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

12,802 篇 会议
138 篇 期刊文献
133 册 图书

馆藏范围

13,073 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

9,064 篇 工学
- 6,282 篇 计算机科学与技术...
- 3,799 篇 软件工程
- 2,538 篇 信息与通信工程
- 2,441 篇 电气工程
- 1,124 篇 光学工程
- 805 篇 机械工程
- 756 篇 控制科学与工程
- 705 篇 生物医学工程（可授...
- 671 篇 电子科学与技术（可...
- 593 篇 生物工程
- 403 篇 仪器科学与技术
- 371 篇 材料科学与工程（可...
- 254 篇 安全科学与工程
- 246 篇 化学工程与技术
- 160 篇 交通运输工程
- 158 篇 土木工程
- 134 篇 测绘科学与技术
3,601 篇 理学
- 1,929 篇 物理学
- 1,505 篇 数学
- 673 篇 生物学
- 340 篇 统计学（可授理学、...
- 294 篇 化学
- 169 篇 系统科学
1,532 篇 医学
- 1,430 篇 临床医学
- 280 篇 基础医学(可授医学...
- 177 篇 药学(可授医学、理...
- 145 篇 特种医学
1,020 篇 管理学
- 558 篇 管理科学与工程(可...
- 493 篇 图书情报与档案管...
- 138 篇 工商管理
136 篇 农学
114 篇 法学
65 篇 教育学
53 篇 经济学
21 篇 文学
21 篇 军事学
10 篇 艺术学

主题

1,460 篇 image processing
910 篇 image segmentati...
732 篇 image coding
371 篇 cameras
371 篇 feature extracti...
277 篇 deep learning
274 篇 image enhancemen...
270 篇 image reconstruc...
255 篇 video coding
253 篇 motion estimatio...
230 篇 image edge detec...
202 篇 image analysis
195 篇 pixel
177 篇 object detection
148 篇 face recognition
148 篇 data mining
147 篇 signal processin...
141 篇 image compressio...
140 篇 computer vision
134 篇 visualization

机构

20 篇 chitkara univers...
15 篇 signal processin...
14 篇 univ chinese aca...
14 篇 university of ch...
13 篇 shanghai jiao to...
12 篇 microsoft resear...
12 篇 maharishi school...
12 篇 school of commun...
11 篇 xidian universit...
10 篇 university of sc...
10 篇 centre of interd...
10 篇 school of electr...
10 篇 school of inform...
10 篇 sri lanka instit...
9 篇 hewlett packard ...
9 篇 institute of inf...
9 篇 beijing institut...
9 篇 department of au...
9 篇 faculty of infor...
8 篇 tsinghua univers...

作者

14 篇 wang yan
12 篇 yang yang
11 篇 wang jing
11 篇 wang wei
10 篇 ghanbari m
10 篇 liu wei
9 篇 liu ying
9 篇 vikrant bhateja
9 篇 suresh chandra s...
9 篇 mohana
9 篇 li jing
8 篇 li li
8 篇 li min
8 篇 zhang hong
8 篇 chien shao-yi
8 篇 a.k. katsaggelos
7 篇 li jin
7 篇 dan popescu
7 篇 wei li
7 篇 strintzis michae...

语言

12,752 篇 英文
267 篇 其他
68 篇 中文
3 篇 俄文
1 篇 西班牙文
1 篇 土耳其文

检索条件"任意字段=Proceedings of the 3rd International Conference on Video and Image Processing"

共 13073 条记录，以下是71-80 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：

Interactive Segmentation of Art images based on Point Cloud Pre-Training 3

Interactive Segmentation of Art Images based on Point Cloud ...

