检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

6,882 篇 会议
159 篇 期刊文献
3 册 图书
2 篇 学位论文

馆藏范围

7,046 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

3,979 篇 工学
- 2,184 篇 计算机科学与技术...
- 1,231 篇 电气工程
- 1,219 篇 软件工程
- 844 篇 信息与通信工程
- 476 篇 光学工程
- 430 篇 控制科学与工程
- 426 篇 生物医学工程（可授...
- 327 篇 仪器科学与技术
- 322 篇 电子科学与技术（可...
- 280 篇 机械工程
- 249 篇 生物工程
- 148 篇 材料科学与工程（可...
- 117 篇 测绘科学与技术
- 98 篇 航空宇航科学与技...
- 92 篇 核科学与技术
- 87 篇 化学工程与技术
- 70 篇 动力工程及工程热...
- 70 篇 交通运输工程
2,307 篇 理学
- 1,730 篇 物理学
- 448 篇 数学
- 266 篇 生物学
- 120 篇 统计学（可授理学、...
- 117 篇 系统科学
- 105 篇 化学
1,191 篇 医学
- 924 篇 临床医学
- 334 篇 特种医学
- 90 篇 基础医学(可授医学...
503 篇 管理学
- 429 篇 管理科学与工程(可...
- 100 篇 图书情报与档案管...
- 81 篇 工商管理
55 篇 农学
51 篇 法学
32 篇 经济学
15 篇 教育学
12 篇 文学
8 篇 军事学
8 篇 艺术学

主题

1,015 篇 image quality
331 篇 image processing
327 篇 image coding
323 篇 image reconstruc...
296 篇 image segmentati...
274 篇 feature extracti...
249 篇 image enhancemen...
229 篇 cameras
199 篇 visualization
190 篇 deep learning
135 篇 image edge detec...
128 篇 image resolution
123 篇 humans
120 篇 psnr
117 篇 accuracy
115 篇 image compressio...
107 篇 real-time system...
105 篇 training
100 篇 three-dimensiona...
100 篇 image color anal...

机构

10 篇 chitkara univers...
9 篇 eastman kodak co...
8 篇 purdue univ sch ...
8 篇 johns hopkins un...
8 篇 beijing universi...
7 篇 univ chinese aca...
7 篇 univ arizona col...
7 篇 chinese acad sci...
7 篇 johns hopkins un...
7 篇 university of ch...
6 篇 shandong institu...
6 篇 univ sci & techn...
6 篇 tianjin univ sch...
6 篇 school of electr...
6 篇 school of intell...
6 篇 univ arizona dep...
6 篇 univ penn dept r...
5 篇 nanyang technol ...
5 篇 institute for in...
5 篇 peking univ peop...

作者

17 篇 triantaphillidou...
10 篇 williams don
9 篇 allebach jan p.
9 篇 pedersen marius
9 篇 agaian sos
8 篇 jacobson ralph e...
8 篇 bovik alan c.
8 篇 zhai guangtao
8 篇 burns peter d.
7 篇 busch christoph
7 篇 liu ming
7 篇 panetta karen
7 篇 chetouani aladin...
7 篇 kupinski matthew...
7 篇 pfefer joshua
7 篇 wueller dietmar
7 篇 heynderickx ingr...
7 篇 siewerdsen j. h.
6 篇 zhang lei
6 篇 liu xinwei

语言

6,914 篇 英文
83 篇 其他
50 篇 中文
6 篇 土耳其文
1 篇 西班牙文
1 篇 法文

检索条件"任意字段=Conference on Image Quality and System Performance XII"

共 7046 条记录，以下是51-60 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Enhancing Data Security and Efficiency: A Hybrid Cryptography Approach (AES + ECC) Integrated with Steganography and Compression Algortihm

Enhancing Data Security and Efficiency: A Hybrid Cryptograph...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International conference on

作者： Akash Badhan Simarjit Singh Malhi School of Computer Science and Engineering Lovely Professional University Phagwara India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

