检索结果-内蒙古大学图书馆

Zero Watermarking algorithms for Medical images Based on Multi-module Fusion with VGG16 and Dual-Logistic Mapping Encryption

引用

CIRCUITS systems AND SIGNAL processing 2025年 1-36页

作者： Li, Jingyou Wei, Rongle xi, xiaotian Zhang, Guangda Yang, Zixin Zhang, Fengshan Qiqihar Univ Sch Comp & Control Engn Qiqihar Heilongjiang Peoples R China Qiqihar Univ Heilongjiang Key Lab Big Data Network Secur Detect Qiqihar Heilongjiang Peoples R China

The current research proposes a new zero watermarking approach that aims to protect medical images from tampering by utilizing the powerful learning capabilities of deep learning. In this paper, we propose a robust zero watermarking scheme based on multi-module fusion of VGG16, which enhances the efficiency and security of medical image transmission. The scheme leverages depthwise separable convolution to speed up feature extraction, enabling the focus on global image features. Furthermore, by incorporating the Convolutional Attention Module with channel and spatial attention, the extracted features are enhanced with stronger perceptual, discriminative, and generalization *** preserve multi-scale information and improve feature reusability, jump-joins are employed. The multi-module fusion of VGG16 facilitates the extraction of deep features with superior generalization, multi-scale, and high perceptual capabilities. Binary feature vectors are generated using a mean hash algorithm and encrypted using a novel dual chaos dual logistics encryption method designed in this paper, which significantly enhances both image watermark security and overall network transmission *** effectiveness of the scheme is verified through extensive experiments. Experimental results demonstrate that the proposed method achieves an NC value of over 0.92 in the presence of noise filtering and rotation attacks, indicating robust security and strong resistance to common image distortions. These results confirm the scheme's capability to provide high security for medical image transmission, ensuring both robustness against attacks and confidentiality in medical systems.

关键词： Zero watermark Multi-module fusion VGG16 Dual-chaos dual-logistics encryption (DcDlE)

来源：评论

学校读者我要写书评

暂无评论

HIPU: A Hybrid Intelligent processing Unit With Fine-Grained ISA for Real-Time Deep Neural Network Inference Applications

引用

IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) systems 2023年第12期31卷 1980-1993页

作者： Zhao, Wenzhe Yang, Guoming xia, Tian Chen, Fei Zheng, Nanning Ren, Pengju Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Natl Engn Res Ctr ofVisual Informat & Applicat Natl Key Lab Human MachineHybrid Augmented Intelli Xian 710049 Shaanxi Peoples R China Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Shaanxi Peoples R China

Neural network algorithms have shown superior performance over conventional algorithms, leading to the designation and deployment of dedicated accelerators in practical scenarios. Coarse-grained accelerators achieve high performance but can support only a limited number of predesigned operators, which cannot cover the flexible operators emerging in modern neural network algorithms. Therefore, fine-grained accelerators, such as instruction set architecture (ISA)-based accelerators, have become a hot research topic due to their sufficient flexibility to cover the unpredefined operators. The main challenges for fine-grained accelerators include the undesired long delays of single-image inference when performing multibatch inference, as well as the difficulty of meeting real-time constraints when processing multiple tasks simultaneously. This article proposes a hybrid intelligent processing unit (HIPU) to address the aforementioned problems. Specifically, we design a novel conversion-free data format, expanding the single-instruction multiple-data (SIMD) instruction set and optimizing the microarchitecture design to improve the performance. We also arrange the inference schedule to guarantee scalability on multicores. The experimental results show that the proposed accelerator maintains high multiply-accumulation (MAC) utilization for all common operators and achieves high performance with 4-7 x speedup against NVIDIA RTX2080Ti GPU. Finally, the proposed accelerator is manufactured using TSMC 28-nm technology, achieving 1 GHz for each core, with a peak performance of 13 TOPS.