引用

3rd international conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Tian, Yuan Tao, Yiran Nanhang Jincheng College Jiangsu Province Nanjing City210000 China

ISBN: (纸本)9798350396157

This study presents an innovative interactive segmentation algorithm for fine art images using point cloud pre-Training principles. With increasing demands for precision and variety in image processing, conventional methods are proving inadequate. image segmentation, a central aspect of visual data manipulation, involves dividing an image into distinct regions based on static or dynamic features. This study reviews supervised and unsupervised segmentation strategies, emphasizing the importance of fuzzy clustering algorithms in practical applications. Despite advances in medical image segmentation, challenges remain due to the complex nature of image processing. A universally applicable segmentation method and standardized evaluation criteria are elusive. To address these challenges, the proposed algorithm combines Local Binary Pattern (LBP) feature extraction with a point cloud pre-Training model, utilizing the U-net architecture for accurate segmentation. Experiments conducted on an Ubuntu 14.04 64-bit OS using C++ and Python demonstrate the effectiveness of the algorithm. The visualized results show its potential for practical applications and lay the foundation for future advances in image segmentation. © 2024 IEEE.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Age and Gender Classification Using Convolution Neural Network 3

Age and Gender Classification Using Convolution Neural Netwo...

引用

3rd IEEE Delhi Section Flagship conference, DELCON 2024

作者： Javeriya, Thonduru Anjum Banshal, Sumit Kumar Thangavel, Gnanaprakasam Moni, Raka Alliance University Department of Computer Science and Engineering Bangalore India Daffodil International University Dhaka Bangladesh

ISBN: (纸本)9798331518592

This work aims to improve the accuracy of computer vision and deep learning methods for age and gender prediction in real time from individual photos or video frames. Automated techniques to recognize these characteristics have grown in significance with the emergence of social media platforms. Still, there are issues with the current approaches, especially with regard to extraneous elements that might skew forecasts, such as cosmetics, lighting, and facial expressions. Our work aims to overcome these difficulties by applying advanced algorithms that accurately assess an individual's gender and estimate their age within a given range. The goal of the project is to analyze visual input in real-time for image and video analysis by combining convolutional neural network (CNN) with open Cv. Because the model is taught to recognize and adjust to real-world situations, it is more resilient to change in environmental variables and picture quality. Our investigation shows that while determining an individual's precise age is still challenging, accuracy is much increased when estimating age ranges. Additionally, across a range of circumstances, the model produces accurate gender predictions. These results demonstrate how age and gender estimates may be enhanced by using deep learning and real-time processing techniques. Finally, this work shows that more robust age and gender prediction algorithms may be developed, which can find applications in social media and security, among other domains, by tackling the problems posed by the intrinsic heterogeneity of real-world images. Keywords-Automatic Age and Gender Identification, Real-time processing, Deep Learning, image and video Analysis, Age Range Classification, Facial Feature Extraction. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples 13

What Learned Representations and Influence Functions Can Tel...

引用

13th international Joint conference on Natural Language processing / 3rd conference of the Asia-Pacific-Chapter of the Association-for-Computational-Linguistics (IJCNLP-AACL)

作者： Tonni, Shakila Mahjabin Dras, Mark Macquarie Univ Sch Comp N Ryde NSW Australia

ISBN: (纸本)9798891760189

Adversarial examples, deliberately crafted using small perturbations to fool deep neural networks, were first studied in image processing and more recently in NLP. While approaches to detecting adversarial examples in NLP have largely relied on search over input perturbations, image processing has seen a range of techniques that aim to characterise adversarial subspaces over the learned representations. In this paper, we adapt two such approaches to NLP, one based on nearest neighbors and influence functions and one on Mahalanobis distances. The former in particular produces a state-of-the-art detector when compared against several strong baselines;moreover, the novel use of influence functions provides insight into how the nature of adversarial example subspaces in NLP relate to those in image processing, and also how they differ depending on the kind of NLP task.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Research on Traditional Art image Reconstruction Method Based on Computer Vision Analysis 3

Research on Traditional Art Image Reconstruction Method Base...

引用

3rd international conference on Artificial Intelligence and Autonomous Robot Systems, AIARS 2024

作者： Ruan, Xunmiao Guangdong University of Science &Technology Dongguan Guangdong523083 China