The paper presents a novel approach for enhancing data security and efficiency using a hybrid cryptography model that is Advanced Encryption Standard (AES) and Elliptic Curve Cryptography (ECC) with steganography and compression techniques to conceal the encrypted data within image file, also compression technique applied to reduce storage usage. The system employs AES for secure data encryption due to its fast encryption time and reliability, while ECC is utilized for encrypting AES keys, benefiting from ECC's lower computational demands and smaller key sizes, which offer secure key exchange. Further to mask the encrypted data, steganography is implemented with inverted least significant bit (LSB) technique. Additionally, the model incorporates the WebP compression algorithm to reduce the overall data size, to facilitate data transmission efficiently without losing data integrity or security. Experimental results of research indicate that the system not only secures data effectively but also preserves the visual quality of digital carrier images. The steganalysis shows the performance of the proposed system performed is quantified by a Peak Signal-to-Noise Ratio (PSNR) of 68.90 and a Mean Squared Error (MSE) OF 0.0083, reflecting minimal and acceptable degradation in image quality. These metrics show the system's capability to maintain excellent image fidelity post encryption and embedding, confirming its reliability for secure communication applications where maintaining data integrity and efficiency is crucial.

关键词： image quality Steganography image coding PSNR Data integrity Elliptic curve cryptography Data models Encryption Reliability Data communication

来源：评论

学校读者我要写书评

暂无评论

Enhancement of image Resolution using RDB

Enhancement of Image Resolution using RDB

引用

2025 International conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Anu, P. Kalyani, N. Mohanapriya, D. Rekha, S. Vimala, S. School of Computing Thanjavur613402 India Sastra Deemed to be University Thanjavur613402 India Psg College of Arts & Science Department of Computer Science Coimbatore641014 India Department of Computer Applications Tirunelveli627011 India

ISBN: (纸本)9798331527495

By using hierarchical features, Convolutional Neural Networks (CNNs) which is a Deep Learning method have shown notable improvements in image restoration (IR) tasks. However, poor performance arises from many existing deep CNN-based IR models' inability to adequately use the hierarchical information included in low-resolution images. To address the problem of image resolution, this study uses the Residual Dense Network (RDN) technology. RDN seeks to improve how well it uses hierarchical features from every convolutional layer. To be more precise, we have extracted localized information using the Residual Dense Block (RDB) and dense convolutional layers. By connecting all the layers of the present RDB twice the state of the preceding RDB, RDB creates a contiguous memory system. We incorporated Local Feature Fusion (LFF) into Residual Dense Blocks to improve the feature extraction from historical and current local data. This improved the stability of training for larger networks. After getting dense local properties, we used Global Feature Fusion (GFF) to extract global hierarchical features. Through the use of RDN in image Super-Resolution (ISR), we have proven its efficacy. Our tests on real datasets show that RDN performs exceptionally well on ISR tasks in visual quality as well as quantitative measures. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Vessel Registration Number Detection and Recognition system

Vessel Registration Number Detection and Recognition System

引用

2025 IEEE/CVF Winter conference on Applications of Computer Vision Workshops, WACVW 2025

作者： Fabijanić, Matej Magdalenić, Maja Obradović, Juraj Kapetanović, Nadir Ferreira, Fausto Mišković, Nikola University of Zagreb Faculty of Electrical Engineering and Computing Croatia

ISBN: (纸本)9798331536626

Accurate identification of ships is vital for global trade and maritime security. More specifically, reliable recognition of the vessel registration number helps in orderly navigation and port use for maritime transportation activities. The purpose of this research was to develop and analyze different methods for detecting vessel registration numbers with a monocular camera. We used existing OCR tools available online and modified them to improve their out-of-the-box performance. Three neural network-based text detection methods were developed and tested. All three methods use different text region detection modules for real scenes, while available OCR software is used in all of them for specific character recognition. The methods are compared using standard optical character recognition metrics. The best method that was developed uses a deep neural network model to detect a vessel, then another fine-tuned neural network model to detect a text region, coupled with deterministic image processing methods to improve picture quality. In conclusion, with an accuracy of 72.69% recognized characters of vessel registrations using a limited image dataset, we achieve satisfactory results. Further effort focusing on collecting and annotating diverse maritime environment datasets featuring footage of vessels with visible registration numbers is needed to have a more reliable and robust system. © 2025 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Undecimated discrete wavelets transform-based image fusion and de-noising in FPGA

Undecimated discrete wavelets transform-based image fusion a...

