for dimensionality reduction and Gaussian Process Regression(GPR)for nonlinear regression.However,these models can yield physically inconsistent results,such as negative mass fractions.As a linear decomposition method,POD complicates the enforcement of constraints in the reduced space,while GPR lacks inherent provisions to ensure physical consistency.To address these challenges,this study proposes a novel constrained reduced-order model framework that enforces physical consistency in predictions.Dimensionality reduction is achieved by downsampling the dataset through low-cost Singular Value Decomposition(lcSVD)using optimal sensor placement,ensuring that the retained data points preserve physical information in the reduced space.We integrate finite-support parametric distribution functions,such as truncated Gaussian and beta distribution scaled to the interval[a,b],into the GPR framework.These bounded likelihood functions explicitly model the observational noise in the bounded space and use variational inference to approximate analytically intractable posterior distributions,producing GP estimations that satisfy physical constraints by construction.We validate the proposed methods using a synthetic dataset and a benchmark case of one-dimensional laminar NH3/H2 flames.The results show that the thermo-chemical state predictions comply with physical constraints while maintaining the high accuracy of unconstrained reduced-order models.展开更多
To locate the right places for embedding watermark signals, and to set the proper streng-th of the embedded watermark signal are two critical problems for obtaining a robust and transpar-ent watermark in color images....To locate the right places for embedding watermark signals, and to set the proper streng-th of the embedded watermark signal are two critical problems for obtaining a robust and transpar-ent watermark in color images. In this paper, a DCT domain visible watermarking scheme based on the luminance and texture features and alligned with transcoding from MPEG-2 to MPEG-1 is proposed. In this scheme, the location of the visible watermark is chosen at the block with minimum number of nonzero DCT coefficients in the I-frames. When embedding the visible watermark （ such as video DC image ） into the unmarked original image, the embedding factors are determined with the local luminance feature and texture features of the original image and watemark image by utilizing DC and 3AC coefficients only. Experimental results demonstrate that the proposed scheme not only provides good fidelity and robustness against MPEG-2 downscaling transcoding, but also achieves a low Computational complexity.展开更多
文摘SAR-BM3D is one of the state of the art despeckling algorithms for SAR images. However, when tackling with high resolution SAR images, it often has an unsatisfying despeckling performance in the homogeneous smooth regions, together with a high time complexity. In this paper, a novel downsampled SAR-BM3D despeckling approach combined with edge compensation is proposed. The proposed algorithm consists of two steps. First, despeckle the image which is a downsampled version of original image with SAR-BM3D. Then, compensate edges in each level when upsampling. This approach not only utilizes the good ability of feature preservation, but also improves performance of smoothing homogenous regions. When it comes to high resolution SAR images, the efficiency can be raised by six to seven times, compared to original SAR-BM3D. Experiments on simulated and real SAR images show that the proposed method reaches a high level in terms of visual quality and act more efficiently.
文摘This paper presents a multi-face detection method for color images. The method is based on the assumption that faces are well separated from the background by skin color detection. These faces can be located by the proposed method which modifies the subtractive clustering. The modified clustering algorithm proposes a new definition of distance for multi-face detection, and its key parameters can be predetermined adaptively by statistical information of face objects in the image. Downsampling is employed to reduce the computation of clustering and speed up the process of the proposed method. The effectiveness of the proposed method is illustrated by three experiments.
基金This research was funded by the Deanship of Scientific Research at Princess Nourah Bint Abdulrahman University through the Fast-track Research Funding Program.
文摘Recently,deep learning(DL)became one of the essential tools in bioinformatics.A modified convolutional neural network(CNN)is employed in this paper for building an integratedmodel for deoxyribonucleic acid(DNA)classification.In any CNN model,convolutional layers are used to extract features followed by max-pooling layers to reduce the dimensionality of features.A novel method based on downsampling and CNNs is introduced for feature reduction.The downsampling is an improved form of the existing pooling layer to obtain better classification accuracy.The two-dimensional discrete transform(2D DT)and two-dimensional random projection(2D RP)methods are applied for downsampling.They convert the high-dimensional data to low-dimensional data and transform the data to the most significant feature vectors.However,there are parameters which directly affect how a CNN model is trained.In this paper,some issues concerned with the training of CNNs have been handled.The CNNs are examined by changing some hyperparameters such as the learning rate,size of minibatch,and the number of epochs.Training and assessment of the performance of CNNs are carried out on 16S rRNA bacterial sequences.Simulation results indicate that the utilization of a CNN based on wavelet subsampling yields the best trade-off between processing time and accuracy with a learning rate equal to 0.0001,a size of minibatch equal to 64,and a number of epochs equal to 20.
