期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到5篇文章
< 1 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
LKAW: A Robust Watermarking Method Based on Large Kernel Convolution and Adaptive Weight Assignment 认领 引用
1
作者 Xiaorui Zhang Rui Jiang +3 位作者 Wei Sun Aiguo Song Xindong Wei Ruohan Meng 《Computers, Materials & Continua》 SCIE EI 2023年第4期1-17,共17页
Robust watermarking requires finding invariant features under multiple attacks to ensure correct extraction.Deep learning has extremely powerful in extracting features,and watermarking algorithms based on deep learnin... Robust watermarking requires finding invariant features under multiple attacks to ensure correct extraction.Deep learning has extremely powerful in extracting features,and watermarking algorithms based on deep learning have attracted widespread attention.Most existing methods use 3×3 small kernel convolution to extract image features and embed the watermarking.However,the effective perception fields for small kernel convolution are extremely confined,so the pixels that each watermarking can affect are restricted,thus limiting the performance of the watermarking.To address these problems,we propose a watermarking network based on large kernel convolution and adaptive weight assignment for loss functions.It uses large-kernel depth-wise convolution to extract features for learning large-scale image information and subsequently projects the watermarking into a highdimensional space by 1×1 convolution to achieve adaptability in the channel dimension.Subsequently,the modification of the embedded watermarking on the cover image is extended to more pixels.Because the magnitude and convergence rates of each loss function are different,an adaptive loss weight assignment strategy is proposed to make theweights participate in the network training together and adjust theweight dynamically.Further,a high-frequency wavelet loss is proposed,by which the watermarking is restricted to only the low-frequency wavelet sub-bands,thereby enhancing the robustness of watermarking against image compression.The experimental results show that the peak signal-to-noise ratio(PSNR)of the encoded image reaches 40.12,the structural similarity(SSIM)reaches 0.9721,and the watermarking has good robustness against various types of noise. 展开更多
关键词 Robust watermarking large kernel convolution adaptive loss weights high-frequency wavelet loss deep learning
暂未订购 下载PDF
High-Quality Single-Pixel Imaging Based on Large-Kernel Convolution under Low-Sampling Conditions 认领 引用
2
作者 Chenyu Yuan Yuanhao Su Chunfang Wang 《Chinese Physics Letters》 SCIE EI CAS CSCD 2025年第4期55-61,共7页
In recent years,deep learning has been introduced into the field of Single-pixel imaging(SPI),garnering significant attention.However,conventional networks still exhibit limitations in preserving image details.To addr... In recent years,deep learning has been introduced into the field of Single-pixel imaging(SPI),garnering significant attention.However,conventional networks still exhibit limitations in preserving image details.To address this issue,we integrate Large Kernel Convolution(LKconv)into the U-Net framework,proposing an enhanced network structure named U-LKconv network,which significantly enhances the capability to recover image details even under low sampling conditions. 展开更多
关键词 large kernel convolution lkconv recover image details U lkconv network high quality single pixel imaging U Net low sampling conditions enhanced network structure large kernel convolution
暂未订购 下载PDF
A Lightweight Network with Dual Encoder and Cross Feature Fusion for Cement Pavement Crack Detection 认领 引用 被引量：3
3
作者 Zhong Qu Guoqing Mu Bin Yuan 《Computer Modeling in Engineering & Sciences》 SCIE EI 2024年第7期255-273,共19页
Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of cr... Automatic crack detection of cement pavement chiefly benefits from the rapid development of deep learning,with convolutional neural networks(CNN)playing an important role in this field.However,as the performance of crack detection in cement pavement improves,the depth and width of the network structure are significantly increased,which necessitates more computing power and storage space.This limitation hampers the practical implementation of crack detection models on various platforms,particularly portable devices like small mobile devices.To solve these problems,we propose a dual-encoder-based network architecture that focuses on extracting more comprehensive fracture feature information and combines cross-fusion modules and coordinated attention mechanisms formore efficient feature fusion.Firstly,we use small channel convolution to construct shallow feature extractionmodule(SFEM)to extract low-level feature information of cracks in cement pavement images,in order to obtainmore information about cracks in the shallowfeatures of images.In addition,we construct large kernel atrous convolution(LKAC)to enhance crack information,which incorporates coordination attention mechanism for non-crack information filtering,and large kernel atrous convolution with different cores,using different receptive fields to extract more detailed edge and context information.Finally,the three-stage feature map outputs from the shallow feature extraction module is cross-fused with the two-stage feature map outputs from the large kernel atrous convolution module,and the shallow feature and detailed edge feature are fully fused to obtain the final crack prediction map.We evaluate our method on three public crack datasets:DeepCrack,CFD,and Crack500.Experimental results on theDeepCrack dataset demonstrate the effectiveness of our proposed method compared to state-of-the-art crack detection methods,which achieves Precision(P)87.2%,Recall(R)87.7%,and F-score(F1)87.4%.Thanks to our lightweight crack detectionmodel,the parameter count of the model in real-world detection scenarios has been significantly reduced to less than 2M.This advancement also facilitates technical support for portable scene detection. 展开更多
