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

12,282 篇 会议
185 篇 期刊文献
157 册 图书

馆藏范围

12,624 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

6,314 篇 工学
- 4,192 篇 计算机科学与技术...
- 2,140 篇 软件工程
- 1,817 篇 电气工程
- 1,256 篇 信息与通信工程
- 809 篇 控制科学与工程
- 631 篇 光学工程
- 451 篇 生物医学工程（可授...
- 432 篇 机械工程
- 432 篇 电子科学与技术（可...
- 391 篇 仪器科学与技术
- 313 篇 生物工程
- 193 篇 测绘科学与技术
- 146 篇 材料科学与工程（可...
- 139 篇 航空宇航科学与技...
- 130 篇 交通运输工程
- 99 篇 安全科学与工程
- 89 篇 网络空间安全
2,970 篇 理学
- 1,941 篇 物理学
- 870 篇 数学
- 355 篇 生物学
- 242 篇 系统科学
- 220 篇 统计学（可授理学、...
- 108 篇 化学
1,337 篇 医学
- 1,179 篇 临床医学
- 189 篇 特种医学
- 155 篇 基础医学(可授医学...
- 98 篇 药学(可授医学、理...
684 篇 管理学
- 417 篇 管理科学与工程(可...
- 289 篇 图书情报与档案管...
- 84 篇 工商管理
56 篇 法学
56 篇 农学
29 篇 教育学
27 篇 文学
25 篇 经济学
17 篇 军事学
16 篇 艺术学
1 篇 哲学

主题

2,580 篇 image processing
1,373 篇 image segmentati...
1,142 篇 signal processin...
601 篇 cameras
590 篇 feature extracti...
583 篇 image edge detec...
516 篇 signal processin...
468 篇 image coding
458 篇 real-time system...
455 篇 image reconstruc...
388 篇 algorithm design...
334 篇 image color anal...
307 篇 pixel
304 篇 deep learning
298 篇 image enhancemen...
298 篇 real time system...
291 篇 object detection
289 篇 computer archite...
283 篇 neural networks
280 篇 hardware

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
11 篇 a. ortega
10 篇 jie yang
10 篇 panetta karen
10 篇 j.m. mendel
10 篇 r. chellappa
9 篇 c.-c.j. kuo
8 篇 frank hannig
8 篇 hannig frank
8 篇 carli m.
7 篇 miller jwv
7 篇 busch christoph
7 篇 semenishchev e.
7 篇 zelensky a.
7 篇 bovik alan c.
7 篇 jerry m. mendel
7 篇 kupriyanov a.v.

语言

12,403 篇 英文
136 篇 其他
74 篇 中文
20 篇 土耳其文
3 篇 葡萄牙文
2 篇 俄文
1 篇 西班牙文
1 篇 法文

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

共 12624 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：

ResNet-50 for Flower image Classification: A Comparative Study of Segmentation and Non-Segmentation Approaches 19

ResNet-50 for Flower Image Classification: A Comparative Stu...

引用

19th International conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Manga, Abdul Rachman Nirmala Azis, Huzain Fattah, Farniwati Salim, Yulita Darwis, Herdianti Departement of Computer Science Universitas Muslim Indonesia Makassar Indonesia

ISBN: (纸本)9798331507817

Flower image classification poses a challenge in digital image processing, requiring effective methods for feature extraction and classification. The aim of this research is to improve the accuracy of flower image classification by employing ResNet-50 for feature extraction, with and without segmentation, and evaluating the effectiveness of various classification algorithms. The dataset consists of images of Calendula and Coreopsis flowers, totaling 2,025 samples. Four segmentation techniques—Canny, Thresholding, Otsu, and Mean Shift—along with a non-segmentation approach are applied. The features extracted using ResNet-50 are classified with Naive Bayes, Support Vector Machine (SVM), Decision Tree, and K-Neighbors Classifier (KNN). Performance evaluation is conducted using accuracy, precision, recall, and F1-score with 5-fold cross-validation. The results show that SVM delivers the best performance in most scenarios. The highest accuracy in segmentation scenarios was achieved with the Mean Shift technique at 0.91, while the non-segmentation approach yielded the highest accuracy of 0.95. The non-segmentation approach proves more effective, indicating segmentation is not always required for high classification accuracy with ResNet-50. This study shows that ResNet-50, especially without segmentation, can significantly improve flower image classification compared to traditional methods, opening opportunities for more efficient systems. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

3rd World conference on Intelligent and 3D Technologies, WCI3DT 2024

3rd World Conference on Intelligent and 3D Technologies, WCI...

