In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal...In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal is to reduce computational and storage requirements while ensuring detection accuracy and reliability,making it an ideal choice for achieving rapid response and efficient processing.In this regard,a lightweight SAR ship target detection algorithm based on YOLOv8 was proposed in this study.Firstly,the C2f-Sc module was designed by fusing the C2f in the backbone network with the ScConv to reduce spatial redundancy and channel redundancy between features in convolutional neural networks.At the same time,the Ghost module was introduced into the neck network to effectively reduce model parameters and computational complexity.A relatively lightweight EMA attention mechanism was added to the neck network to promote the effective fusion of features at different levels.Experimental results showed that the Parameters and GFLOPs of the improved model are reduced by 8.5%and 7.0%when mAP@0.5 and mAP@0.5:0.95 are increased by 0.7%and 1.8%,respectively.It makes the model lightweight and improves the detection accuracy,which has certain application value.展开更多
As a branch of quantum image processing,quantum image scaling has been widely studied.However,most of the existing quantum image scaling algorithms are based on nearest-neighbor interpolation and bilinear interpolatio...As a branch of quantum image processing,quantum image scaling has been widely studied.However,most of the existing quantum image scaling algorithms are based on nearest-neighbor interpolation and bilinear interpolation,the quantum version of bicubic interpolation has not yet been studied.In this work,we present the first quantum image scaling scheme for bicubic interpolation based on the novel enhanced quantum representation(NEQR).Our scheme can realize synchronous enlargement and reduction of the image with the size of 2^(n)×2^(n) by integral multiple.Firstly,the image is represented by NEQR and the original image coordinates are obtained through multiple CNOT modules.Then,16 neighborhood pixels are obtained by quantum operation circuits,and the corresponding weights of these pixels are calculated by quantum arithmetic modules.Finally,a quantum matrix operation,instead of a classical convolution operation,is used to realize the sum of convolution of these pixels.Through simulation experiments and complexity analysis,we demonstrate that our scheme achieves exponential speedup over the classical bicubic interpolation algorithm,and has better effect than the quantum version of bilinear interpolation.展开更多
We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantu...We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby propose a novel hybrid quantum deep neural network(HQDNN) used for image classification. After bilinear interpolation reduces the original image to a suitable size, an improved novel enhanced quantum representation(INEQR) is used to encode it into quantum states as the input of the HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of parameterized quantum circuits are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of the HQDNN, we conduct binary classification and three classification experiments on the MNIST(Modified National Institute of Standards and Technology) data set. In the first binary classification, the accuracy of 0 and 4 exceeds98%. Then we compare the performance of three classification with other algorithms, the results on two datasets show that the classification accuracy is higher than that of quantum deep neural network and general quantum convolutional neural network.展开更多
Processing underwater digital images is critical in ocean engineering,biology,and environmental studies,focusing on challenges such as poor lighting,image de-scattering,and color restoration.Due to environmental condi...Processing underwater digital images is critical in ocean engineering,biology,and environmental studies,focusing on challenges such as poor lighting,image de-scattering,and color restoration.Due to environmental conditions on the sea floor,improving image contrast and clarity is essential for underwater navigation and obstacle avoidance.Particularly in turbid,low-visibility waters,we require robust computer vision techniques and algorithms.Over the past decade,various models for underwater image enrichment have been proposed to address quality and visibility issues under dynamic and natural lighting conditions.This research article aims to evaluate various image improvement methods and propose a robust model that improves image quality,addresses turbidity,and enhances color,ultimately improving obstacle avoidance in autonomous systems.The proposed model demonstrates high accuracy compared to traditional models.The result analysis indicates the proposed model produces images with greatly improved visibility and exceptional color accuracy.Furthermore,research can unlock new possibilities for underwater exploration,monitoring,and intervention by advancing the state-of-the-art models in this domain.展开更多
Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color...Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual perception.Finally, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.展开更多
Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image qual...Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.展开更多
