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

13,207 篇 会议
218 篇 期刊文献
176 册 图书
3 篇 学位论文
1 篇 资讯

馆藏范围

13,605 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

7,036 篇 工学
- 4,656 篇 计算机科学与技术...
- 2,295 篇 软件工程
- 2,121 篇 电气工程
- 1,339 篇 信息与通信工程
- 872 篇 控制科学与工程
- 686 篇 光学工程
- 503 篇 生物医学工程（可授...
- 472 篇 机械工程
- 471 篇 电子科学与技术（可...
- 461 篇 仪器科学与技术
- 336 篇 生物工程
- 241 篇 测绘科学与技术
- 169 篇 材料科学与工程（可...
- 160 篇 航空宇航科学与技...
- 145 篇 交通运输工程
- 107 篇 安全科学与工程
- 93 篇 化学工程与技术
- 91 篇 网络空间安全
3,498 篇 理学
- 2,405 篇 物理学
- 936 篇 数学
- 394 篇 生物学
- 249 篇 系统科学
- 241 篇 统计学（可授理学、...
- 122 篇 化学
1,509 篇 医学
- 1,336 篇 临床医学
- 210 篇 特种医学
- 171 篇 基础医学(可授医学...
- 111 篇 药学(可授医学、理...
725 篇 管理学
- 438 篇 管理科学与工程(可...
- 311 篇 图书情报与档案管...
62 篇 法学
61 篇 农学
30 篇 教育学
29 篇 经济学
29 篇 文学
20 篇 军事学
18 篇 艺术学
1 篇 哲学

主题

2,762 篇 image processing
1,431 篇 image segmentati...
1,168 篇 signal processin...
616 篇 feature extracti...
615 篇 cameras
584 篇 image edge detec...
567 篇 signal processin...
489 篇 image coding
489 篇 image reconstruc...
466 篇 real-time system...
399 篇 algorithm design...
352 篇 image color anal...
312 篇 image enhancemen...
311 篇 pixel
309 篇 deep learning
307 篇 real time system...
302 篇 image analysis
301 篇 computer archite...
297 篇 hardware
296 篇 object detection

机构

22 篇 signal and image...
20 篇 samara national ...
14 篇 school of electr...
11 篇 samara national ...
11 篇 purdue univ sch ...
11 篇 univ texas san a...
11 篇 department of el...
11 篇 school of electr...
10 篇 samara national ...
10 篇 center for signa...
9 篇 information syst...
9 篇 institute of ima...
9 篇 university of to...
9 篇 tongji universit...
8 篇 university of ch...
8 篇 electrical compu...
8 篇 image processing...
8 篇 information syst...
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
9 篇 c.-c.j. kuo
8 篇 frank hannig
8 篇 hannig frank
8 篇 carli m.
8 篇 a. ortega
8 篇 egiazarian karen
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

语言

13,369 篇 英文
145 篇 其他
79 篇 中文
20 篇 土耳其文
3 篇 西班牙文
3 篇 葡萄牙文
2 篇 俄文
1 篇 法文

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

共 13605 条记录，以下是141-150 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：

Identification of Human image Mapped with Clothing for Dress Selection

Identification of Human Image Mapped with Clothing for Dress...

引用

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

作者： D Prem Raja Kailasam Selvaraj A. Baranidharan Rajkumar Pandiarajan V. Sivakumar V.Baby Shalini Department of Information Technology Kalasalingam Academy of Research and Education Krishnankoil India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

With a significant increase in the fashion market, consumers can shop from the comfort of own home through e-shopping. However, one of the prominent disadvantages is lack of ability to try a garment before buying through Internet; customers may feel unsure about size and yet look. The selection of dress from the proposed system is made realistic and accurate by implementing image processing, machine learning, and AR. The first step to the process is to isolate the human figure from the input image by using feature extraction such as background subtraction, edge-detection and of body part. Once the human figure is isolated, the system is then in a position to place chosen gargets on the corresponding identified points on the human figure. This mapping process encompasses the placement of clothing item's outline and fabric feel on the figure and gender of the user.