引用

3rd World conference on Intelligent and 3D Technologies, WCI3DT 2024

ISBN: (纸本)9789819791279

The proceedings contain 45 papers. The special focus in this conference is on Intelligent and 3D Technologies. The topics include: Multi-scale Point Cloud Shape Completion Network Based on Deep Learning;research on Application and Effect Evaluation of Product Innovation Management Based on Deep Learning;study on Deep Learning-Based Personalised Product Recommendation Model for Autonomous Question-and-Answer Robot;application of image Watermarking Technology Based on Deep Learning in Copyright Protection;research on the Combination of Building Structural Health Monitoring and Deep Learning image processing;electrical Equipment Prediction in a Variable Electromagnetic Field Using Deep Learning;state Monitoring and Fault Prediction of Wind Farm Transmission and Transformation Equipment Based on Deep Learning;application of Deep Learning algorithms in the Innovation Ecosystem of Electric Power;optimization Strategy for Inventory Management Based on Machine Learning;intelligent Design and Evaluation of Aging Adaptable Public Spaces Based on Deep Learning;performance Optimization and Acceleration of Machine Learning algorithms in Task Allocation of Mine Maintenance Robots;Application of Deep Learning to Improve the Performance of Automotive Electronic Control Unit (ECU);deep Learning-Based Scene Classification for Remote Sensing images;Improved Swarm Intelligence Optimization Algorithm Based on SL-Relu Activation Function Improvement Strategy and Its Application in Price Forecasting;Automatic Segmentation of Traumatic Penumbra in Rat Brain Based on Improved UNet++;A Brain Tumor Classification Method Based on ResNeXt-SESA Network;A LSTM Algorithm for Coastal City Cultural Scene Value Sustainable Development Forecast Improvement;pattern Recognition in Archive Analysis Using Data Mining;building Crack Detection Method Based on Convolutional Neural Network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3rd World conference on Intelligent and 3D Technologies, WCI3DT 2024

3rd World Conference on Intelligent and 3D Technologies, WCI...

引用

3rd World conference on Intelligent and 3D Technologies, WCI3DT 2024

ISBN: (纸本)9789819791231

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chaos Theory Based Gravitational Search Algorithm For Medical image Segmentation 27th

Chaos Theory Based Gravitational Search Algorithm For Medica...

引用

27th International conference on Pattern Recognition, ICPR 2024

作者： Rather, Sajad Ahmad Roy, Partha Pratim Das, Sujit Department of Computer Science and Engineering Indian Institute of Technology Roorkee247667 India Department of Computer Science and Engineering National Institute of Technology Telangana506004 India

ISBN: (纸本)9783031781032

Multilevel thresholding plays a crucial role in image processing, with extensive applications in object detection, machine vision, medical imaging, and traffic control systems. It entails the partitioning of an image into distinct regions based on optimal pixel values. However, as the number of threshold levels increases, so does the computational cost for segmentation. To address this challenge, a novel method is proposed namely Chaos theory based Gravitational Search Algorithm (CGSA) for multilevel thresholding. CGSA combines the standard Gravitational Search Algorithm (GSA) for exploration with chaotic maps for exploitation of the complex pixel problem space. In this study, Kapur’s entropy method is utilized to segment sample images into various partitions based on optimal pixel values. The effectiveness of CGSA in real-world scenarios is evaluated using COVID-19 chest CT scan imaging datasets from Kaggle database. The quality, symmetry, and consistency of the segmented output are assessed using metrics like Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and Feature Similarity Index Measure (FSIM). Qualitative analysis includes convergence curves, segmented graphs, colormap images, and box plots. Statistical validation is conducted using the signed Wilcoxon rank sum test. Additionally, a comparison is made between CGSA’s performance and that of eight state-of-the-art heuristic algorithms. The findings demonstrate the superior performance of CGSA, evidenced by its reduced computational time and enhanced image quality metrics values. Specifically, CGSA achieved SSIM of 0.81, FSIM of 0.82, and PSNR of 24.27, surpassing the performance of other competitive algorithms. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Novel Visual Communication Scenario Based on image processing algorithms

A Novel Visual Communication Scenario Based on Image Process...