Hyperspectral images typically have high spectral resolution but low spatial resolution,which impacts the reliability and accuracy of subsequent applications,for example,remote sensingclassification and mineral identi...Hyperspectral images typically have high spectral resolution but low spatial resolution,which impacts the reliability and accuracy of subsequent applications,for example,remote sensingclassification and mineral identification.But in traditional methods via deep convolution neural net-works,indiscriminately extracting and fusing spectral and spatial features makes it challenging toutilize the differentiated information across adjacent spectral channels.Thus,we proposed a multi-branch interleaved iterative upsampling hyperspectral image super-resolution reconstruction net-work(MIIUSR)to address the above problems.We reinforce spatial feature extraction by integrat-ing detailed features from different receptive fields across adjacent channels.Furthermore,we pro-pose an interleaved iterative upsampling process during the reconstruction stage,which progres-sively fuses incremental information among adjacent frequency bands.Additionally,we add twoparallel three dimensional(3D)feature extraction branches to the backbone network to extractspectral and spatial features of varying granularity.We further enhance the backbone network’sconstruction results by leveraging the difference between two dimensional(2D)channel-groupingspatial features and 3D multi-granularity features.The results obtained by applying the proposednetwork model to the CAVE test set show that,at a scaling factor of×4,the peak signal to noiseratio,spectral angle mapping,and structural similarity are 37.310 dB,3.525 and 0.9438,respec-tively.Besides,extensive experiments conducted on the Harvard and Foster datasets demonstratethe superior potential of the proposed model in hyperspectral super-resolution reconstruction.展开更多
Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep...Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep learning,data-driven paradigm has become the mainstreammethod of CSI image feature extraction and representation,and in this process,datasets provideeffective support for CSI retrieval performance.However,there is a lack of systematic research onCSI image retrieval methods and datasets.Therefore,we present an overview of the existing worksabout one-class and multi-class CSI image retrieval based on deep learning.According to theresearch,based on their technical functionalities and implementation methods,CSI image retrievalis roughly classified into five categories:feature representation,metric learning,generative adversar-ial networks,autoencoder networks and attention networks.Furthermore,We analyzed the remain-ing challenges and discussed future work directions in this field.展开更多
Abstract:Stephen Crane was an outstanding American novelist,poet,and journalist.He achieved great success in his literary works during his brief career.Crane’s most well-known work,The Red Badge of Courage,is commonl...Abstract:Stephen Crane was an outstanding American novelist,poet,and journalist.He achieved great success in his literary works during his brief career.Crane’s most well-known work,The Red Badge of Courage,is commonly believed to be the first great novel of the American Civil War,largely because of its vivid and detailed description of the experience of warfare.This paper analyzes the images of color,animal and machine,which convey Crane’s thoughts of war:war is full of chaos,brutality,and confusion,without any romantic elements or heroism.展开更多
To develop a quick, accurate and antinoise automated image registration technique for infrared images, the wavelet analysis technique was used to extract the feature points in two images followed by the compensation f...To develop a quick, accurate and antinoise automated image registration technique for infrared images, the wavelet analysis technique was used to extract the feature points in two images followed by the compensation for input image with angle difference between them. A hi erarchical feature matching algorithm was adopted to get the final transform parameters between the two images. The simulation results for two infrared images show that the method can effectively, quickly and accurately register images and be antinoise to some extent.展开更多
This study investigates the effects of displacement damage on the dark signal of a pinned photodiode CMOS image sensor(CIS)following irradiation with back-streaming white neutrons from white neutron sources at the Chi...This study investigates the effects of displacement damage on the dark signal of a pinned photodiode CMOS image sensor(CIS)following irradiation with back-streaming white neutrons from white neutron sources at the China spallation neutron source(CSNS)and Xi'an pulsed reactor(XAPR).The mean dark signal,dark signal non-uniformity(DSNU),dark signal distribution,and hot pixels of the CIS were compared between the CSNS back-n and XAPR neutron irradiations.The nonionizing energy loss and energy distribution of primary knock-on atoms in silicon,induced by neutrons,were calculated using the open-source package Geant4.An analysis combining experimental and simulation results showed a noticeable proportionality between the increase in the mean dark signal and the displacement damage dose(DDD).Additionally,neutron energies influence DSNU,dark signal distribution,and hot pixels.High neutron energies at the same DDD level may lead to pronounced dark signal non-uniformity and elevated hot pixel values.展开更多
Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for...Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for this process is to combine inertial navigation system sensor information with the global navigation satellite system(GNSS)signal.However,some factors can interfere with the GNSS signal,such as ionospheric scintillation,jamming,or spoofing.One alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced images.But a high effort is required for image edge extraction.Here a support vector regression(SVR)model is proposed to reduce this computational load and processing time.The dynamic partial reconfiguration(DPR)of part of the SVR datapath is implemented to accelerate the process,reduce the area,and analyze its granularity by increasing the grain size of the reconfigurable region.Results show that the implementation in hardware is 68 times faster than that in software.This architecture with DPR also facilitates the low power consumption of 4 mW,leading to a reduction of 57%than that without DPR.This is also the lowest power consumption in current machine learning hardware implementations.Besides,the circuitry area is 41 times smaller.SVR with Gaussian kernel shows a success rate of 99.18%and minimum square error of 0.0146 for testing with the planning trajectory.This system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application,thus contributing to lower power consumption,smaller hardware area,and shorter execution time.展开更多
