检索结果-内蒙古大学图书馆

20th ieee international conference on Advanced Video and signal-based Surveillance (AVSS)

作者： Sun, Ruotong Liao, Fayang He, Jing Liu, Ying Yi, Wei Fan, Qinrui Hu, Shu Wang, Xin Hu, Jing Chengdu Univ Informat Technol Chengdu Peoples R China Purdue Univ W Lafayette IN 47907 USA SUNY Albany Albany NY 12222 USA

ISBN: (纸本)9798350374292;9798350374285

In the field of medical imaging, 3D image reconstruction has emerged as a crucial technique for accurate disease diagnosis. Neural Radiance Field (NeRF) has shown promise in generating high-quality 3D models through deep learning, but its application in medical imaging remains limited. This paper presents RepMedGraf, an improved model addressing the limitations of NeRF. RepMedGraf utilizes a generator based on lightweight RepVGG Blocks instead of MedNeRF model. By doing so, the risk of overfitting is reduced, and training efficiency is improved. The proposed method is trained on publicly available chest and knee datasets. Comparative evaluations are conducted based on the generated radiation fields, demonstrating the effectiveness and quality of the 3D models produced by RepMedGraf. The results highlight the potential of RepMedGraf as a valuable tool in medical imaging for enhanced diagnostic accuracy and improved patient care.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

PLC signal Level based Traffic Light System Using RPi: An Experimental Setup 3

PLC Signal Level Based Traffic Light System Using RPi: An Ex...

引用

3rd international conference for Advancement in technology, ICONAT 2024

作者： Kumawat, Ashok Kumar Manipal University Jaipur Dept. of Mechatronics Engineering Jaipur India

ISBN: (纸本)9798350354171

It is necessary to regularly enhance the traffic light system's control using the newest technology. The PLC-based systems that are now in use make it difficult to adopt modern technologies like artificial intelligence, machine learning, and the internet of things etc. This work aims to convert the logic level signal based on PLC to a logic level signal based on Raspberry Pi. A raspberry pi is used as the control unit in the development of an experimental four direction-based traffic light prototype. Two different types of logic level converters are used in this system to create signals that are compatible with both 24 V traffic light system and Raspberry Pi. Python programming on the Raspberry Pi is used to control the entire system. © 2024 ieee.

关键词： Traffic signals

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Underwater image Enhancement Techniques

Performance Evaluation of Underwater Image Enhancement Techn...

引用

2024 ieee international conference on Information technology, Electronics and Intelligent Communication systems, ICITEICS 2024

作者： Shubhangi, Adagale-Vairagar Gupta, Praveen CSMU Navi Mumbai Mumbai India

ISBN: (纸本)9798350382693

Absorption, scattering, and colour distortion make underwater photography difficult. Marine biology, underwater archaeology, and surveillance need better underwater photos. This research compares cutting-edge underwater image-enhancing methods to assess their efficacy and usefulness. This paper provides a comparative analysis of the various filtering approaches for underwater image enhancement, such as median filtering, average filtering, Gaussian filtering, Wiener filtering, and wavelet-based soft thresholding. The performance of these techniques is evaluated based on the mean square error, peak signal-to-noise ratio, average gradient, PCQI, and UICQI. The effectiveness of the suggested filtering scheme is validated on some sample images of the public UIEB dataset. It provides the analytical finding, advantages, disadvantages and performance of the different techniques for wide variety of underwater images enhancement. The paper also explores underwater image enhancement issues and future approaches. The promising research directions are integrating domain-specific information, real-time processing, and adaptive algorithms for dynamic underwater scenes. The discoveries help increase underwater photography visibility and interpretability, increasing underwater exploration and monitoring systems. © 2024 ieee.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Text-to-image Retrieval based on Zero-shot Transfer Learning with CLIP Model and Vector Database 11

Text-to-image Retrieval Based on Zero-shot Transfer Learning...

引用

11th ieee international conference on Behavioural and Social Computing, BESC 2024

作者： Xie, Junfeng Chen, Junying School of Software Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798331531904

With the continuous increase in the number of internet users, the explosion of multimodal data on the web has led to a growing demand for image retrieval. Current text-to-image retrieval systems often rely on keyword matching, which frequently fails to accurately capture users' retrieval needs. This work proposes a text-to-image retrieval method based on zero-shot transfer learning with the CLIP model and vector database, designed to be applied in text-to-image retrieval systems. By leveraging the semantic alignment capability of the CLIP model for text and images, this study effectively addresses the semantic gap problem in text-to-image retrieval. Additionally, the method utilizes the Milvus database for efficient storage and retrieval of image feature vectors, thereby enhancing system stability. Experimental results on the Flickr30k dataset demonstrate that this method improves the accuracy of text-to-image retrieval, verifying its effectiveness. Furthermore, this work extends the proposed method by incorporating the iFLYTEK Spark Cognitive Model to support image retrieval using Chinese text descriptions, further broadening the system's applicability and reliability. © 2024 ieee.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence image Detection System based on internet of Things 2

Artificial Intelligence Image Detection System Based on Inte...