关键词： Industries Scalability image edge detection Clothing Machine learning Prediction algorithms Feature extraction User experience Fabrics Internet

来源：评论

学校读者我要写书评

暂无评论

Learning systems in Forgery image Detection 1st

Learning Systems in Forgery Image Detection

引用

1st International conference on Intelligent systems in Computing and Communications, ISCComm 2023

作者： Shetty, Sudheer Ganesh, Devadiga Likhit kumar Poojary, Rahul R. Raviraj Tejas, R. Hegde, Nagaratna P. Vikkurty, Sireesha Department of ISE Sahyadri College of Engineering & Management Mangaluru Affiliated to Visvesvaraya Technological University Karnataka Belagavi India Department of ISE Alvas Institute of Engineering and Technology Moodbidri Affiliated to Visvesvaraya Technological University Karnataka Belagavi India Department of CSE Vasavi College of Engineering Telangana Hyderabad India

ISBN: (纸本)9783031756078

In an era dominated by the ubiquitous sharing of visual content on social media, the proliferation of fake photographs and digital fakes has emerged as a critical issue. This paper explores how fake images are detected with fusion of by various techniques of image processing, CNN, and machine learning, presenting an innovative approach to address the intricate challenge of identifying manipulated images. This paper gives insight on various approaches of image processing techniques and state-of-the-art machine learning algorithms used in a robust forgery image detection system. A comprehensive framework is proposed on various image forensic methods, ensuring the precise detection of fake images across diverse contexts. The paper also emphasizes the impact of countering the dissemination of fake photographs to preserve the credibility of digital media. This combination of image processing, CNN and machine learning propels the ongoing quest to uncover the truth behind the surge of digital fakes in today's digital landscape. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of interactive image measurement software based on Tkinter and PIL library 25

Design and implementation of interactive image measurement s...

引用

Proceedings of the 4th International conference on Computer, Artificial Intelligence and Control Engineering

作者： Xiao He Zhulin Wang Shaozheng Zhan National Key Laboratory of Strength and Structural Integrity Xi' an Shaanxi China Aircraft Strength Research Institute of China Xi' an Shaanxi China

ISBN: (纸本)9798400712647

In this paper, we design and implement a high-precision image processing and measurement software based on Python. The software utilizes the Tkinter and PIL libraries to build a graphical user interface and integrates a variety of commonly used image processing algorithms, including grayscale conversion, edge extraction, Gaussian blur, image sharpening, binarization, and median filtering, enabling effective image enhancement and segmentation. In addition, the software provides interactive measurement functionality, allowing users to draw rectangular regions on the image using the mouse and automatically calculate the dimensions of these rectangles. Measurement results can be stored, displayed, and managed, facilitating users in analyzing and processing the data. To evaluate the performance and reliability of the software, we conducted experiments on multiple datasets. The experimental results demonstrate that the software can accurately process images of different types and qualities and provide stable and reliable measurement results. Compared with the existing C-scan measurement software of current equipment, the software developed in this study has certain advantages in terms of functional integration, interactivity, and measurement accuracy. The design and implementation of this software can meet the need to replace the existing C-scan system software, while also providing valuable references and insights for the further development of intelligent and automated image analysis systems.

关键词： PIL

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Pre-processing Technique For Eye image Segmentation

An Enhanced Pre-Processing Technique For Eye Image Segmentat...

引用

Advances in Computer Science, Electrical, Electronics, and Communication Technologies (CE2CT), International conference on

作者： Satrughan Kumar Arun Kumar Deepti Sahu Computer Science and Engineering Sharda University Greater Noida U.P India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

Early diagnosis is essential to controlling glaucoma, a progressive disorder that results in irreversible vision loss. Retinal fundus imaging has emerged as a crucial diagnostic technique for retinal disorders, such as glaucoma, in recent times. But because of the intricate vascular patterns and intricate architecture of the retina, it can be difficult to analyze these images appropriately. Areas of interest in fundus pictures are frequently found using image segmentation algorithms; however, this can be challenging. This study examines a variety of segmentation techniques, emphasizing both conventional and cutting-edge ways for splitting retinal fundus pictures. It also covers assessment metrics that are used to evaluate how well segmentation algorithms perform in identifying minute structural alterations associated with glaucoma. The study also looks at how deep learning algorithms can be implemented to separate optic disc and cup. Deep learning models typically perform worse with larger datasets, even though they have demonstrated good accuracy with smaller datasets. The investigation underscores the need for more sophisticated deep learning methodologies and efficient segmentation techniques, as it shows that effectively segmenting the optic disc (OD) and cup (OC) remains a considerable challenge, particularly for large and complex datasets.

关键词： Deep learning Glaucoma Measurement Learning systems image segmentation Accuracy Refining Lighting Retina Optical imaging

来源：评论

学校读者我要写书评

暂无评论

Construction Waste image Classification Algorithm Based on Fusion of Multiple Features

Construction Waste Image Classification Algorithm Based on F...