ISBN: (纸本)9798350376173

In the information age, image processing technology has become prevalent across various domains. To enhance image correction, computer vision algorithms can be employed. Traditional methods for structural system identification rely on wired or wireless measurement systems for data gathering, which can be cumbersome and time-consuming due to the need for arranging sensors and data collection equipment. The proposed system involves two primary steps: line drawing extraction and rendering. During the extraction phase, an edge detection technique that integrates low and middle-level visual information is utilized. Based on the results of traditional edge detection, the edges are simplified and connected using computer vision principles. This approach treats image processing as the focal point and aims to establish a scientific model for distorted images. image restoration can be facilitated through sample image filtering and noise reduction techniques. Additionally, this article delves into the principles and associated technologies of computer vision, analyzing patterns of visual interaction. Chinese traditional art imagery, as a cultural medium and symbol, fulfills an artistic communication function while preserving the nation's rich cultural heritage. The image processing techniques grounded in computer vision algorithms offer numerous advantages and superior accuracy. © 2024 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Automatic Generation and Optimization Design of Embroidery Patterns Based on image processing 3

Automatic Generation and Optimization Design of Embroidery P...

引用

3rd international conference on Artificial Intelligence and Autonomous Robot Systems, AIARS 2024

作者： Qiao, Shuang Beijing Institute of Fashion Technology Beijing100105 China

ISBN: (纸本)9798350376173

With the improvement of living environment and the improvement of people's quality of life, embroidery, as a traditional handicraft art, is gradually receiving more attention and love from people. Deep learning (DL) has demonstrated strong capabilities in image generation and processing, particularly in generating visually reasonable and highly detailed images. This provides new opportunities for the automatic generation and optimization design of embroidery patterns. Traditional embroidery pattern generation methods may rely on rules, templates, or manual adjustments, while DL methods can automatically learn complex patterns and structures in images by training large amounts of data, improving the efficiency of embroidery pattern generation and optimization. The DL model can process a large amount of data in a short period of time and automatically generate and optimize patterns. This article designs an automatic generation and optimization algorithm for embroidery patterns based on image processing, using DL technology to learn and generate innovative and artistic embroidery patterns from a large amount of embroidery image data. The experimental results show that the algorithm proposed in this paper can achieve automatic generation and optimization of embroidery patterns, meeting the needs of users for unique and beautiful embroidery patterns. © 2024 IEEE.

关键词： Automatic generation and optimization Embroidered patterns image processing

来源：评论

学校读者我要写书评

暂无评论

Sign Language Translation Using image processing to Audio Conversion 3

Sign Language Translation Using Image Processing to Audio Co...

引用

3rd IEEE international conference on Intelligent Techniques in Control, Optimization and Signal processing, INCOS 2024

作者： Subashini, V. Someshwaran, B. Sowmya, S. Kumar, S Ashwin Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798350361186

Sign language has long been a fundamental mode of communication for deaf and mute individuals, serving as a crucial tool for inclusivity and interaction. Nonetheless, communication barriers persist as many individuals outside of these communities struggle to comprehend and utilize sign language effectively. A ground-breaking system known as hand gesture recognition using image processing to audio conversion has emerged to address this issue. This innovative system aims to develop an application capable of translating sign language and hand gestures into text and audio, thereby facilitating communication between deaf and mute individuals and the wider society. This system enables the detection and classification of hand gestures by employing computer vision techniques, such as CNN algorithms for image processing and the MediaPipe framework for hand gesture identification in real-time video streams. Subsequently, the system utilizes audio signals to provide immediate feedback by converting the detected gestures into corresponding sounds. The feature extraction CNN algorithm is implemented in Python, while the execution takes place on a Raspberry Pi connected to an external camera utilizing OpenCV libraries. Through this comprehensive approach, the system endeavours to bridge the communication gap and enhance the inclusion of deaf and mute individuals in various social settings. © 2024 IEEE.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Research on image Art Creation System of Integrated 3D Computer image Vision Digital Media 3

Research on Image Art Creation System of Integrated 3D Compu...

引用

3rd IEEE international conference on Electrical Engineering, Big Data and Algorithms, EEBDA 2024

作者： Liu, Yang Guo, Dongqi Institute of Arts and Media Guangzhou Vocational University of Science and Technology Guangzhou China Jeonbuk National University Department of Industrial Design Jeonju Korea Republic of

ISBN: (纸本)9798350380989

The accuracy and real-time performance of existing image labeling algorithms are not high. This project intends to study the video sequence feature labeling algorithm for digital multimedia images. A digital multimedia image segmentation method based on wavelet transform is proposed. Then the system adopts the color video segmentation method based on edge detection. Based on visual salience features, the model combines color features and gradient features to describe local image quality. The method fuses the brightness channels of the reference image and the corresponding distorted image, and calculates the similarity between the gradient map of the channel and the gradient map of the reference/distorted image. Target detection is realized by matching the target image with the gray information. Then the color feature and gradient feature are combined organically by means of the mean offset weight method, and a better image quality evaluation effect is obtained. The performance of many evaluation algorithms and has some advantages compared with the existing evaluation methods. © 2024 IEEE.