关键词： Network-on-chip (NoC) neural network (NN) inference accelerating out-of-order (OoO) superscalar processor reduced instruction set architecture

来源：评论

学校读者我要写书评

暂无评论

Tested mirror precision alignment system using a pinhole point diffraction interferometer based on machine vision

引用

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS image SCIENCE AND VISION 2024年第8期41卷 1452-1460页

作者： Lu, Jiasheng Li, Bing Zhao, Zhuo Geng, Leqi Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn 99 Yanxiang Rd Xian 710054 Shaanxi Peoples R China Xi An Jiao Tong Univ Int Joint Res Lab Micro Nano Mfg & Measurement Tec Xian 710049 Shaanxi Peoples R China Chinese Acad Sci Changchun Inst Opt Fine Mech & Phys State Key Lab Appl Opt Changchun 130033 Peoples R China

In the pinhole point diffraction interferometer (PPDI), proper alignment between the reflection spot of the tested component and the pinhole is critical to obtain accurate interferograms. At present, adjusting for tilt error requires manual manipulation, and defocus error cannot be corrected. These limitations impede the instrumentation process of PPDI. To address this issue, the proposed tested mirror alignment system utilizes diffraction theory to analyze the mathematical error caused by the misalignment of the tested mirror's reflected beam and pinhole. An alignment system based on machine vision was designed according to specific requirements. This system incorporates a CCD camera with a zoom lens, the classic PPDI with a pinhole substrate containing a lithography-made mark, and a 3-DOF stepper motor adjusting frame to mount the tested mirror. Additionally, image processing algorithms and step motor driving programs were applied to achieve precise alignment. The system implementation and experimental results indicated that the tilt errors are well-controlled, achieving the defocus error modification, making the interferogram acquisition process more convenient. From the results, this system offers desirable precision and efficiency for PPDI's tested mirror alignment. (c) 2024 Optica Publishing Group

关键词： CCD cameras Diffraction theory Extreme ultraviolet lithography Machine vision Optical systems Optical testing

来源：评论

学校读者我要写书评

暂无评论

Design of Cloud Platform for Efficient Remote Sensing Big Data processing Based on Open Stack

Design of Cloud Platform for Efficient Remote Sensing Big Da...

引用

2023 International Conference on Integrated Intelligence and Communication systems, ICIICS 2023

作者： Huang, Yan Zhang, Weimeng Xi'an Traffic Engineering Institute Shaanxi Xi'an China Xi'an Technical School Shaanxi Xi'an China

ISBN: (纸本)9798350315455

The rapid preparation of computing resources is an important step to realize efficient remote sensing image processing. It takes a lot of time for researchers to prepare hardware resources and deploy computing framework. It often mistakes in the preparation and careless deployment of the framework which can lead to high research costs. To solve this problem, this paper uses Open Stack to virtualize hardware resources and uses Linux Shell scripting language to quickly prepare and deploy the Spark parallel computing environment. In this paper, based on the remote sensing image change detection method of connection condition, for example, the data processing algorithm in advance import platform algorithms library, component library, used to support the remote sensing image change detection of business flow of creation and recognition, resources rapid preparation, execution and presentation of the results of the algorithm and implement of massive remote sensing image change detection and efficient. It effectively improves the efficiency of remote sensing data management. © 2023 IEEE.

关键词： linux shell open stack remote sensing data management spark

来源：评论

学校读者我要写书评

暂无评论

Enhancing domain adaptation for plant diseases detection through Masked image Consistency in Multi-Granularity Alignment

引用

EXPERT systems WITH APPLICATIONS 2025年 276卷

作者： Guo, Guinan Lai, Songning Wu, Qingyang Shou, Yuntao Shi, Wenxu Sun Yat Sen Univ Sch Geog & Planning Guangzhou 510700 Peoples R China Shandong Univ Sch Informat Sci & Engn Qingdao 266237 Peoples R China Univ Calif Los Angeles Dept Environm Hlth Sci Los Angeles CA 90095 USA Xi An Jiao Tong Univ Sch Comp Sci Xian 710049 Peoples R China Univ Chinese Acad Sci Aerosp Informat Res Inst Chinese Acad Sci Beijing 100049 Peoples R China