Technique s for constructing full view panoramic mosaics from sequences of images are pres ented. The goal of this work is to remove too many limitations for pure panning motion. The best reference block is important...Technique s for constructing full view panoramic mosaics from sequences of images are pres ented. The goal of this work is to remove too many limitations for pure panning motion. The best reference block is important for the block-matching method for improving the robustness and performance. It is automatically selected in the h igh-frequency image, which always contains the plenty visible features. In orde r to reduce accumulated registration errors, the global registration using the p hase-correlation matching method with rotation adjustment is applied to the who le sequence of images, which results in an optimal image mosaic with resolving t ranslational or rotational motion. The local registration using the Levenberg-M arquardt iterative non-linear minimization algorithm is applied to compensating for small amounts of motion parallax introduced by translations of the camera a nd other unmodeled distortions, then minimizing the discrepancy after applying t he global registration. The accumulated misregistration errors may cause a visib le gap between the two images. A smoothing filter is introduced for removing the visible artifact.展开更多
As a non-destructive testing technology,neutron imaging plays an important role in various fields,including material science,nuclear engineering,and fundamental science.An imaging detector with a neutron-sensitive ima...As a non-destructive testing technology,neutron imaging plays an important role in various fields,including material science,nuclear engineering,and fundamental science.An imaging detector with a neutron-sensitive image intensifier has been developed and demonstrated to achieve good spatial resolution and timing resolution.However,the influence of the working voltage on the performance of the neutron-sensitive imaging intensifier has not been studied.To optimize the performance of the neutron-sensitive image intensifier at different voltages,experiments have been performed at the China Spallation Neutron Source(CSNS)neutron beamline.The change in the light yield and imaging quality with different voltages has been acquired.It is shown that the image quality benefits from the high gain of the microchannel plate(MCP)and the high accelerating electric field between the MCP and the screen.Increasing the accelerating electric field is more effective than increasing the gain of MCPs for the improvement of the imaging quality.Increasing the total gain of the MCP stack can be realized more effectively by improving the gain of the standard MCP than that of the n MCP.These results offer a development direction for image intensifiers in the future.展开更多
Time-encoded imaging is useful for identifying potential special nuclear materials and other radioactive sources at a distance.In this study,a large field-of-view time-encoded imager was developed for gamma-ray and ne...Time-encoded imaging is useful for identifying potential special nuclear materials and other radioactive sources at a distance.In this study,a large field-of-view time-encoded imager was developed for gamma-ray and neutron source hotspot imaging based on a depth-of-interaction(DOI)detector.The imager primarily consists of a DOI detector system and a rotary dual-layer cylindrical coded mask.An EJ276 plastic scintillator coupled with two SiPMs was designed as the DOI detector to increase the field of view and improve the imager performance.The difference in signal time at both ends and the log of the signal amplitude ratio were used to calculate the interaction position resolution.The position resolution of the DOI detector was calibrated using a collimated Cs-137 source,and the full width at half maximum of the reconstruction position of the Gaussian fitting curve was approximately 4.4 cm.The DOI detector can be arbitrarily divided into several units to independently reconstruct the source distribution images.The unit length was optimized via Am-Be source-location experiments.A multidetector filtering method is proposed for image denoising.This method can effectively reduce image noise caused by poor DOI detector position resolution.The vertical field of view of the imager was(-55°,55°)when the detector was placed in the center of the coded mask.A DT neutron source at 20 m standoff could be located within 2400 s with an angular resolution of 3.5°.展开更多
In the era of big data,the number of images transmitted over the public channel increases exponentially.As a result,it is crucial to devise the efficient and highly secure encryption method to safeguard the sensitive ...In the era of big data,the number of images transmitted over the public channel increases exponentially.As a result,it is crucial to devise the efficient and highly secure encryption method to safeguard the sensitive image.In this paper,an improved sine map(ISM)possessing a larger chaotic region,more complex chaotic behavior and greater unpredictability is proposed and extensively tested.Drawing upon the strengths of ISM,we introduce a lightweight symmetric image encryption cryptosystem in wavelet domain(WDLIC).The WDLIC employs selective encryption to strike a satisfactory balance between security and speed.Initially,only the low-frequency-low-frequency component is chosen to encrypt utilizing classic permutation and diffusion.Then leveraging the statistical properties in wavelet domain,Gaussianization operation which opens the minds of encrypting image information in wavelet domain is first proposed and employed to all sub-bands.Simulations and theoretical analysis demonstrate the high speed and the remarkable effectiveness of WDLIC.展开更多