引用

International conference on Energy, Power, Environment, Control and Computing (ICEPECC 2025)

作者： Fahad Ahmad Muhammad H. Ahmed Yumna Adnan Department of Electrical Engineering University of Gujrat Gujrat Pakistan

ISBN: (数字)9781837243150

image processing is a vast field of study and has gained significant importance in recent years. image fusion and denoising a re most important methods in the field of image processing. The project develops an image processing system on a Field-Programmable Gate Array (FPGA) platform that uses the Undecimated Discrete Wavelet Transform (UDWT) for image fusion and denoising. By merging several images into a single better image and using sophisticated wavelet techniques to reduce noise the aim is to improve image quality. UDWT preserves image details by maintaining high-frequency components without down sampling. Reconstructing denoised images thresholding to remove noise and dividing images into wavelet coefficients are the steps in the process that culminate in the creation of a superior composite image. Due to its ability to process data in parallel the FPGA platform is preferred over conventional CPU-based techniques for processing large amounts of data quickly. Suitable for real-time applications, this method takes advantage of the intrinsic parallelism of FPGA to process data quickly and efficiently. According to the results the FPGA-based system performs faster and produces better images than traditional techniques making it a reliable option for high-performance image processing application.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Brake Drum Surface Defect Detection system Based on Machine Vision Technology

Research on Brake Drum Surface Defect Detection System Based...

引用

IEEE Information Technology and Mechatronics Engineering conference (ITOEC)

作者： Xuefeng Han Bin Zheng School of Intelligent Manufacturing Panzhihua University Panzhihua

ISBN: (数字)9798331529482

ISBN: (纸本)9798331529499

This paper focuses on the development of an efficient and accurate brake drum surface defect detection system to meet the growing demands for brake safety performance in the manufacturing industry. The system analyzes common defect types on brake drum surfaces, such as chips and cracks, and designs a comprehensive detection scheme. In terms of hardware architecture, it integrates high-resolution image acquisition equipment and a customized lighting system to ensure clear and comprehensive images of the brake drum surface under different lighting conditions. At the software level, the system implements image preprocessing steps, including noise filtering and contrast enhancement, to optimize image quality. Subsequently, advanced feature extraction algorithms are used to precisely locate and analyze the characteristic information of potential defects. Ultimately, the system achieves the identification of brake drum surface defects. Experimental results show that the system not only effectively distinguishes between different types of surface defects but also exhibits significant advantages in detection speed and accuracy, significantly enhancing the efficiency of quality control on brake drum production lines. Compared with traditional manual detection methods, this system significantly reduces the rates of missed and false detections while alleviating the human workload, providing strong support for the intelligent upgrade of the brake manufacturer industry.

关键词： Accuracy Machine vision Software algorithms Lighting Hardware Safety Brakes Surface cracks Surface treatment Defect detection

来源：评论

学校读者我要写书评

暂无评论

Integration of Large Language Models and Computer Vision Algorithms in LMS: A Methodology for Automated Verification of Software Tasks and Multimodal Analysis of Educational Data

Integration of Large Language Models and Computer Vision Alg...