Plant diseases have various impacts on the environment, encompassing ecosystems, water bodies, soils, and biodiversity. The most direct adverse effect of plant diseases on humans lies in their potential to reduce crop yields, posing a threat to food security. Employing deep learning models for object detection of plant diseases can effectively enhance diseases prevention and control, thereby exerting a positive influence on both ecological environment and sustainable agricultural development. However, during the detection of plant diseases, disparities in environmental conditions, locations, and data styles during data collection can result in significant variations in feature distributions between the training and testing datasets of deep learning models. In reality, the presence of such inter-domain differences leads to a notable decrease in the model's detection performance. Therefore, the primary objective of our study is to enhance the domain generalization capability of plant diseases object detection models. We employed an enhanced version of the object detector and introduced the use of Multi-Granularity Alignment (MGA) for domain adaptation, coupled with Masked image Consistency (MIC) for domain augmentation (MIC-MGA). Initially, we refined and optimized the backbone and neck sections of the object detector, and then combined it with the Multi-Granularity Alignment domain adaptation module, and finally used the Masked image Consistency module inspired by natural language processing to bolster the model's domain generalization detection capabilities. To further scrutinize the cross- domain detection robustness of MIC-MGA, we innovatively applied image style transformation techniques for data augmentation. Finally, we validated the model's performance using plant diseases data collected from various scenarios. Our approach outperformed other algorithms in all three tasks, achieving the highest mean Average Precision (mAP). Our research results affirm that the

关键词： Plant diseases object detection Sustainable development Cross domain Domain adaptation Deep learning

来源：评论

学校读者我要写书评

暂无评论

Untrained Neural Nets for Snapshot Compressive Imaging: Theory and algorithms 38

Untrained Neural Nets for Snapshot Compressive Imaging: Theo...

引用

38th Conference on Neural Information processing systems, NeurIPS 2024

作者： Zhao, Mengyu Chen, xi Yuan, xin Jalali, Shirin ECE Department Rutgers University New Brunswick United States School of Engineering Westlake University China

Snapshot compressive imaging (SCI) recovers high-dimensional (3D) data cubes from a single 2D measurement, enabling diverse applications like video and hyperspectral imaging to go beyond standard techniques in terms of acquisition speed and efficiency. In this paper, we focus on SCI recovery algorithms that employ untrained neural networks (UNNs), such as deep image prior (DIP), to model source structure. Such UNN-based methods are appealing as they have the potential of avoiding the computationally intensive retraining required for different source models and different measurement scenarios. We first develop a theoretical framework for characterizing the performance of such UNN-based methods. The theoretical framework, on the one hand, enables us to optimize the parameters of data-modulating masks, and on the other hand, provides a fundamental connection between the number of data frames that can be recovered from a single measurement to the parameters of the untrained NN. We also employ the recently proposed bagged-deep-image-prior (bagged-DIP) idea to develop SCI Bagged Deep Video Prior (SCI-BDVP) algorithms that address the common challenges faced by standard UNN solutions. Our experimental results show that in video SCI our proposed solution achieves state-of-the-art among UNN methods, and in the case of noisy measurements, it even outperforms supervised solutions. Code is publicly available at https://***/Computational-Imaging-RU/SCI-BDVP. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantitative Measurement of Hydrodynamics in a Binary Fluidized Bed by Capacitance Probes

引用

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH 2024年第14期63卷 6297-6312页

作者： Wan, Zhen Wang, Hao Lu, Youjun Xi An Jiao Tong Univ State Key Lab Multiphase Flow Power Engn Xian 710049 Shaanxi Peoples R China