引用

Machine Learning and Autonomous systems (ICMLAS), International conference on

作者： Jinhua Yang Li Hou Xijing University Shaanxi Xian China

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

In order to comply with the trend of intelligent visual communication, this study proposed an innovative visual communication scenario based on image processing algorithms. The framework aims to optimize traditional key technologies such as the image generation, editing, style transfer and image compression. First, as the foundation of visual communication, this study proposes a generative adversarial network model based on text semantic information for image generation and editing. The model achieves stable image generation and efficient editing from a theoretical level through paired training of text and image pairs. Secondly, for image style transfer, this study designed an improved VGG19 convolutional neural network. At the same time, the adaptive instance normalization technology was combined to optimize the effect of style transfer. Finally, in terms of image compression, the study proposed an improved generative adversarial network (REVISED-GAN) model. This model can dynamically adjust the compression error based on structured information to improve image compression efficiency. Through comparative tests, the proposed image style transfer and image compression algorithms have shown excellent performance in terms of structural similarity, image quality and compression ratio.

关键词： Training Adaptation models image coding Machine learning algorithms Visual communication image synthesis Heuristic algorithms Semantics Generative adversarial networks Neural style transfer

来源：评论

学校读者我要写书评

暂无评论

Medical image Segmentation Techniques: Advances and Challenges

Medical Image Segmentation Techniques: Advances and Challeng...

引用

International image processing, Applications and systems conference (IPAS)

作者： Hela Boulehmi Rania Linda Filali ISET de Bizerte DGET Bizerta Tunisia

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

Medical image segmentation plays a pivotal role in computer-aided diagnosis by facilitating the extraction of essential features necessary for disease detection and treatment strategies. The continuous progress in image processing technologies has led to the development of numerous segmentation methods, encompassing traditional algorithms, machine learning (ML)-driven approaches, and cutting-edge deep learning (DL) techniques. This study undertakes a comparative evaluation of these methods, focusing on their efficiency, accuracy, and suitability across different medical imaging modalities. It also delves into prominent segmentation techniques like thresholding, region-based methods, edge detection, graph cuts, active contour models, and convolutional neural networks (CNNs). Additionally, the paper explores ongoing challenges and prospective advancements aimed at enhancing segmentation efficacy in medical imaging.

关键词： Deep learning image segmentation Thresholding (Imaging) Machine learning algorithms image edge detection Focusing Feature extraction Convolutional neural networks Medical diagnostic imaging Active contours

来源：评论

学校读者我要写书评

暂无评论

Application of Various Novel Computer image processing (CIP) algorithms in Digital Media Art images

Application of Various Novel Computer Image Processing (CIP)...

引用

Multi-Agent systems for Collaborative Intelligence (ICMSCI), International conference on

作者： Xian Du Shanghai Institute of Visual Arts Shanghai China

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

With the continuous development of digital image processing algorithms, its application scenarios have been integrated from the simple research of a single image and a single algorithm to a multi-algorithm fusion analysis paradigm. Therefore, this study proposes a digital media art image analysis framework that combines multiple computer image processing (CIP) algorithms. This breakthrough covers three core architectures: image edge extraction, image style transfer, and image compression. In the image edge extraction module, this study designed an improved edge detection algorithm based on de-noising auto-encoder. This algorithm improves the accuracy of edge detection through multi-directional feature extraction and (I, O)-fuzzy rough set optimization, while maintaining global stability. In the image style transfer module, this study proposed a dual-module network. The network includes a texture translation network and a perceptual loss network, and achieves cross-domain style transfer through a fusion model. At the same time, the algorithm optimizes the perceptual loss function to enhance semantic matching capabilities. In the image compression module, this study uses chaotic systems to construct an optimized measurement matrix. Specifically, through a distributed data parallel training framework, a compression method based on the LPAC gradient sparse algorithm is constructed. By testing the three modules separately, the experimental results confirm the effectiveness of the proposed algorithm.