引用

2nd international conference on 3D Immersion, Interaction and Multi-Sensory Experiences, ICDIIME 2023

作者： Liu, Guangcai Zhang, Wenbin Sun, Li Chen, Xianya Wu, Liqin Lin, Zhongjie Hao, Liang North Automatic Control Technology Institute Shanxi Taiyuan China

ISBN: (纸本)9798350323818

With the development of image recognition technology and computer technology, artificial intelligence is more and more applied in people's production and life. In addition, the internet of Things technology can be seen everywhere in our daily life. The purpose of this paper is to design an image detection system based on the internet of Things technology, which uses CMOS image sensor to obtain real-time images, obtains candidate flame areas through flame judgment of image pixels, and uses flame detection method of in-depth study of neural network for flame detection. It communicates through the internet of Things module and sends fire alarms and alarm messages to the server platform based on the flame detection results. The results show that the system designed in this paper meets the design requirements. © 2023 ieee.

关键词： systems analysis

来源：评论

学校读者我要写书评

暂无评论

A novel SAR image denoising method based on self-supervised network 2

A novel SAR image denoising method based on self-supervised ...

引用

2nd ieee international conference on signal, Information and Data Processing, ICSIDP 2024

作者： He, Kunze Li, Pucheng Wang, Guanxing Song, Ziyuan Li, Linghao Wang, Jianping Beijing Institute of Technology School of Information and Electronics Chongqing Innovation Center Chongqing China School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (纸本)9798331515669

Noise suppression is an important preprocessing step for sythetic aperture radar (SAR) image interpretation. In particular, noise affects the quality of SAR images, which in turn affects the subsequent down streaming processing, such as target identification, classificatio, etc. In this paper, a novel SAR image denoising method based on self-supervised framework is proposed, which utilizes the statistical distribution characteristics of noise and conducts denoising processing through the self-supervised network framework, and then achieves high-quality denoised radar image. Moreover, the effectiveness of the proposed method is verified through computer simulation experiments. © 2024 ieee.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Data Security using Edge-Preserving image Interpolation for Reversible Data Hiding 2

Enhancement of Data Security using Edge-Preserving Image Int...

引用

2nd ieee international conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Pandey, Supriya Pandey, Shrawan Kumar Tripathi, Abhinandan Buddha Institute of Technology Department of Computer Science & Engineering Gorakhpur India

ISBN: (纸本)9798350368109

The proliferation of online data, video, and audio transfer over the internet has made Reversible Data Hiding (RDH) a significant area of research. However, embedding data into an image can be challenging as it can cause distortion and degrade image quality. To mitigate this issue, we have proposed edge-preserving image smoothing before data embedding to reduce distortion. The outcomes of proposed schemes are evaluated using metrics such as Peak signal to Noise Ratio (PSNR), encoding capacity (EC) including incorporation time and embedding speed. The study reveals that the proposed technique surpasses existing state-of-the-art methods. © 2024 ieee.

关键词： EC PSNR RDH

来源：评论

学校读者我要写书评

暂无评论

PRIVACY-PRESERVING DEEP LEARNING USING DEFORMABLE OPERATORS FOR SECURE TASK LEARNING 49

PRIVACY-PRESERVING DEEP LEARNING USING DEFORMABLE OPERATORS ...

引用

49th ieee international conference on Acoustics, Speech, and signal Processing (ICASSP)

作者： Perez, Fabian Lopez, Jhon Arguello, Henry Univ Ind Santander Dept Comp Sci Bucaramanga 680002 Colombia

ISBN: (纸本)9798350344868;9798350344851

In the era of cloud computing and data-driven applications, it is crucial to protect sensitive information to maintain data privacy, ensuring truly reliable systems. As a result, preserving privacy in deep learning systems has become a critical concern. Existing methods for privacy preservation rely on image encryption or perceptual transformation approaches. However, they often suffer from reduced task performance and high computational costs. To address these challenges, we propose a novel Privacy-Preserving framework that uses a set of deformable operators for secure task learning. Our method involves shuffling pixels during the analog-to-digital conversion process to generate visually protected data. Those are then fed into a well-known network enhanced with deformable operators. Using our approach, users can achieve equivalent performance to original images without additional training using a secret key. Moreover, our method enables access control against unauthorized users. Experimental results demonstrate the efficacy of our approach, showcasing its potential in cloud-based scenarios and privacy-sensitive applications.