The hydrodynamics of binary particle mixing in a gas-solid fluidized bed were measured by using the capacitance probe method. A novel output voltage signal processing method based on a double threshold was proposed. Originally employed for voidage measurement in monodisperse systems, the capacitance probe method has been successfully extended to assess bubble and mixing characteristics in binary systems by establishing bubble and emulsion phase search algorithms. Through direct comparison with digital image analysis (DIA), quantiles of 0.15 and 0.45 were determined as thresholds for identifying emulsion and bubble phase, respectively. Experimental results demonstrated that under steady-state conditions, the volume ratio of jetsam decreased with increasing bed height, while higher gas velocities enhanced longitudinal and transverse mixing. Average bubble size and rising velocity increased with both the probe height and gas velocity. An improved empirical correlation for bubble diameter was proposed based on variations in local bed mixing degree, yielding a relative error below 20%. The average bubble rising velocity exhibited a direct relationship with the bubble diameter. Relative errors of measured velocities obtained through the capacitance probe method, DIA method, and empirical relation all remained below 15% across each operating condition.

关键词： Bubbles Electrical properties Emulsions Mathematical methods Probes

来源：评论

学校读者我要写书评

暂无评论

A Study on multi-scale landscape character extraction combining GIS and graphic processing algorithms 3

A Study on multi-scale landscape character extraction combin...

引用

3rd International Conference on Environmental Remote Sensing and Geographic Information Technology, ERSGIT 2024

作者： Wang, Shuwei Liu, Yang Li, Guangqi Su, Xueying Wang, Sen Bai, Xuyong Center for Geophysical Survey China Geological Survey Langfang China Technology Innovation Center for Earth Near Surface Detection China Geological Survey China

ISBN: (纸本)9781510690219

This research presents an innovative approach to accurately extract multi-scale landscape characters by combining geographic information systems (GIS) and graphic processing algorithms. It is essential to recognize and analyze landscape characters at different scales. This study uses GIS advantages in spatial analysis and the K-Means clustering algorithm in image enhancement, feature extraction, image segmentation, and color quantification. Through image interpretation and deep learning, the distribution characteristics of buildings in Langfang City are obtained to provide guidance and suggestions for the future construction and development of the city. The proposed method covers data preparation, algorithm design, and system implementation. In addition, the future research direction of improving the method is also discussed, and the possibility of its application in other fields is explored. © 2025 SPIE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Downhole image Reconstruction in Oil and Gas Drilling through Low Rank Sparse Models 3

Enhancing Downhole Image Reconstruction in Oil and Gas Drill...

引用

3rd International Conference on Digital Society and Intelligent systems, DSInS 2023

作者： Zhou, Yixi Li, Lin Xue, Chaoyang Ji, Kexin School of Electronic Engineering Xi'an Shiyou University Xi'an710065 China

ISBN: (纸本)9798350331387

para>Effective subsurface monitoring is vital in oil drilling. This study emphasizes the need for an algorithm to streamline video transmission from underground to the wellsite, overcoming bandwidth and interference challenges for high-quality transmission. It employs low-rank and sparse models to enhance image quality. Comparing three image processing algorithms, the Structured Low Dimensional Representation (SLDR) algorithm stands out. The research aims to improve subsurface image accuracy, ensuring underground pipeline system safety and integrity. © 2023 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based High-Speed Remote Sensing Satellite image Data Transmission System 10th

FPGA-Based High-Speed Remote Sensing Satellite Image Data Tr...

引用

10th International Conference on Signal and Information processing, Network and Computers, ICSINC 2022

作者： He, Yifeng Sun, Peng Liu, Qian Zhang, Hao Zhao, Dayang Xi’an Institute of Space Radio Technology Xi’an710100 China

ISBN: (纸本)9789811999673

At present, with the increasing number of remote sensing satellite systems established in China, a large amount of remote sensing satellite image data has been obtained. Based on FPGA, this paper studies the transmission of high-speed remote sensing satellite image data, studies the image characteristics, image preprocessing methods and image detection principles of remote sensing satellite images, and analyzes various methods of image preprocessing. For different targets and different image backgrounds, the specific processing algorithms are also different. Only by flexibly using the basic theory of image processing can a good image processing effect be achieved. Among them, the fast connected region labeling algorithm designed and implemented can realize the merging of equivalent pairs while scanning. The results show that the system can reliably implement the algorithm in this paper, complete the processing of image data, and meet the requirements of the project. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Field programmable gate arrays (FPGA)

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：