基金Funded by the National Natural Science Foundation of China (No.60671037)Ningbo Industry Foundation (No.2007B10051)+2 种基金Zhejiang Province Key Industry Foundation (No.2006C11200)Scientific Research Fund of Zhejiang Provincial Education Department (No.20070956, No.20070978, No.20061661)Ningbo University Foundation (XK0610031)
文摘Multiple description coding has recently been proposed as a joint source and channel coding to solve the problem of robust image transmission over unreliable network, and it can offer a variety of tradeoff between signal redundancy and transmission robustness. In this letter, a novel pre- and post-processing method with flexible redundancy insertion for polyphase downsampling multiple de- scription coding is presented. The proposed method can be implemented as pre- and post-processing to all standards for image and video communications, with obvious advantages. Simulation results show that this approach can reduce the computational complexity while provide a flexible redundancy in- sertion to make the system robust for any packet loss situation over different networks.
文摘<strong>Background:</strong> High-resolution medical images often need to be downsampled because of the memory limitations of the hardware used for machine learning. Although various image interpolation methods are applicable to downsampling, the effect of data preprocessing on the learning performance of convolutional neural networks (CNNs) has not been fully investigated. <strong>Methods:</strong> In this study, five different pixel interpolation algorithms (nearest neighbor, bilinear, Hamming window, bicubic, and Lanczos interpolation) were used for image downsampling to investigate their effects on the prediction accuracy of a CNN. Chest X-ray images from the NIH public dataset were examined by downsampling 10 patterns. <strong>Results:</strong> The accuracy improved with a decreasing image size, and the best accuracy was achieved at 64 × 64 pixels. Among the interpolation methods, bicubic interpolation obtained the highest accuracy, followed by the Hamming window.
基金support of the HECO2-Axe-1 project,funded by the Walloon Region under the REPowerEU initiative,Bel-giumfinancial support from the ERC proof of concept grant INVENT(grant agreement No:101123406).
文摘Reduced-order models offer a cost-effective and accurate approach to analyzing high-dimensional combustion problems.These surrogate models are built in a data-driven manner by combining computational fluid dynamics simulations with Proper Orthogonal Decomposition(POD)for dimensionality reduction and Gaussian Process Regression(GPR)for nonlinear regression.However,these models can yield physically inconsistent results,such as negative mass fractions.As a linear decomposition method,POD complicates the enforcement of constraints in the reduced space,while GPR lacks inherent provisions to ensure physical consistency.To address these challenges,this study proposes a novel constrained reduced-order model framework that enforces physical consistency in predictions.Dimensionality reduction is achieved by downsampling the dataset through low-cost Singular Value Decomposition(lcSVD)using optimal sensor placement,ensuring that the retained data points preserve physical information in the reduced space.We integrate finite-support parametric distribution functions,such as truncated Gaussian and beta distribution scaled to the interval[a,b],into the GPR framework.These bounded likelihood functions explicitly model the observational noise in the bounded space and use variational inference to approximate analytically intractable posterior distributions,producing GP estimations that satisfy physical constraints by construction.We validate the proposed methods using a synthetic dataset and a benchmark case of one-dimensional laminar NH3/H2 flames.The results show that the thermo-chemical state predictions comply with physical constraints while maintaining the high accuracy of unconstrained reduced-order models.
基金This work is supported by National Natural Science Foundation of China(60462001) , and Beijing Institute of Electronic Science and Technology&Information Security and Privacy key Laboratory (YZDJ0416) .
文摘To locate the right places for embedding watermark signals, and to set the proper streng-th of the embedded watermark signal are two critical problems for obtaining a robust and transpar-ent watermark in color images. In this paper, a DCT domain visible watermarking scheme based on the luminance and texture features and alligned with transcoding from MPEG-2 to MPEG-1 is proposed. In this scheme, the location of the visible watermark is chosen at the block with minimum number of nonzero DCT coefficients in the I-frames. When embedding the visible watermark （ such as video DC image ） into the unmarked original image, the embedding factors are determined with the local luminance feature and texture features of the original image and watemark image by utilizing DC and 3AC coefficients only. Experimental results demonstrate that the proposed scheme not only provides good fidelity and robustness against MPEG-2 downscaling transcoding, but also achieves a low Computational complexity.