This article proposes a novel fractional heterogeneous neural network by coupling a Rulkov neuron with a Hopfield neural network(FRHNN),utilizing memristors for emulating neural synapses.The study firstly demonstrates...This article proposes a novel fractional heterogeneous neural network by coupling a Rulkov neuron with a Hopfield neural network(FRHNN),utilizing memristors for emulating neural synapses.The study firstly demonstrates the coexistence of multiple firing patterns through phase diagrams,Lyapunov exponents(LEs),and bifurcation diagrams.Secondly,the parameter related firing behaviors are described through two-parameter bifurcation diagrams.Subsequently,local attraction basins reveal multi-stability phenomena related to initial values.Moreover,the proposed model is implemented on a microcomputer-based ARM platform,and the experimental results correspond to the numerical simulations.Finally,the article explores the application of digital watermarking for medical images,illustrating its features of excellent imperceptibility,extensive key space,and robustness against attacks including noise and cropping.展开更多
For digital image transmission security and information copyright,a new holographic image self-embedding watermarking encryption scheme is proposed.Firstly,the plaintext is converted to the RGB three-color channel,the...For digital image transmission security and information copyright,a new holographic image self-embedding watermarking encryption scheme is proposed.Firstly,the plaintext is converted to the RGB three-color channel,the corresponding phase hologram is obtained by holographic technology and the watermark is self-embedded in the frequency domain.Secondly,by applying the Hilbert transform principle and genetic center law,a complete set of image encryption algorithms is constructed to realize the encryption of image information.Finally,simulation results and security analysis indicate that the scheme can effectively encrypt and decrypt image information and realize the copyright protection of information.The introduced scheme can provide some support for relevant theoretical research,and has practical significance.展开更多
The recent discovery of field emission devices based on one-dimensional nanostructures has attracted much interest in emerging applications on next-generation flat panel displays,molecule-based sensors,and so forth.To...The recent discovery of field emission devices based on one-dimensional nanostructures has attracted much interest in emerging applications on next-generation flat panel displays,molecule-based sensors,and so forth.To achieve a comprehensive understanding of surface potentials at the nano-emitters during the tunneling process,in this study we systematically investigated the image potentials of single-walled boron nitride nanotubes with different edges,diameters and lengths in the frame of a composite first-principles calculation.The image potentials of zigzag single-walled boron nitride nanotubes are found to be dependent on the non-equivalent sides.Only the image potentials of isolated armchair single-walled boron nitride nanotube can be well fitted with the image potential of an ideal metal sphere of a size comparable to the tube diameter.On the contrary,the image potentials of zigzag and grounded armchair single-walled boron nitride nanotubes exhibit a strong length-dependence characteristic and are significantly different from that of an ideal metal sphere,which originates from the significant axial symmetry breaking of induced charge at the tip for the long tube.The correlation between the testing electron and electronic structure of single-walled boron nitride nanotube has also been discussed.展开更多
文摘In recent years,with the development of synthetic aperture radar(SAR)technology and the widespread application of deep learning,lightweight detection of SAR images has emerged as a research direction.The ultimate goal is to reduce computational and storage requirements while ensuring detection accuracy and reliability,making it an ideal choice for achieving rapid response and efficient processing.In this regard,a lightweight SAR ship target detection algorithm based on YOLOv8 was proposed in this study.Firstly,the C2f-Sc module was designed by fusing the C2f in the backbone network with the ScConv to reduce spatial redundancy and channel redundancy between features in convolutional neural networks.At the same time,the Ghost module was introduced into the neck network to effectively reduce model parameters and computational complexity.A relatively lightweight EMA attention mechanism was added to the neck network to promote the effective fusion of features at different levels.Experimental results showed that the Parameters and GFLOPs of the improved model are reduced by 8.5%and 7.0%when mAP@0.5 and mAP@0.5:0.95 are increased by 0.7%and 1.8%,respectively.It makes the model lightweight and improves the detection accuracy,which has certain application value.
基金Project supported by the Scientific Research Fund of Hunan Provincial Education Department,China (Grant No.21A0470)the Natural Science Foundation of Hunan Province,China (Grant No.2023JJ50268)+1 种基金the National Natural Science Foundation of China (Grant Nos.62172268 and 62302289)the Shanghai Science and Technology Project,China (Grant Nos.21JC1402800 and 23YF1416200)。
文摘As a branch of quantum image processing,quantum image scaling has been widely studied.However,most of the existing quantum image scaling algorithms are based on nearest-neighbor interpolation and bilinear interpolation,the quantum version of bicubic interpolation has not yet been studied.In this work,we present the first quantum image scaling scheme for bicubic interpolation based on the novel enhanced quantum representation(NEQR).Our scheme can realize synchronous enlargement and reduction of the image with the size of 2^(n)×2^(n) by integral multiple.Firstly,the image is represented by NEQR and the original image coordinates are obtained through multiple CNOT modules.Then,16 neighborhood pixels are obtained by quantum operation circuits,and the corresponding weights of these pixels are calculated by quantum arithmetic modules.Finally,a quantum matrix operation,instead of a classical convolution operation,is used to realize the sum of convolution of these pixels.Through simulation experiments and complexity analysis,we demonstrate that our scheme achieves exponential speedup over the classical bicubic interpolation algorithm,and has better effect than the quantum version of bilinear interpolation.
