检索结果-内蒙古大学图书馆

Enhanced Vgg16 for Medical Image Zero Watermarking: Integrating Attention, Skip Connections, Depth-Separated Convolution, and Dual-Logistic Encryption

SSRN

引用

SSRN 2024年

作者： Li, Jingyou Rongle, Wei Xi, Xiaotian Zhang, Guangda Yang, Zixin Zhang, Fengshan 1. School of Computer and Control Engineering Qiqihar University 2. Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar University

The paper proposes an enhanced VGG16 network((referred to as DS-ResVGG16 with CBAM)) that incorporates the attention mechanism CBAM, skip connections, and depth-separable convolution to solve the medical image content protection problem. The three innovative improvements of the enhanced VGG16 network are reflected in the following: first, replacing the regular convolution with depth-separable convolution substantially improves the computational efficiency and parameter utilization of the network;second, the introduction of the CBAM after the 2nd, 3rd, 4th, and 5th max-pooling layers further strengthens the network's capability to recognize and respond to crucial features.;and lastly, by adding a skip connection after the 2nd, 3rd, and 4th CBAM modules followed by the addition of skip connections, the transfer and integration of features were enhanced, improving the learning ability and generalization of the model. The improved network extracts Deep features from the original medical images, and binary feature vectors are generated using the mean hash algorithm. To further strengthen content protection security, this study innovatively adopts an encryption technique based on dual-logistics mapping and Joseph's ring for high-strength encryption of watermarks. During the generation of the zero watermark, the encrypted watermark and the feature vectors of the medical image are subjected to an iso-orthogonal operation, which ensures the concealment and security of the embedding. The validity and reasonableness of the modules and locations added by the scheme are verified and compared through experiments. The experimental results show that the scheme is robust enough to handle typical and geometric attacks. The medical image content protection problem is realized. © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Zero Watermarking Algorithms for Medical Images Based on Cnn and Transformer with Dual-Branch network

SSRN

引用

SSRN 2024年

作者： Li, Jingyou Wei, Rongle Xi, Xiaotian Zhang, Guangda Yang, Zixin Zhang, Fengshan 1. School of Computer and Control Engineering Qiqihar University 2. Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar University

The current research proposes a new zero-watermarking approach that aims to protect medical images from tampering by utilizing the power of deep learning. In this paper, we construct an innovative dual-branch network to capture subtle features of pictures and use them efficiently. First, one of the branches of the dual-branch network is to analyze the local details of the medical images by an enhanced convolutional neural network (specifically the Skip-connected VGG16, i.e., Res-VGG16). In contrast, the other branch employs the state-of-the-art Swin transformer v2 structure to parse the global context of the medical images. Second, adding a spatial transform network and a Gaussian filter as preprocessing before the two-branch network can further overcome the low robustness of medical images to geometric and noise attacks. Thirdly, we use a feature fusion method with a maximum voting mechanism to merge the features extracted from the two-branch network. We generate feature vectors of medical images using the DCT method and achieve watermark encryption by utilizing logistic mapping and a hash function. Finally, we generate a zero watermark by applying logical operations to the encrypted watermark and the medical image feature vectors. The implementation results show that the algorithm can effectively overcome the tampering problem of medical images and can recover the original data from the encrypted watermark with good robustness under conventional and geometric attacks. © 2024, The Authors. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Bi-layered coded metasurface for multi-functional hologram with broadband transmission and efficient reflection

引用

Chinese Optics Letters 2024年第5期22卷 8-16页

作者：朱磊李绪胜董亮谢文静尚关玉 Shah Nawaz Burokur 丁旭旻 School of Computer and Control Engineering Qiqihar UniversityQiqihar 161006China Communication and Electronics Engineering Institute Qiqihar UniversityQiqihar 161006China Heilongjiang Key Laboratory of Big Data Network Security Detection and Analysis Qiqihar UniversityQiqihar 161000China Department of Microwave Engineering Harbin Institute of TechnologyHarbin 150001China LEME UPLUniversitéParis NanterreF92410 Ville d’AvrayFrance Advanced Microscopy and Instrumentation Research Center Harbin Institute of TechnologyHarbin 150080China Key Laboratory of Millimeter Waves Southeast UniversityNanjing 210096China

A multi-functional full-space metasurface based on frequency and polarization multiplexing is *** metasurface unit consists of metallic patterns printed on the two faces of a single-layered dielectric *** unit cell can control electromagnetic wavefronts to achieve a broadband transmission with amplitudes greater than 0.4 from 4.4 to 10.4 ***,at 11.7 GHz and 15.4 GHz,four high-efficiency reflection channels with a reflection amplitude greater than 0.8 are also *** illuminated by linearly polarized waves,five different functions can be realized at five different frequencies,which are demonstrated by theoretical calculations,full-wave simulations,and experimental measurements.

关键词： multi-functional metasurface broadband transmission efficient reflection full space

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：