关键词： Computational Imaging Deformable Operators image Privacy image Encryption

来源：评论

学校读者我要写书评

暂无评论

image Segmentation Algorithm of Ischemic Stroke based on Wavelet Pooling Neural Network 2

Image Segmentation Algorithm of Ischemic Stroke based on Wav...

引用

2nd ieee international conference on signal, Information and Data Processing, ICSIDP 2024

作者： Zhu, Huiyuan Zhai, Yao Wu, Jinghe Lu, Chuwei Zhang, Xianchao Li, Ruide Beijing Institute of Technology School of Cyberspace Science and Technology Beijing China College of Medicine Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Department of Nursing Jiaxing China Beijing Institute of Technology School of Information and Electronics Beijing China Aviation Industry Corporation of China Avic Xi' An Flight Automatic Control Research Institute Xi'an China Jiaxing University Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Jiaxing China

ISBN: (纸本)9798331515669

Ischemic stroke is a high-risk brain disease that causes disability or death in adults worldwide. Rapid diagnosis and treatment, as well as segmentation of ischemic lesions from stroke medical images so that doctors can evaluate and develop treatment plans, are crucial to reducing brain damage. Currently, doctors' manual segmentation of lesions is time-consuming and labor-intensive and prone to missed or misdiagnosed diagnoses, delaying the best time for treatment. A well-trained neural network is considered as an effective aid for image segmentation tasks. However, in the traditional neural network down-sampling process, the pooling layer loses feature information, and the lost information significantly impacts the edge regions. While for medical images, edge regions are crucial features in the segmentation process. Therefore, to address the above issues, in this paper we improve upon the existing stroke lesion segmentation algorithm U-net, we design a segmentation network based on wavelet pooling and attention mechanisms. The network was tested on ISLES 2018 and ISLES 2022 datasets, and the Dice coefficient improved by 2.13% and 1.93% compared to baseline network, respectively. © 2024 ieee.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

TPE-AP: Thumbnail-Preserving Encryption based on Adjustable Precision for JPEG images

引用

ieee internet OF THINGS JOURNAL 2024年第22期11卷 37021-37031页

作者： Chai, Xiuli Cao, Gongyao Gan, Zhihua Zhang, Yushu Ma, Yakun He, Xin Henan Univ Henan Engn Res Ctr Ind Internet Things Sch Artificial Intelligence Zhengzhou 450046 Peoples R China Henan Univ Inst Intelligent Network Syst Intelligent Data Proc Engn Res Ctr Henan Prov Sch Software Kaifeng 475004 Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China

As the development of the internet of Things (IoT), the security of images in social networks is attracting more and more attention. Among the various encryption methods, thumbnail-preserving encryption (TPE) has gained much attention and diverse study, for it has powerful capability of balancing the security and usability of cloud storage images by simultaneously securing privacy and preserving visual information of images. Unfortunately, most of the existing TPE schemes for JPEG images have the disadvantages of limited thumbnail precision or weak security or irreversibility, making them vulnerable to cryptanalysis. To address these issues, we propose a TPE based on adjustable precision (TPE-AP) for JPEG images. First, a joint adjustment strategy is introduced for encrypted quantized QC coefficient (QDCC) and quantized AC coefficient (QACC) of plain image, which makes the security and usability of the thumbnail controllable by exploiting numerical characteristics of QDCC and distribution features of QACC. Second, a time-varying encryption strategy based on international time is presented, characteristics of JPEG compression and quantized coefficients are combined to generate encryption sequences, improving the security of the whole encryption process. In addition, we explore the redundancy of QACC within DCT blocks and provide an improved embedding strategy to solve irreversibility problem. Experimental results show that the peak signal-to-noise ratio (PSNR) of thumbnail-preserving accuracy reaches 52 dB, the file expansion is minimally limited to 6.3%, the decryption time less than 0.13 s, and the mean average precision (mAP) of retrieval attains 62%, it indicates that TPE-AP outperforms the state-of-the-art methods.

关键词： Adjustable precision JPEG image security and usability thumbnail-preserving encryption (TPE) Adjustable precision JPEG image security and usability thumbnail-preserving encryption (TPE)

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：