基金Project supported by the Natural Science Foundation of Shandong Province,China (Grant No. ZR2021MF049)the Joint Fund of Natural Science Foundation of Shandong Province (Grant Nos. ZR2022LLZ012 and ZR2021LLZ001)。
文摘We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby propose a novel hybrid quantum deep neural network(HQDNN) used for image classification. After bilinear interpolation reduces the original image to a suitable size, an improved novel enhanced quantum representation(INEQR) is used to encode it into quantum states as the input of the HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of parameterized quantum circuits are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of the HQDNN, we conduct binary classification and three classification experiments on the MNIST(Modified National Institute of Standards and Technology) data set. In the first binary classification, the accuracy of 0 and 4 exceeds98%. Then we compare the performance of three classification with other algorithms, the results on two datasets show that the classification accuracy is higher than that of quantum deep neural network and general quantum convolutional neural network.
文摘Processing underwater digital images is critical in ocean engineering,biology,and environmental studies,focusing on challenges such as poor lighting,image de-scattering,and color restoration.Due to environmental conditions on the sea floor,improving image contrast and clarity is essential for underwater navigation and obstacle avoidance.Particularly in turbid,low-visibility waters,we require robust computer vision techniques and algorithms.Over the past decade,various models for underwater image enrichment have been proposed to address quality and visibility issues under dynamic and natural lighting conditions.This research article aims to evaluate various image improvement methods and propose a robust model that improves image quality,addresses turbidity,and enhances color,ultimately improving obstacle avoidance in autonomous systems.The proposed model demonstrates high accuracy compared to traditional models.The result analysis indicates the proposed model produces images with greatly improved visibility and exceptional color accuracy.Furthermore,research can unlock new possibilities for underwater exploration,monitoring,and intervention by advancing the state-of-the-art models in this domain.
基金supported by the national key research and development program (No.2020YFB1806608)Jiangsu natural science foundation for distinguished young scholars (No.BK20220054)。
文摘Due to the selective absorption of light and the existence of a large number of floating media in sea water, underwater images often suffer from color casts and detail blurs. It is therefore necessary to perform color correction and detail restoration. However,the existing enhancement algorithms cannot achieve the desired results. In order to solve the above problems, this paper proposes a multi-stream feature fusion network. First, an underwater image is preprocessed to obtain potential information from the illumination stream, color stream and structure stream by histogram equalization with contrast limitation, gamma correction and white balance, respectively. Next, these three streams and the original raw stream are sent to the residual blocks to extract the features. The features will be subsequently fused. It can enhance feature representation in underwater images. In the meantime, a composite loss function including three terms is used to ensure the quality of the enhanced image from the three aspects of color balance, structure preservation and image smoothness. Therefore, the enhanced image is more in line with human visual perception.Finally, the effectiveness of the proposed method is verified by comparison experiments with many stateof-the-art underwater image enhancement algorithms. Experimental results show that the proposed method provides superior results over them in terms of MSE,PSNR, SSIM, UIQM and UCIQE, and the enhanced images are more similar to their ground truth images.
文摘Handheld ultrasound devices are known for their portability and affordability,making them widely utilized in underdeveloped areas and community healthcare for rapid diagnosis and early screening.However,the image quality of handheld ultrasound devices is not always satisfactory due to the limited equipment size,which hinders accurate diagnoses by doctors.At the same time,paired ultrasound images are difficult to obtain from the clinic because imaging process is complicated.Therefore,we propose a modified cycle generative adversarial network(cycleGAN) for ultrasound image enhancement from multiple organs via unpaired pre-training.We introduce an ultrasound image pre-training method that does not require paired images,alleviating the requirement for large-scale paired datasets.We also propose an enhanced block with different structures in the pre-training and fine-tuning phases,which can help achieve the goals of different training phases.To improve the robustness of the model,we add Gaussian noise to the training images as data augmentation.Our approach is effective in obtaining the best quantitative evaluation results using a small number of parameters and less training costs to improve the quality of handheld ultrasound devices.
