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

12,600 篇 会议
189 篇 期刊文献
161 册 图书

馆藏范围

12,950 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6,510 篇 工学
- 4,291 篇 计算机科学与技术...
- 2,186 篇 软件工程
- 1,876 篇 电气工程
- 1,291 篇 信息与通信工程
- 840 篇 控制科学与工程
- 652 篇 光学工程
- 463 篇 生物医学工程（可授...
- 441 篇 电子科学与技术（可...
- 437 篇 机械工程
- 427 篇 仪器科学与技术
- 316 篇 生物工程
- 222 篇 测绘科学与技术
- 151 篇 材料科学与工程（可...
- 144 篇 航空宇航科学与技...
- 135 篇 交通运输工程
- 101 篇 安全科学与工程
- 93 篇 网络空间安全
- 84 篇 化学工程与技术
3,128 篇 理学
- 2,086 篇 物理学
- 891 篇 数学
- 357 篇 生物学
- 246 篇 系统科学
- 224 篇 统计学（可授理学、...
- 111 篇 化学
1,434 篇 医学
- 1,272 篇 临床医学
- 193 篇 特种医学
- 157 篇 基础医学(可授医学...
- 99 篇 药学(可授医学、理...
698 篇 管理学
- 426 篇 管理科学与工程(可...
- 293 篇 图书情报与档案管...
59 篇 法学
59 篇 农学
30 篇 教育学
27 篇 文学
26 篇 经济学
17 篇 军事学
15 篇 艺术学
1 篇 哲学

主题

2,662 篇 image processing
1,390 篇 image segmentati...
1,144 篇 signal processin...
609 篇 cameras
607 篇 feature extracti...
585 篇 image edge detec...
521 篇 signal processin...
477 篇 real-time system...
474 篇 image reconstruc...
460 篇 image coding
390 篇 algorithm design...
336 篇 image color anal...
316 篇 deep learning
308 篇 image enhancemen...
304 篇 pixel
300 篇 real time system...
296 篇 object detection
291 篇 computer archite...
286 篇 hardware
284 篇 neural networks

机构

22 篇 signal and image...
19 篇 samara national ...
14 篇 school of electr...
11 篇 samara national ...
11 篇 univ texas san a...
11 篇 department of el...
11 篇 school of electr...
10 篇 center for signa...
9 篇 information syst...
9 篇 institute of ima...
9 篇 tongji universit...
8 篇 university of to...
8 篇 purdue univ sch ...
8 篇 university of ch...
8 篇 electrical compu...
8 篇 image processing...
8 篇 information syst...
8 篇 samara national ...
7 篇 school of electr...
7 篇 department of ma...

作者

19 篇 anon
13 篇 de-shuang huang
13 篇 jagdish chand ba...
11 篇 p. pirsch
10 篇 jie yang
10 篇 panetta karen
10 篇 j.m. mendel
10 篇 r. chellappa
10 篇 a. ortega
9 篇 c.-c.j. kuo
8 篇 frank hannig
8 篇 bovik alan c.
8 篇 hannig frank
8 篇 mahalanobis a
8 篇 ilias maglogiann...
8 篇 carli m.
7 篇 miller jwv
7 篇 busch christoph
7 篇 semenishchev e.
7 篇 zelensky a.

语言

12,254 篇 英文
611 篇 其他
94 篇 中文
19 篇 土耳其文
3 篇 葡萄牙文
2 篇 西班牙文
2 篇 俄文
1 篇 法文

检索条件"任意字段=Conference on Image Processing - Algorithms and Systems XII"

共 12950 条记录，以下是431-440 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：

Advanced HLS for Reconfigurable image processing in Big Data systems 12th

Advanced HLS for Reconfigurable Image Processing in Big Da...