引用

International Russian Smart Industry conference (SmartIndustryCon)

作者： E. I. Markin V. V. Zuparova A. I. Martyshkin Penza state technological University PSTU Penza Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

This paper presents a study on the design and development of a learning management system (LMS) integrated with large language models (LLMs) and image recognition/generation algorithms to automate software task validation and multimodal educational data analysis. The purpose of the development is to improve the quality of feedback for learners, deepen the understanding of errors made and expand the capabilities of the system by synthesizing formal LLM models and visual processing algorithms. The system is based on the use of domestic LLMs such as GigaChat and YandexGPT, Retrieval-Augmented Generation (RAG) technology, and modern computer vision algorithms. The system architecture is described, including GitVerse for code storage, GitVerse Actions for automated testing of solutions in Docker containers, and image processing modules for analyzing and generating visual data in the educational process. The conducted experiment demonstrates the effectiveness of the integrative approach, which allows to improve the quality of feedback and increase the performance of students. Prospects for further research include optimization of computational resources and development of techniques for integrated analysis of multimodal educational data.

关键词： Visualization Computer vision Codes image recognition Costs Large language models Computational modeling Software algorithms Trajectory Testing

来源：评论

学校读者我要写书评

暂无评论

Secure and High-Fidelity Medical image Generation: A GAN-Based Approach for Steganography

Secure and High-Fidelity Medical Image Generation: A GAN-Bas...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International conference on

作者： B. Sumitra S. Selvin Ebenezer G. Vallathan B. Sundaramurthy Venkata Rami Reddy Dorsela Department of ECE Geethanjali College of Engineering & Technology Hyderabad India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of ECE Geethanjali College of Engineering and Technology Hyderabad India Department of CSE Vinayaka Missions Research Foundation Vinayaka Missions Kirupananda Variyar Engineering College (Deemed to be University) Salem India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Traditional image steganography methods embed secret data into cover images but often face detection by steganalysis tools due to detectable pixel modifications, which increase the risk of data leakage. These techniques also typically degrade image quality and offer limited capacity. To overcome these challenges, a novel approach for medical imaging is proposed, integrating Generative Adversarial Networks (GANs), PatchGAN, Adaptive LSB steganography, and a dual attention mechanism. PatchGAN improves fine-grained texture details, while Adaptive LSB securely embeds sensitive data within the images. The dual attention mechanism highlights critical regions, enhancing both image clarity and diagnostic accuracy. This method improves image quality and security, benefiting clinical decision-making and patient outcomes. The system is evaluated against traditional methods like GAN and IDGAN using metrics such as embedding capacity, classification accuracy (stego, cover, global), and discriminator loss. Results demonstrate that the proposed system outperforms existing techniques, offering significant improvements in both performance and security for medical imaging applications.

关键词： image quality Steganography Attention mechanisms Adaptive systems Accuracy image synthesis Generative adversarial networks Security Data communication Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Research on Digital Creative Content Generation system Based on Artificial Intelligence

Research on Digital Creative Content Generation System Based...

引用

Cybersecurity, Internet of Things and Soft Computing (CITSC), Asia-Europe conference on

作者： Guanfeng Lv Guangzhou Huashang Vocational College Guangzhou Guangdong China

ISBN: (数字)9798331504205

ISBN: (纸本)9798331504212

A new algorithm framework is proposed, which combines the self-attention mechanism and the transformer model, to enhance the efficiency and quality of the creation of digital creative content. The system realizes the semantic understanding and generation tasks of multimodal data by designing a multi-layer Transformer architecture, and fully exploits the context modeling ability of the self-attention mechanism. To verify the performance of the algorithm, this paper simulates the model in image generation, text generation and multimodal content generation tasks. The test results show that the system has achieved significant improvements in the coherence, diversity and innovation of the generated content. Experiments on a public dataset show that the BLEU score of the generated text content is 12.3% higher than that of the traditional method, the FID index of image generation is reduced by 15.7 % , and the semantic consistency score of multimodal generation reaches 92.4%. These results prove the superiority and practicality of the proposed algorithm. This research not only provides a new way to generate digital creative content, but also provides a theoretical basis for the further integration of AI and creative industry.