基金the National Natural Science Foun-dation of China(Nos.61471263,61872267 and U21B2024)the Natural Science Foundation of Tianjin,China(No.16JCZDJC31100)Tianjin University Innovation Foundation(No.2021XZC0024).
文摘Hyperspectral images typically have high spectral resolution but low spatial resolution,which impacts the reliability and accuracy of subsequent applications,for example,remote sensingclassification and mineral identification.But in traditional methods via deep convolution neural net-works,indiscriminately extracting and fusing spectral and spatial features makes it challenging toutilize the differentiated information across adjacent spectral channels.Thus,we proposed a multi-branch interleaved iterative upsampling hyperspectral image super-resolution reconstruction net-work(MIIUSR)to address the above problems.We reinforce spatial feature extraction by integrat-ing detailed features from different receptive fields across adjacent channels.Furthermore,we pro-pose an interleaved iterative upsampling process during the reconstruction stage,which progres-sively fuses incremental information among adjacent frequency bands.Additionally,we add twoparallel three dimensional(3D)feature extraction branches to the backbone network to extractspectral and spatial features of varying granularity.We further enhance the backbone network’sconstruction results by leveraging the difference between two dimensional(2D)channel-groupingspatial features and 3D multi-granularity features.The results obtained by applying the proposednetwork model to the CAVE test set show that,at a scaling factor of×4,the peak signal to noiseratio,spectral angle mapping,and structural similarity are 37.310 dB,3.525 and 0.9438,respec-tively.Besides,extensive experiments conducted on the Harvard and Foster datasets demonstratethe superior potential of the proposed model in hyperspectral super-resolution reconstruction.
文摘Crime scene investigation(CSI)image is key evidence carrier during criminal investiga-tion,in which CSI image retrieval can assist the public police to obtain criminal clues.Moreover,with the rapid development of deep learning,data-driven paradigm has become the mainstreammethod of CSI image feature extraction and representation,and in this process,datasets provideeffective support for CSI retrieval performance.However,there is a lack of systematic research onCSI image retrieval methods and datasets.Therefore,we present an overview of the existing worksabout one-class and multi-class CSI image retrieval based on deep learning.According to theresearch,based on their technical functionalities and implementation methods,CSI image retrievalis roughly classified into five categories:feature representation,metric learning,generative adversar-ial networks,autoencoder networks and attention networks.Furthermore,We analyzed the remain-ing challenges and discussed future work directions in this field.
文摘Abstract:Stephen Crane was an outstanding American novelist,poet,and journalist.He achieved great success in his literary works during his brief career.Crane’s most well-known work,The Red Badge of Courage,is commonly believed to be the first great novel of the American Civil War,largely because of its vivid and detailed description of the experience of warfare.This paper analyzes the images of color,animal and machine,which convey Crane’s thoughts of war:war is full of chaos,brutality,and confusion,without any romantic elements or heroism.
文摘To develop a quick, accurate and antinoise automated image registration technique for infrared images, the wavelet analysis technique was used to extract the feature points in two images followed by the compensation for input image with angle difference between them. A hi erarchical feature matching algorithm was adopted to get the final transform parameters between the two images. The simulation results for two infrared images show that the method can effectively, quickly and accurately register images and be antinoise to some extent.
基金supported by the Young Elite Scientists Sponsorship Program by CAST(No.YESS20210441)the National Natural Science Foundation of China(Nos.U2167208,11875223)。
文摘This study investigates the effects of displacement damage on the dark signal of a pinned photodiode CMOS image sensor(CIS)following irradiation with back-streaming white neutrons from white neutron sources at the China spallation neutron source(CSNS)and Xi'an pulsed reactor(XAPR).The mean dark signal,dark signal non-uniformity(DSNU),dark signal distribution,and hot pixels of the CIS were compared between the CSNS back-n and XAPR neutron irradiations.The nonionizing energy loss and energy distribution of primary knock-on atoms in silicon,induced by neutrons,were calculated using the open-source package Geant4.An analysis combining experimental and simulation results showed a noticeable proportionality between the increase in the mean dark signal and the displacement damage dose(DDD).Additionally,neutron energies influence DSNU,dark signal distribution,and hot pixels.High neutron energies at the same DDD level may lead to pronounced dark signal non-uniformity and elevated hot pixel values.
基金financially supported by the National Council for Scientific and Technological Development(CNPq,Brazil),Swedish-Brazilian Research and Innovation Centre(CISB),and Saab AB under Grant No.CNPq:200053/2022-1the National Council for Scientific and Technological Development(CNPq,Brazil)under Grants No.CNPq:312924/2017-8 and No.CNPq:314660/2020-8.