引用

12th International conference on Big Data and Artificial Intelligence, BDA 2024

作者： Bhagirath, K. Pant, Dheeraj Tiwari, Abhishek Khaneja, Vivek Noida201309 India

ISBN: (纸本)9783031818202

This paper introduces novel HLS techniques for reconfigurable and memory-efficient image processing within deep learning frameworks, addressing inherent limitations of current deep learning accelerators (DLAs) due to their dependency on the host processor, leading to pipeline delays and reduced throughput. The proposed approach emphasizes parallelization, on-chip buffering, and scalability, enhancing computational efficiency and throughput for AI applications in big data and edge computing environments. Methodologically, the paper emphasizes mathematical analysis, hardware architecture specification, HLS modeling, Verilog RTL implementation. By addressing these challenges, this work contributes to advancing the performance capabilities of DLAs in deep learning inference tasks. The algorithms integrates seamlessly with DLA IP subsystems, such as AXI interfaces, external (DRAM) and internal (SRAM) memory interfaces, and activation/pooling engines. Key contributions include advanced algorithm design to enhance memory efficiency and reconfigurability, essential for adapting to diverse hardware architectures. Experimental validation demonstrates substantial improvements in computational speed and resource utilization compared to traditional methods, making it suitable for intensive AI tasks in big data analytics. In conclusion, this research presents a framework for integrating HLS techniques into hardware accelerators, facilitating efficient image processing across diverse applications in big data and edge computing. These advancements aim to bolster DLAs’ capabilities in handling complex AI workloads effectively, promising enhanced solutions for AI-driven domains. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

RestoreAgent: Autonomous image Restoration Agent via Multimodal Large Language Models 38

RestoreAgent: Autonomous Image Restoration Agent via Multimo...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： Chen, Haoyu Li, Wenbo Gu, Jinjin Ren, Jingjing Chen, Sixiang Ye, Tian Pei, Renjing Zhou, Kaiwen Song, Fenglong Zhu, Lei The Hong Kong University of Science and Technology Guangzhou China Huawei Noah's Ark Lab Canada The University of Sydney Australia The Hong Kong University of Science and Technology Hong Kong

Natural images captured by mobile devices often suffer from multiple types of degradation, such as noise, blur, and low light. Traditional image restoration methods require manual selection of specific tasks, algorithms, and execution sequences, which is time-consuming and may yield suboptimal results. All-in-one models, though capable of handling multiple tasks, typically support only a limited range and often produce overly smooth, low-fidelity outcomes due to their broad data distribution fitting. To address these challenges, we first define a new pipeline for restoring images with multiple degradations, and then introduce RestoreAgent, an intelligent image restoration system leveraging multimodal large language models. RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration. Experimental results demonstrate the superior performance of RestoreAgent in handling complex degradation, surpassing human experts. Furthermore, the system's modular design facilitates the fast integration of new tasks and models. © 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

High-speed AI image space wavefront sensing using embedded computing: achieving 1000 frames per second 12

High-speed AI image space wavefront sensing using embedded c...

引用

2025 conference on Photonic Instrumentation Engineering

作者： Baudat, Gaston Lavanchy, David Muller, Guillaume Innovat Foresight LLC 4432 Mallard Point Columbus IN 47201 USA Univ Arizona Wyant Coll Opt Sci 1630 E. Univ Blvd Tucson AZ 85721 USA Univ Appl Sci Western Switzerland HEIG VD Route Cheseaux 1Case Postale 521 CH-CH1401 Yverdon Switzerland