关键词 Shallow feature extraction module large kernel atrous convolution dual encoder lightweight network crack detection
暂未订购 下载PDF
E-SegNet:E-Shaped Structure Networks for Accurate 2D and 3D Medical Image Segmentation 认领 引用
4
作者 Wei Wu Xin Yang +3 位作者 Chenggui Yao Ou Liu Qi Zhao Jianwei Shuai 《Research》 SCIE EI CSCD 2026年第3期858-873,共16页
U-structure has become a foundational approach in medical image segmentation,consistently demonstrating strong performance across various segmentation tasks.Most current models are based on this framework,customizing ... U-structure has become a foundational approach in medical image segmentation,consistently demonstrating strong performance across various segmentation tasks.Most current models are based on this framework,customizing encoder-decoder components to achieve higher accuracy across various segmentation challenges.However,this often comes at the cost of increased parameter counts,which inevitably limit their practicality in real-world applications.In this study,we provide an E-shaped segmentation framework that discards the traditional step-by-step resolution recovery decoding process,instead directly aggregating multi-scale features extracted by the encoder at each stage for deep crosslevel integration.Additionally,we propose an innovative multi-scale large-kernel convolution(MLKConv)module,designed to enhance high-level feature representation by effectively capturing both local and global contextual information.Compared to U-structure,the proposed E-structured approach substantially reduces parameters while delivering superior performance,especially in complex segmentation tasks.Based on this structure,we develop 2 segmentation networks specifically for 2-dimensional(2D)and 3D medical images.2D E-SegNet is evaluated on four 2D segmentation benchmark datasets(Synapse multiorgan,ACDC,Kvasir-Seg,and BUSI),while 3D E-SegNet is assessed on four 3D segmentation benchmark datasets(Synapse,ACDC,NIH Pancreas,and Lung).Experimental results demonstrate that our approach outperforms the current leading U-shaped models across multiple datasets,achieving new state-of-the-art(SOTA)performance with fewer parameters.In summary,our research introduces a novel approach to medical image segmentation,offering potential improvements and contributing to ongoing advancements in the field.Our code is publicly available on http://gffzz188fe103f8f1460asvkwo5nv5w05c66bc.ffgz.tsg.suse.edu.cn/zhaoqi106/E-SegNet. 展开更多
关键词 medical image segmentationconsistently multi scale feature aggregation D segmentation e shaped structure medical image segmentation multi scale large kernel convolution U structure parameter reduction
Model for the online frontal image selection of silkworm pupae using machine vision 认领 引用
5
作者 Feng Guo Jing Li +2 位作者 Wei Qin Chunjiang Zhao Guanglin Li 《International Journal of Agricultural and Biological Engineering》 SCIE 2026年第1期163-169,共7页
The sorting of male and female silkworm pupae is an essential process of silkworm breeding,with its accuracy directly affecting the quality of hybrid silkworm eggs and silk.Gonadal characteristics serve as a reliable ... The sorting of male and female silkworm pupae is an essential process of silkworm breeding,with its accuracy directly affecting the quality of hybrid silkworm eggs and silk.Gonadal characteristics serve as a reliable basis for sex identification in silkworm pupae;however,the gonads only exist on the positive side of the tail.Due to the unique geometry of silkworm pupae,online sex recognition based on machine vision requires flipping and taking many photos of the same silkworm pupae.Thus,accurately selecting the frontal image from multiple images of the same silkworm pupae in different poses is a prerequisite for subsequent sex identification.To address this challenge,we proposed SPNet-GS(Silkworm Pupae Network for Gonad Selection),a lightweight model for online selection of frontal silkworm pupae images.The model first employed a large kernel convolution to enhance the receptive field and capture the relevant information between adjacent pixels.Then the correlation between long-distance pixels under multi-scale information can be obtained by dilated convolutions.Finally,the correlation information between near and far pixels was fused to enhance feature extraction.Experimental results demonstrated that our method outperforms other models with an average accuracy of 98.41%and an average F1 score of 99.02%.The average inference time of each image was 0.03 s,which can fully meet the requirements of online selection of male and female silkworm pupae.Moreover,the gender identification accuracy rates using the selected frontal image and gonad region image reached 84.68%and 94.58%,respectively.These results were 10%and 19.90%higher than using multi-pose images for sex identification,demonstrating the effectiveness of the frontal image selection strategy.The findings of this investigation may provide a valuable reference for the machine vision-based intelligent online sorting of silkworm pupae by gender. 展开更多
关键词 frontal image selection gonad image large kernel convolution sex identification of silkworm pupae
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