关键词： 3D image recognition media image digital processing visual feature

来源：评论

学校读者我要写书评

暂无评论

image processing based Real-Time Online Attendance Monitoring System using Facial Recognition 3

Image Processing based Real-Time Online Attendance Monitorin...

引用

3rd international conference on image processing and Robotics, ICIPRoB 2024

作者： Fernando, Ravishka Athauda, Hashini Cinec Campus Department of Electrical and Electronics Engineering Malabe Sri Lanka

ISBN: (纸本)9798350374766

With the advancement of technology and due to the recent pandemic situation, the education sector has turned to the online teaching method. But the main problem here is the inconvenience and irregularities in the student's attendance. To ensure traditional attendance and reduce time wastage, this research aims to explore and implement an automated attendance marking system using facial recognition technology. This will enable students to be marked present or absent in real-time and will also help teachers to identify students who are present or absent for the online session. As a novelty of this research gives a more efficient and accurate method for attendance marking and eliminating manual and false attendance marking in online sessions. The proposed system employs the latest advancements in image processing and machine learning techniques such as the Haar Cascade feature and LBPH algorithm to accurately detect and recognize the face of a student. The performance of the system is evaluated on its own dataset which was the images of students captured through a video stream from a web camera and the results demonstrate through a confusion matrix its effectiveness in accurately recognizing faces and marking attendance in real-time. The results showed that the attendance system achieved 99.22% accuracy and can accurately mark the attendance of students in an Excel sheet. This real-time GUI-based system is unique in that it revolutionizes the traditional attendance marking process by automating it and providing real-time attendance data. © 2024 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

video extensometry measurement method for materials with large deformations 3

Video extensometry measurement method for materials with lar...

引用

3rd international conference on Machine Vision, Automatic Identification, and Detection, MVAID 2024

作者： Shi, Haoran Zhang, Zhijia Yang, Minmin Shenyang University of Technology School of artificial Intelligence China

ISBN: (纸本)9781510681880

This paper addresses the issue of segmentation errors in video extensometer caused by deformation, dispersion, and cracks in markers during the stretching process. A method combining frame-to-frame matching with deep learning is proposed to address the high robustness segmentation problem of black and white markers on materials undergoing large strains. The selection of template position during image matching and the update of the template throughout the stretching process are discussed. Experiments and analysis were conducted on various types of rubber and plastic specimens that exhibit significant strain and irregular deformation. The results demonstrate that this method can be applied to line marker-type video extensometers, enhancing the overall robustness of the measurement algorithm. © 2024 SPIE.

关键词： image matching

来源：评论

学校读者我要写书评

暂无评论

Methodology for the Implementation of Slurm-based HPC Services 3

Methodology for the Implementation of Slurm-based HPC Servic...

引用

3rd international conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Curia-Alcantara, Neil Erick Inga-Coveñas, Camilo Auccahuasi, Wilver Universidad Cientifica del Sur Lima Peru

ISBN: (纸本)9798331532420

Nowadays, with the growth of the increasing demand for computational capabilities, it is necessary to have workstations with extreme computational capacity, for which we find in the market many solutions, depending on the needs and funding, in most cases commercial solutions, have high costs. As an alternative we present a methodology for the implementation of HPC services, using the SLURM tool, which provides mechanisms to perform HPC processes at low cost, with the resources that are available, we present the requirements and procedures for the configuration of these solutions, as well as the demonstration of operation, finally we indicate as conclusions, the mechanisms for the application and implementation of the methodology in different cases, where it is required to perform high performance processes based on HPC solutions. © 2024 IEEE.

关键词： video signal processing

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 << < 4 5 6 7 8 9 10 11 12 13 > >>

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：