ISBN: (纸本)9781510684942;9781510684959

Wavefront sensing is fundamental to numerous scientific and industrial applications in optics, particularly in adaptive optics (AO). This paper presents a high-speed image space AI-powered wavefront sensing system, based on a patented technology known as AI4Wave, that eliminates the need for dedicated wavefront sensors, such as Shack-Hartmann, relying solely on fast cameras and AI edge computing devices, specifically an NVIDIA Jetson embedded module in our implementation. This module could also be utilized in the future to directly control actuators, streamlining the entire AO process. The system captures defocused images of a point source or similar, which are processed by a feedforward artificial neural network (NN) trained exclusively on synthetic data [1]. This approach enables real-time phase retrieval, overcoming the local derivative limitations of Shack-Hartmann sensors and handling large wavefront or surface errors spanning multiple wavelengths. It also provides a unique capability for field-dependent wavefront measurement from a single image of multiple sources. Yu Wu et al. [2] proposed a sub-millisecond phase retrieval method that requires two simultaneous images for optimal performance and NN training on physical data. However, this approach necessitates retraining whenever system parameters, such as f/#, wavelength, or pixel size, are altered. In contrast, AI4Wave employs synthetic, normalized data that is agnostic to most optical layout changes, enabling robust and versatile training and validation. Combined with off-the-shelf NVIDIA hardware, it offers a ready-to-use solution for industrial deployment. By integrating optimized algorithms within modern AI acceleration frameworks, such as NVIDIA TensorRT, and leveraging advanced AI edge computers, the system achieves processing speeds of 1000 frames per second or more, effectively providing sub-millisecond wavefront sensing capability. The minimal hardware setup, consisting only of a camera and an NVIDI

关键词： Cameras Education and training Monochromatic aberrations Wavefront sensors Wavefronts Phase retrieval Adaptive optics image retrieval Point spread functions Sensors

来源：评论

学校读者我要写书评

暂无评论

COVID-19 and Pneumonia Detection using X-ray image-Based Deep Learning Methods 2

COVID-19 and Pneumonia Detection using X-ray Image-Based Dee...

引用

2nd International conference on Advanced algorithms and Signal image processing, AASIP 2022

作者： Li, Yuxiao McGill University Montreal Canada

ISBN: (纸本)9781510660571

Globally, pneumonia is the leading cause of death for young people and children. An X-ray of the chest is usually used to diagnose pneumonia by a trained specialist. However, the process is tedious and can result in disagreements among radiologists. It is possible to improve diagnostic accuracy through the use of computer-aided diagnostic systems. In this work, the ResNet model was selected to work as the covid-19 and pneumonia detector based on X-ray image. Several experiments are conducted on to achieve an optimal results. © 2022 SPIE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Study on Operational Techniques of Preliminary Refinement of images in Camouflaged Enemy Detection 8th

A Study on Operational Techniques of Preliminary Refinement ...

引用

8th International conference on Information and Communication Technology for Intelligent systems, ICTIS 2024

作者： Suneel, J.S. Dileep, M.R. Department of Master of Computer Applications Visvesvaraya Technological University—Research Centre Nitte Meenakshi Institute of Technology Karnataka Bengaluru India Department of Master of Computer Applications Nitte Meenakshi Institute of Technology Karnataka Bengaluru India

ISBN: (纸本)9789819766833

This study investigates the crucial significance of image processing in the domain of image analysis for the identification and detection of potential threats in advanced defense systems. Real-time images, captured over a wide range of terrains, introduce specific challenges and possibilities for precise target differentiation. The success of subsequent analyses is heavily dependent on the meticulous preprocessing of obtained images, aiming to improve pertinent features and reduce noise interference. It involves a series of operations applied to an image to enhance its quality, correct imperfections, or prepare it for further analysis. Some of the common image preprocessing techniques are Resizing and Rescaling, Normalizing the pixel values, Gray-scale conversion, Cropping, Noise reduction, Contrast enhancement, Edge detection, Thresholding, etc. Also, a wide analysis and survey have been conducted by considering variant parameters that reflect the outcome. By conducting an examination of the literature and carrying out empirical assessments, this study showcases the effectiveness of the proposed preprocessing techniques in enhancing capabilities for detecting adversaries. The outcomes highlight significant enhancements in the precision, robustness, sensitivity, and speed of algorithms designed for enemy detection when employed in conjunction with the specified preprocessing methods. This paper discusses various techniques that influence image analysis and explores the utilization of these techniques across multiple computer vision domains. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： image analysis

来源：评论

学校读者我要写书评

暂无评论

Robust and Faster Zeroth-Order Minimax Optimization: Complexity and Applications 38

Robust and Faster Zeroth-Order Minimax Optimization: Complex...