关键词： Technical requirements Technological innovation image synthesis Simulation Scalability Semantics Diversity reception Coherence Transformers Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

EfficientNet-Based Feature Extraction and Ensemble Learning for Tomato quality Classification 3

EfficientNet-Based Feature Extraction and Ensemble Learning ...

引用

3rd International conference on Intelligent systems, Advanced Computing, and Communication, ISACC 2025

作者： Shanthini, S. Dheeran, S. Anish Partho, M. St. Joseph's College of Engineering Department of CSE Tamil Nadu Chennai India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Tomato quality and maturation detection play a critical role in ensuring the freshness and ripeness of tomatoes in the agricultural and food industries. Traditional methods for evaluating tomato quality are often labor-intensive, prone to human error, and inconsistent. This paper presents a robust machine learning-based system for automating the detection of tomato quality and maturation stages using image data. We leverage EfficientNetB0 as the backbone for feature extraction due to its state-of-the-art performance in image classification tasks with minimal computational cost. The extracted features are then classified using an ensemble of traditional machine learning classifiers, including Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Gradient Boosting Machine (GBM), integrated through a stacking ensemble approach. To improve generalization, cross-validation techniques and model fine-tuning are employed, and model explainability is achieved through Grad-CAM visualizations, offering insight into model decisions. The system is evaluated on a dataset of tomatoes categorized as fresh, rotten, mature, and immature. Our approach achieves high accuracy of 80% in classifying tomato quality and maturation, demonstrating the effectiveness of combining EfficientNetB0 for feature extraction with ensemble learning for classification. This study introduces a novel hybrid system for automating the detection of tomato quality and maturation stages using advanced image processing and machine learning techniques. EfficientNet-B0 serves as the backbone for feature extraction, enabling high accuracy with minimal computational resources. Extracted features are processed through a stacking ensemble comprising Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), and Gradient Boosting Machine (GBM) classifiers. The model leverages Grad-CAM visualizations to enhance interpretability. Comprehensive evaluations on a diverse tomato d

关键词： Agricultural Automation Deep Learning EfficientNetB0 Ensemble Learning Feature Extraction Grad-CAM Gradient Boosting Machine (GBM) image Classification K-Nearest Neighbors (KNN) Machine Learning Maturation Stage Classification Random Forest (RF) Support Vector Machine (SVM) Tomato quality Detection

来源：评论

学校读者我要写书评

暂无评论

ELL-ORB-SLAM: Improved Robust Monocular Visual SLAM Algorithm Based on image Enhancement and Dynamic FAST Threshold for Low-light Environment

ELL-ORB-SLAM: Improved Robust Monocular Visual SLAM Algorith...

引用

Consumer Electronics and Computer Engineering (ICCECE), 2021 IEEE International conference on

作者： Jiahui Dai Tao Yan Xin Jiang Hanguang Xiao Hongguo Xin Chengbao Zhang School of Artificial Intelligence Chongqing University of Technology Chongqing China

ISBN: (数字)9798331533113

ISBN: (纸本)9798331533120

The accuracy of visual localization estimation heavily relies on the quality of input images and feature point extraction, with variations in illumination significantly impacting matching results under challenging conditions. To address this, we propose an enhanced ORB-SLAM algorithm (ELL-ORB-SLAM) based on dynamic adaptive FAST thresholds and image enhancement techniques, including illumination map estimation, improved Truncated Adaptive Gamma Correction, and CLAHE, to improve performance in low-light conditions and refine feature point extraction. Experiments conducted on the EuRoC, KITTI, and ETH3D datasets demonstrate that ELL-ORB-SLAM significantly outperforms the state-of-the-art ORB-SLAM3, particularly in challenging environments. Additionally, real-world tests using a monocular camera showcase the system's robustness and versatility across diverse settings.

关键词： Location awareness image quality Visualization Simultaneous localization and mapping Heuristic algorithms Lighting Estimation Feature extraction Robustness image enhancement

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 2 3 4 5 6 7 8 9 10 11 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：