关键词： Training image coding Art image analysis Translation image edge detection Digital images Semantics Media Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Route Recommendation Algorithm Based on Multi-Dimensional Data Fusion and Analysis of its Social Utility 3

A Route Recommendation Algorithm Based on Multi-Dimensional ...

引用

3rd International conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Dai, Yazhe Li, You College of Electrical and Information Engineering JiLin Agricultural Science and Technology University Jilin China

ISBN: (纸本)9798331508456

The current route recommendation algorithm has problems such as single data. This paper designs a route recommendation algorithm based on multidimensional data fusion, uses convolutional neural network (CNN) to extract the features of user behavior data, geographic location information and environmental factor data, and then uses the attention mechanism to realize the fusion processing of multidimensional data. Based on the fused multidimensional data features, collaborative filtering and content-based recommendation algorithms are used to generate personalized route recommendations in combination with user preferences and real-time traffic conditions. Experiments have shown that the recommendation accuracy of this algorithm can reach up to 100%under controlled test conditions. Compared with the Bellman-Ford algorithm, this algorithm takes an average of 5.46 minutes less time, and the adoption rate of the recommendation results of this algorithm is as high as 99.9%, which proves the effectiveness of the algorithm in the cultural and tourism route recommendation scenario. © 2025 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Vehicle image Anomaly Detection Based on Improved K-Means Algorithm and High-Resolution Camera 2

Vehicle Image Anomaly Detection Based on Improved K-Means Al...

引用

2nd International conference on Machine Learning and Autonomous systems, ICMLAS 2025

作者： Yang, Xiaoqin Alias, Syazwina Wang, Hui FoEBEIT SEGi University Kota Damansara Selangor Malaysia College of Computer and Communication Engineering Nanjing Tech University Pujiang Institute Jiangsu Nanjing210000 China

ISBN: (纸本)9798331505745

This study proposes a vehicle image anomaly detection framework based on improved K-means algorithm and high-resolution camera, which provides a new idea for road safety construction from the image processing level. The main innovation of the study contains 4 aspects: 1. A new vehicle target extraction algorithm based on deep learning is proposed. The algorithm uses the YOLOv5s network structure and combines the SimAM attention mechanism to optimize the model while improving the detection accuracy of vehicle targets. 2. A visual-based traffic flow clustering analysis is performed. This analysis achieved effective clustering of traffic flow through deep HOG feature extraction and parallel K-means clustering algorithm. 3. An optimized license plate detection and recognition algorithm based on YOLOv5 is proposed. The algorithm improves the accuracy of license plate recognition by adding the key point detectors. 4. The traditional K-means algorithm is optimized. The optimization idea is mainly to combine quantum computing and space-time theory. This optimization improves the convergence speed and clustering effect of the algorithm. The results of comparative experiments show that the improved K-means algorithm converges faster in traffic flow clustering analysis, and its license plate recognition accuracy is significantly better than traditional algorithms (such as k-means and FCM). © 2025 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Framework for Skin Cancer Detection using Transfer Learning

A Machine Learning Framework for Skin Cancer Detection using...

引用

International image processing, Applications and systems conference (IPAS)

作者： Mary Linda Panakal Augustine Sotirios Spanogianopoulos Mhd Saeed Sharif Department of Computer Science and Digital Technologies School of Architecture Computing and Engineering University of East London London UK School of Electrical and Mechanical Engineering University of Portsmouth Portsmouth UK

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

This paper uses deep learning algorithms including InceptionV2, InceptionV3, DenseNet, MobileNet, and VGG19 to improve skin cancer detection. This research aims to improve skin cancer diagnosis. This work aims to determine the most effective evolutionary metrics-based technique to recognizing skin cancer, which is comparable to other diseases. Ultimately, our paper aims to create a realistic skin cancer detection system that uses the best deep learning algorithm. This discovery might improve medical diagnostics, leading to earlier diagnosis and improved healthcare outcomes.

关键词： Deep learning Machine learning algorithms image processing Transfer learning Medical diagnosis Reliability Skin cancer image classification

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：