引用

38th conference on Neural Information processing systems, NeurIPS 2024

作者： An, Weixin Liu, Yuanyuan Shang, Fanhua Liu, Hongying Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Artificial Intelligence Xidian University China College of Intelligence and Computing Tianjin University China Medical School Tianjin University China Peng Cheng Lab Shenzhen China

Many zeroth-order (ZO) optimization algorithms have been developed to solve nonconvex minimax problems in machine learning and computer vision areas. However, existing ZO minimax algorithms have high complexity and rely on some strict restrictive conditions for ZO estimations. To address these issues, we design a new unified ZO gradient descent extragradient ascent (ZO-GDEGA) algorithm, which reduces the overall complexity to O(dϵ-6) to find an ϵ-stationary point of the function ψ for nonconvex-concave (NC-C) problems, where d is the variable dimension. To the best of our knowledge, ZO-GDEGA is the first ZO algorithm with complexity guarantees to solve stochastic NC-C problems. Moreover, ZO-GDEGA requires weaker conditions on the ZO estimations and achieves more robust theoretical results. As a by-product, ZO-GDEGA has advantages on the condition number for the NC-strongly concave case. Experimentally, ZO-GDEGA can generate more effective poisoning attack data with an average accuracy reduction of 5%. The improved AUC performance also verifies the robustness of gradient estimations. © 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

Object Detection in Adverse Weather Conditions using Machine Learning

Object Detection in Adverse Weather Conditions using Machine...

引用

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

作者： Kumar, Manish Yadav, Anup Lal Arora, Abhilaksh Deb, Arnab Chandigarh University Department of Computer Science and Engineering Punjab India

ISBN: (纸本)9798350315455

Object detection in challenging weather conditions is a formidable hurdle in the realm of computer vision. Unfavorable weather circumstances, encompassing rain, snow, fog, and low light conditions, substantially impede the effectiveness of conventional computer vision algorithms. This research paper introduces an innovative approach to image-to-image translation by harnessing the power of CycleGAN, a deep learning architecture renowned for its proficiency in transmuting images from one domain to another. This study is dedicated to tailoring the CycleGAN framework to the specific task of enhancing images captured in adverse weather conditions, such as rain, fog, and snow. The proposed methodology capitalizes on the deployment of two distinctive generators, trained cyclically, for the transformation of images between a source domain (representing adverse weather) and a target domain (signifying clear weather). These generators are bolstered by discriminator networks, enabling adversarial training to enhance the quality of image translation. © 2023 IEEE.

关键词： Adversarial Training Autonomous Driving bdd100k Computer Vision CycleGAN Data Augmentation Dataset Deep Learning Generative Adversarial Networks image Degradation image Enhancement image processing image Quality Improvement image-to-image Translation Neural Networks Synthetic Data Weather Conditions

来源：评论

学校读者我要写书评

暂无评论

A REVIEW OF PHOTOREALISTIC image STYLIZATION TECHNIQUES 5

A REVIEW OF PHOTOREALISTIC IMAGE STYLIZATION TECHNIQUES

引用

5th IEEE International conference on image processing Applications and systems (IPAS)

作者： Qazi, Hassaan A. Univ Waterloo Dept Appl Math Waterloo ON Canada

ISBN: (纸本)9781665462198

Rendering photorealistic images from the image stylization technique is still considered as a challenging task. In this paper, we compare three recent state-of-the-art approaches. All three algorithms are mainly driven by Convolution Neural Network (CNN) technique. A brief discussion of the selected approaches is followed by some comparisons and results. Both Structural Similarity Index (SSIM) and Learned Perceptual image Patch Similarity (LPIPS) metrics are used to generate new findings of the methodologies. Finally, subjective analysis is also presented to gauge the efficacy of the algorithms in discussion.