引用

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

作者： Yi You Boon Cheong Chew Institute of Technology Management and Entrepreneurship Universiti Teknikal Malaysia Melaka Malacca Malaysia Construction College Taizhou Vocational & Technical College Taizhou China Faculty of Technology Management and Technopreneurship Universiti Teknikal Malaysia Melaka Malacca Malaysia

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

The rapid development of global urbanization has triggered the rapid expansion of the construction industry. The consequent construction waste problem has caused serious pollution to the environment and occupied a large amount of valuable land resources. In this context, effective classification and treatment of construction waste has become particularly urgent, which can help reduce environmental burdens and promote sustainable economic development. This study proposes a fine-grained construction waste classification algorithm based on image processing technology. The algorithm achieves automatic classification through a multi-feature fusion model and can accurately distinguish five major types of construction waste, including concrete, bricks, metal, wood, and plastic. This study further explores the impact of spatial positional relationships, semantic correlation, and internal structure analysis on improving classification accuracy. These research results not only provide technical support for the effective processing of construction waste, but also provide new methods and perspectives for other fine-grained image classification tasks. Experimental results prove that the algorithm proposed in this study significantly improves the classification accuracy. Specifically, the algorithm achieved high accuracy of 98.97%, 98.69%, 98.70%, 98.72% and 98.68% respectively in the classification tasks of concrete, bricks, metal, wood and plastic, which is significantly better than those based on CNN and enhanced FCM. Although these models are close to the performance of the algorithm in this study in some cases, the overall accuracy is lower.

关键词： Accuracy Urban areas Semantics Metals Stability analysis Real-time systems Classification algorithms Plastics Reliability image classification

来源：评论

学校读者我要写书评

暂无评论

GPU-Accelerated Feature Extraction for Real-Time Vision AI and LLM systems Efficiency: Autonomous image Segmentation, Unsupervised Clustering, and Smart Pattern Recognition for Scalable AI processing with 6.6× Faster Performance, 2.5× Higher Accuracy, and UX-Centric UI Boosting Human-in-the-Loop Productivity

GPU-Accelerated Feature Extraction for Real-Time Vision AI a...

引用

IEEE/SEMI conference and Workshop on Advanced Semiconductor Manufacturing

作者： Kiarash Ahi Stewart Wu Satya Sriram Germain Fenger Siemens EDA USA Siemens EDA Belgium Siemens EDA India

ISBN: (数字)9798331531850

ISBN: (纸本)9798331531867

The high computational cost of digital image processing, requiring high-performance hardware and extensive resources, severely limits real-time applications. While advancements in algorithm design and GPU acceleration have significantly improved efficiency, modern AI-driven applications such as large language models (LLMs), Generative AI (GenAI), medical imaging, autonomous vehicle perception, photography, advanced nano-scale semiconductor metrology, satellite image analysis, high-precision manufacturing, robotics, and real-time anomaly detection, still demand further optimization to reduce computational overhead and improve *** this paper, we introduce GPU-Accelerated Feature Extraction to enhance runtime and efficiency in edge-based simulations. Our approach leverages AI-driven clustering, grouping images with similar visual and pattern characteristics to enable adaptive tuning on a small subset before generalizing across the full dataset. This method achieves a 3.78× reduction in ***, rather than processing an entire image, we recognize and extract a single representative pattern or region of interest (ROI) per image, removing redundant data and background noise. This refinement results in an additional 1.74× runtime improvement, culminating in an overall 6.6× speed boost, enhancing Scalable Real-Time AI processing. We also demonstrated that with a similar runtime, the accuracy achieved is 2.5× *** solution, integrated into Calibre SEMSuite™, supports multicloud and real-time deployment for enhanced scalability, usability, and performance, providing users with a powerful tool for fully automated, AI-driven image classification, making high-throughput image review feasible even at the scale required for cutting-edge *** performance gains, this approach introduces autonomous data cleaning, anomaly detection and defect identification mechanism, allowing failed patterns and defective images to be identified without h

关键词： Accuracy Runtime image edge detection Clustering algorithms Feature extraction Real-time systems Computational efficiency Artificial intelligence Anomaly detection Tuning

来源：评论

学校读者我要写书评

暂无评论

Detection Algorithm for High Impedance Faults on Electrical Edge Device

Detection Algorithm for High Impedance Faults on Electrical ...