文摘Unmanned aerial vehicles(UAVs)have been widely used in military,medical,wireless communications,aerial surveillance,etc.One key topic involving UAVs is pose estimation in autonomous navigation.A standard procedure for this process is to combine inertial navigation system sensor information with the global navigation satellite system(GNSS)signal.However,some factors can interfere with the GNSS signal,such as ionospheric scintillation,jamming,or spoofing.One alternative method to avoid using the GNSS signal is to apply an image processing approach by matching UAV images with georeferenced images.But a high effort is required for image edge extraction.Here a support vector regression(SVR)model is proposed to reduce this computational load and processing time.The dynamic partial reconfiguration(DPR)of part of the SVR datapath is implemented to accelerate the process,reduce the area,and analyze its granularity by increasing the grain size of the reconfigurable region.Results show that the implementation in hardware is 68 times faster than that in software.This architecture with DPR also facilitates the low power consumption of 4 mW,leading to a reduction of 57%than that without DPR.This is also the lowest power consumption in current machine learning hardware implementations.Besides,the circuitry area is 41 times smaller.SVR with Gaussian kernel shows a success rate of 99.18%and minimum square error of 0.0146 for testing with the planning trajectory.This system is useful for adaptive applications where the user/designer can modify/reconfigure the hardware layout during its application,thus contributing to lower power consumption,smaller hardware area,and shorter execution time.
文摘Technique s for constructing full view panoramic mosaics from sequences of images are pres ented. The goal of this work is to remove too many limitations for pure panning motion. The best reference block is important for the block-matching method for improving the robustness and performance. It is automatically selected in the h igh-frequency image, which always contains the plenty visible features. In orde r to reduce accumulated registration errors, the global registration using the p hase-correlation matching method with rotation adjustment is applied to the who le sequence of images, which results in an optimal image mosaic with resolving t ranslational or rotational motion. The local registration using the Levenberg-M arquardt iterative non-linear minimization algorithm is applied to compensating for small amounts of motion parallax introduced by translations of the camera a nd other unmodeled distortions, then minimizing the discrepancy after applying t he global registration. The accumulated misregistration errors may cause a visib le gap between the two images. A smoothing filter is introduced for removing the visible artifact.
基金Project supported by the National Key R&D Program of China (Grant Nos.2023YFC2206502 and 2021YFA1600703)the National Natural Science Foundation of China (Grant Nos.12175254 and 12227810)the Guangdong–Hong Kong–Macao Joint Laboratory for Neutron Scattering Science and Technology。
文摘As a non-destructive testing technology,neutron imaging plays an important role in various fields,including material science,nuclear engineering,and fundamental science.An imaging detector with a neutron-sensitive image intensifier has been developed and demonstrated to achieve good spatial resolution and timing resolution.However,the influence of the working voltage on the performance of the neutron-sensitive imaging intensifier has not been studied.To optimize the performance of the neutron-sensitive image intensifier at different voltages,experiments have been performed at the China Spallation Neutron Source(CSNS)neutron beamline.The change in the light yield and imaging quality with different voltages has been acquired.It is shown that the image quality benefits from the high gain of the microchannel plate(MCP)and the high accelerating electric field between the MCP and the screen.Increasing the accelerating electric field is more effective than increasing the gain of MCPs for the improvement of the imaging quality.Increasing the total gain of the MCP stack can be realized more effectively by improving the gain of the standard MCP than that of the n MCP.These results offer a development direction for image intensifiers in the future.
基金supported by the National Natural Science Foundation of China(Nos.11975121,12205131)the Fundamental Research Funds for the Central Universities(No.lzujbky-2021-sp58)the Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX22_0354)。
文摘Time-encoded imaging is useful for identifying potential special nuclear materials and other radioactive sources at a distance.In this study,a large field-of-view time-encoded imager was developed for gamma-ray and neutron source hotspot imaging based on a depth-of-interaction(DOI)detector.The imager primarily consists of a DOI detector system and a rotary dual-layer cylindrical coded mask.An EJ276 plastic scintillator coupled with two SiPMs was designed as the DOI detector to increase the field of view and improve the imager performance.The difference in signal time at both ends and the log of the signal amplitude ratio were used to calculate the interaction position resolution.The position resolution of the DOI detector was calibrated using a collimated Cs-137 source,and the full width at half maximum of the reconstruction position of the Gaussian fitting curve was approximately 4.4 cm.The DOI detector can be arbitrarily divided into several units to independently reconstruct the source distribution images.The unit length was optimized via Am-Be source-location experiments.A multidetector filtering method is proposed for image denoising.This method can effectively reduce image noise caused by poor DOI detector position resolution.The vertical field of view of the imager was(-55°,55°)when the detector was placed in the center of the coded mask.A DT neutron source at 20 m standoff could be located within 2400 s with an angular resolution of 3.5°.