关键词： image stylization Photorealistic Artistic framework Deep Neural Network Wavelet transform Perceptual similarity metrics

来源：评论

学校读者我要写书评

暂无评论

A Smart Agriculture Friendly Intelligent Flying Robot Design to Identify Plant Leaf Diseases by using Digital image processing with Learning Approach

A Smart Agriculture Friendly Intelligent Flying Robot Design...

引用

2023 International conference on Innovative Computing, Intelligent Communication and Smart Electrical systems, ICSES 2023

作者： Kavitha, M.S. Harikrishnan, R. Shankar, S. Vijay Krishnakumari, S. Sherly, S. Irin R.M.K.Engineering College Department ECE Chennai India S.A. Engineering College Department of ECE Chennai India Sona College of Technology Department of Electrical and Electronics Engineering Salem India Loyola ICAM College of Engineering and Technology Department of ECE Chennai India Panimalar Engineering College Department of Information Technology Chennai India

ISBN: (纸本)9798350319200

Smart agriculture practices have become crucial in meeting the growing global food demand while minimizing resource use. In this context, the development of intelligent systems and automation plays a pivotal role. This paper introduces a novel solution: a smart agriculture-friendly intelligent flying robot equipped with cutting-edge digital image processing techniques and a learning approach to identify plant leaf diseases. The suggested system merges state-of-the-art robotics and aerial technology with advanced machine learning techniques, specifically the VGG-SVM model. The flying robot is equipped with a high-resolution camera to capture images of plant leaves in real-time, and the VGG-SVM model processes these images for disease detection. VGG offers deep feature extraction capabilities, while SVM provides accurate classification, making the model adept at discerning healthy from diseased leaves. Through digital image processing, the robot captures high-resolution images of plant leaves, which are subsequently subjected to advanced machine learning algorithms. These algorithms analyze and classify the images, providing real-time insights into the health of crops. The combination of precision aerial data collection and machine learning ensures early disease detection and targeted intervention, optimizing crop yield, reducing resource consumption, and ultimately contributing to sustainable agriculture. Proposed model excels with the highest accuracy of 0.97, indicating an overall high rate of correct predictions. © 2023 IEEE.

关键词： Deep Learning Drones Plant Leaf Diseases SVM VGG

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence (AI) Assisted Literature Review 3

Artificial Intelligence (AI) Assisted Literature Review

引用

3rd International conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Hilda, Jabanjalin Jeevaa, S.V. Bhadhrinath, U. Solanki, Darshini Sr. School of Computer Science Engineering Vellore Institute of Technology Vellore India Vellore Institue of Tehnology Vellore Vellore India

ISBN: (纸本)9798331527549

This research aims to address the inefficiencies and inaccuracies in traditional literature review methodologies by integrating advanced Artificial Intelligence (AI) technologies, specifically transformer-based models. The study focuses on optimizing PDF-to-text conversion through image and character recognition, thereby minimizing resource wastage and errors associated with manual transcription. Additionally, the research employs advanced Natural Language processing (NLP) techniques to automate the identification of critical phrases such as keywords and organizational entities, significantly reducing manual errors and improving accuracy. The methodology also includes the use of sophisticated summarization algorithms and sentiment analysis, streamlining the process of summarizing extensive literature and identifying study limitations. By leveraging state-of-the-art transformer models and industry-standard libraries, this research introduces a novel, efficient framework for literature analysis. The outcome is a comprehensive, AI-powered toolkit that enhances the speed, accuracy, and precision of literature reviews, ultimately providing researchers with a more reliable and resource-efficient approach to navigating scholarly content. © 2025 IEEE.

关键词： Natural language processing systems

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 << < 40 41 42 43 44 45 46 47 48 49 > >>

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：