引用

Grid Edge Technologies conference & Exposition (Grid Edge), IEEE PES

作者： Xiangying Meng Souvik Chandra Dmitry Ishchenko Michael Nowak Soumyabrata Talukder Eaton Corporation USA

ISBN: (数字)9798350352528

ISBN: (纸本)9798350352535

In recent years, there has been a growing interest in using machine learning algorithms for solving challenging power systems protection problems. One such difficult problem, High impedance (HiZ) faults are characterized by low fault currents and erratic harmonic behavior which are not detected traditional overcurrent protection. These faults when not immediately cleared pose public safety hazard and potential to start a wildfire. This paper presents advanced signal processing techniques that quantify harmonic energy and randomness in current signature, enabling timely identification and clearance of HiZ faults. The detection method includes an anomaly event monitoring algorithm which identifies time points with sustained changes in harmonic features, distinguishing abnormal events from normal operation. Once an anomaly event is detected, features associated with HiZ faults are extracted and applied to identify faults. This approach uses features which are trained using a machine learning algorithm but still can be implemented in regular edge devices like relays, recloser controls etc. with significantly reduced computational burden. The method shows promising detection time and accuracy for lab emulated actual high impedance faults.

关键词： Fault diagnosis Machine learning algorithms Wildfires image edge detection Signal processing algorithms Power system harmonics Signal processing Harmonic analysis Feature extraction Impedance

来源：评论

学校读者我要写书评

暂无评论

Underwater image Enhancement Using Gaussian Smoothing and Edge Detection

Underwater Image Enhancement Using Gaussian Smoothing and Ed...

引用

International conference on Inventive Computation Technologies (ICICT)

作者： V. Lambodara Aravind C. Bagyalakshmi Department of Computer Applications Hindustan Institute of Technology and Science

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Underwater acoustic communication is used for oceanographic data collection, environmental monitoring, disaster alarm systems, and navy applications. Underwater has its peculiarities such strong signal attenuation and limited bandwidths, multipath nature of signals, and ambient noises. All these characteristics bring a great deal of interference probably in transmission with certainty and effectiveness. This work propounded an optimized hybrid model that works concurrently with advanced signal processing and noise-reducing techniques for communication enhancement. The purpose of the proposed model is to develop high signal-to-noise ratio (SNR) received signals with lesser transmission error using time-frequency domain analysis and filtering techniques, which are specifically designed for underwater applications. Thus, the main aim of this work, in fact, is towards the development of a robust underwater communication platform, which ensures a very reliable transfer of data under conditions of excessive noise even in the rapidly changing aquatic environments. Comparison of the proposed model with traditional techniques shows that this model stands much higher than the earlier techniques regarding transmission accuracy, noise resilience, and overall efficiency, thus extending the development of more reliable underwater communication systems toward future marine and defense applications.

关键词： Adaptation models Underwater communication Smoothing methods image edge detection Computational modeling Signal processing algorithms Reliability Underwater acoustics image enhancement Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Architectural Decoration image Recognition and Classification based on Convolutional Neural Network

Architectural Decoration Image Recognition and Classificatio...

引用

Intelligent systems and Computational Networks (ICISCN), International conference on

作者： Wenhao Zhang Jianyang Yang Mingjie Yang Weifang Engineering Vocational College Weifang China

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Architectural decoration images are of various types and complex features. Therefore, fast and accurate recognition and classification of architectural decoration images has become a key challenge to improve design efficiency and project management level. This paper proposes an innovative solution - a CNN-based architectural decoration image recognition and classification method. The paper first collects and annotates various types of architectural decoration images to construct a dataset containing multiple architectural decoration styles and preprocesses these images. In the construction of CNN model, a deep network structure integrating convolutional layer, pooling layer, fully connected layer, etc. is designed. The CNN model is trained using the preprocessed architectural decoration image dataset, and the model parameters are adjusted through the back propagation algorithm to minimize the classification error. The results show that the average recognition accuracy of CNN in architectural decoration image recognition reaches 97.61%, which is significantly higher than the 91.35% of DeepLabv3+, and the processing speed is also faster. This paper provides a new technical means for the field of architectural decoration, which helps to promote technological progress and innovation in this field.

关键词： Backpropagation Training Technological innovation image recognition Accuracy Computational modeling Data models Classification algorithms Convolutional neural networks Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

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

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

引用

International conference on Ubiquitous Information Management and Communication (IMCOM)

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

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

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.

关键词： Support vector machines Performance evaluation image segmentation Accuracy Thresholding (Imaging) Flowering plants Streaming media Feature extraction Classification algorithms 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 << < 11 12 13 14 15 16 17 18 19 20 > >>

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：