基金Project supported by the Key Area Research and Development Program of Guangdong Province,China(Grant No.2022B0701180001)the National Natural Science Foundation of China(Grant No.61801127)+1 种基金the Science Technology Planning Project of Guangdong Province,China(Grant Nos.2019B010140002 and 2020B111110002)the Guangdong–Hong Kong–Macao Joint Innovation Field Project(Grant No.2021A0505080006).
文摘In the era of big data,the number of images transmitted over the public channel increases exponentially.As a result,it is crucial to devise the efficient and highly secure encryption method to safeguard the sensitive image.In this paper,an improved sine map(ISM)possessing a larger chaotic region,more complex chaotic behavior and greater unpredictability is proposed and extensively tested.Drawing upon the strengths of ISM,we introduce a lightweight symmetric image encryption cryptosystem in wavelet domain(WDLIC).The WDLIC employs selective encryption to strike a satisfactory balance between security and speed.Initially,only the low-frequency-low-frequency component is chosen to encrypt utilizing classic permutation and diffusion.Then leveraging the statistical properties in wavelet domain,Gaussianization operation which opens the minds of encrypting image information in wavelet domain is first proposed and employed to all sub-bands.Simulations and theoretical analysis demonstrate the high speed and the remarkable effectiveness of WDLIC.
文摘This article proposes a novel fractional heterogeneous neural network by coupling a Rulkov neuron with a Hopfield neural network(FRHNN),utilizing memristors for emulating neural synapses.The study firstly demonstrates the coexistence of multiple firing patterns through phase diagrams,Lyapunov exponents(LEs),and bifurcation diagrams.Secondly,the parameter related firing behaviors are described through two-parameter bifurcation diagrams.Subsequently,local attraction basins reveal multi-stability phenomena related to initial values.Moreover,the proposed model is implemented on a microcomputer-based ARM platform,and the experimental results correspond to the numerical simulations.Finally,the article explores the application of digital watermarking for medical images,illustrating its features of excellent imperceptibility,extensive key space,and robustness against attacks including noise and cropping.
基金Project supported by the National Natural Science Foundation of China(Grant No.62061014)。
文摘For digital image transmission security and information copyright,a new holographic image self-embedding watermarking encryption scheme is proposed.Firstly,the plaintext is converted to the RGB three-color channel,the corresponding phase hologram is obtained by holographic technology and the watermark is self-embedded in the frequency domain.Secondly,by applying the Hilbert transform principle and genetic center law,a complete set of image encryption algorithms is constructed to realize the encryption of image information.Finally,simulation results and security analysis indicate that the scheme can effectively encrypt and decrypt image information and realize the copyright protection of information.The introduced scheme can provide some support for relevant theoretical research,and has practical significance.
基金the financial support from the National Natural Science Foundation of China(Grant Nos.12004083 and 51972069)the Science and Technology Projects in Guangzhou(Grant Nos.202102020350 and 202102010470)+7 种基金the National Key R&D Program of China(Grant No.2016YFB0200800)the Opening Project of Joint Laboratory for Planetary Science and Supercomputing(Grant No.CSYYGS-QT-2024-14)the Key-Area Research and Development Program of Guangdong Province(Grant No.2019B030330001)the College Students Innovation and Entrepreneurship Training Program of Guangdong Province(Grant No.S202311078133)Key Discipline of Materials Science and Engineering,Bureau of Education of Guangzhou(Grant No.202255464)the National Supercomputer Center in Guangzhouthe National Supercomputing Center in Chengduthe Network Center of Guangzhou University。
文摘The recent discovery of field emission devices based on one-dimensional nanostructures has attracted much interest in emerging applications on next-generation flat panel displays,molecule-based sensors,and so forth.To achieve a comprehensive understanding of surface potentials at the nano-emitters during the tunneling process,in this study we systematically investigated the image potentials of single-walled boron nitride nanotubes with different edges,diameters and lengths in the frame of a composite first-principles calculation.The image potentials of zigzag single-walled boron nitride nanotubes are found to be dependent on the non-equivalent sides.Only the image potentials of isolated armchair single-walled boron nitride nanotube can be well fitted with the image potential of an ideal metal sphere of a size comparable to the tube diameter.On the contrary,the image potentials of zigzag and grounded armchair single-walled boron nitride nanotubes exhibit a strong length-dependence characteristic and are significantly different from that of an ideal metal sphere,which originates from the significant axial symmetry breaking of induced charge at the tip for the long tube.The correlation between the testing electron and electronic structure of single-walled boron nitride nanotube has also been discussed.
