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

1,670 篇 会议
12 册 图书
6 篇 期刊文献

馆藏范围

1,688 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,197 篇 工学
- 926 篇 计算机科学与技术...
- 751 篇 软件工程
- 398 篇 光学工程
- 380 篇 信息与通信工程
- 247 篇 生物工程
- 214 篇 控制科学与工程
- 184 篇 电气工程
- 140 篇 生物医学工程（可授...
- 139 篇 机械工程
- 130 篇 电子科学与技术（可...
- 99 篇 化学工程与技术
- 91 篇 材料科学与工程（可...
- 86 篇 仪器科学与技术
- 75 篇 网络空间安全
- 59 篇 安全科学与工程
- 51 篇 交通运输工程
- 36 篇 动力工程及工程热...
- 34 篇 土木工程
770 篇 理学
- 416 篇 物理学
- 275 篇 数学
- 255 篇 生物学
- 119 篇 化学
- 85 篇 统计学（可授理学、...
269 篇 管理学
- 152 篇 管理科学与工程(可...
- 116 篇 图书情报与档案管...
- 58 篇 工商管理
114 篇 医学
- 94 篇 临床医学
- 68 篇 基础医学(可授医学...
- 60 篇 药学(可授医学、理...
32 篇 农学
- 32 篇 作物学
27 篇 法学
21 篇 经济学
10 篇 教育学
5 篇 军事学
2 篇 文学

主题

194 篇 computer vision
143 篇 image processing
102 篇 image segmentati...
71 篇 image enhancemen...
71 篇 deep learning
60 篇 feature extracti...
55 篇 image recognitio...
48 篇 convolutional ne...
41 篇 object detection
35 篇 image classifica...
34 篇 cameras
34 篇 machine vision
30 篇 visualization
29 篇 image reconstruc...
25 篇 real-time system...
25 篇 accuracy
24 篇 image edge detec...
21 篇 machine learning
20 篇 training
18 篇 neural networks

机构

12 篇 chitkara univers...
12 篇 maharishi school...
10 篇 centre of interd...
8 篇 university of ch...
6 篇 national univers...
6 篇 the islamic univ...
6 篇 graphic era hill...
5 篇 school of comput...
4 篇 university of sc...
4 篇 guangdong key la...
4 篇 school of inform...
4 篇 shenyang institu...
4 篇 image processing...
4 篇 college of elect...
4 篇 tianjin universi...
4 篇 saveetha school ...
3 篇 college of compu...
3 篇 school of comput...
3 篇 chitkara univers...
3 篇 graphic era deem...

作者

8 篇 li li
6 篇 mohana
6 篇 anand vatsala
5 篇 chauhan rahul
4 篇 gill kanwarparta...
4 篇 luo haibo
4 篇 wang chao
4 篇 pei jihong
4 篇 zhao yang
4 篇 hassan ghassemia...
4 篇 e.j. delp
4 篇 yan bin
4 篇 zhang wei
3 篇 li yang
3 篇 shilaskar swati
3 篇 li min
3 篇 yang yang
3 篇 zhang bo
3 篇 kukreja vinay
3 篇 zhang yan

语言

1,638 篇 英文
46 篇 其他
9 篇 中文
1 篇 德文
1 篇 土耳其文

检索条件"任意字段=3rd International Conference on Image Processing and Vision Engineering, IMPROVE 2023"

共 1688 条记录，以下是31-40 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：

Intrinsic image Decomposition: Challenges and New Perspectives

Intrinsic Image Decomposition: Challenges and New Perspectiv...

引用

3rd international conference on image processing and vision engineering, improve 2023

作者： Ulucan, Diclehan Ulucan, Oguzhan Ebner, Marc Institut für Mathematik und Informatik Universität Greifswald Walther-Rathenau-Straße 47 Greifswald17489 Germany

ISBN: (纸本)9789897586422

In the field of intrinsic image decomposition, alongside developing a robust algorithm for the ill-posed problem, it is also required to benchmark the method on a comprehensive dataset by using a suitable evaluation metric. However, there are certain limitations in existing evaluation metrics. In this study, two new evaluation strategies are proposed to analyze intrinsics according to their characteristics. The ensemble of metrics combines different perceptual quality metrics in scale-space, while the imperceptible ΔE score is the modified version of the classical ΔE metric. Intrinsic image decomposition studies that extract the reflectance and shading images are benchmarked on two datasets. Furthermore, an overview of the field of intrinsic image decomposition is provided and the challenges that have to be overcome are pointed out. © 2023 by SCITEPRESS – Science and Technology Publications, Lda.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ConvNext: A Contemporary Architecture for Convolutional Neural Networks for image Classification 3

ConvNext: A Contemporary Architecture for Convolutional Neur...

引用

3rd international conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Todi, Agastya Narula, Navya Sharma, Moolch Gupta, Umesh Computer Science Engineering Maharaja Agrasen Institute of Technology New Delhi India Electronics and Communication Engineering Maharaja Agrasen Institute of Technology New Delhi India Computer Science Engineering Bennett University Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350303360

Convolutional neural networks (CNNs) have established themselves as the industry standard for image classification jobs. Convolutional neural network architectures have been created and enhanced recently to improve accuracy and decrease computational complexity. Convolutional Neural Networks' effectiveness declined as transformers became more widely used in computer vision. The transformers, such as vision transformers, outperformed the antecedent CNNs in image classification tasks requiring computer vision. However, in 2022, Facebook researchers created a collection of convolutional neural networks that performed better than vision transformers in the image Classification experiment. A ResNet was used to build this network, subsequently 'modernized' to make it more resemble a vision Transformer. Following this, the curated model was trained and evaluated on the imageNet1k and imageNet22k datasets for image Classification, yielding several novel results. ConvNext was the name of this network, and it has many variations. On the CIFAR-10 dataset, we assess the effectiveness of the ConvNext models in this work. We demonstrate the advantage of the ConvNext model in terms of accuracy by comparing the results with those from other cutting-edge models. © 2023 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Vegetable image recognition algorithm based on Swin Transformer 3

Vegetable image recognition algorithm based on Swin Transfor...

引用

3rd international conference on Signal image processing and Communication, ICSIPC 2023

作者： Guo, Song Zhang, Qingyao School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510670945

Target detection techniques based on computer vision can be used for vegetable recognition and classification, which can effectively avoid the time-consuming and labor-intensive problems faced by manual operations at the large supermarket checkout lanes and produce market. In order to accurately recognize vegetable image, an improved Faster R-CNN recognition technique based on the Swin Transformer is proposed in this paper. The backbone network is replaced by the Swin Transformer to improve the accuracy and efficiency of feature extraction. The ROI Align is employed to protect the integrity of image data. Furthermore, the more effective GIoU loss function is used to simplify the training process in order to reduce the computational resources and time consuming during training. Finally, the experimental results show that the proposed algorithm has an accuracy improvement of 6.1% compared with the previous methods. © 2023 SPIE.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

An experimental teaching platform for machine vision-based real-time detection taking quality inspection of paper cups as instance 3

An experimental teaching platform for machine vision-based r...

引用

3rd international conference on Educational Technology, ICET 2023

作者： Huang, Yanzhe Luo, Yabo Zhou, Xiangyu Wuhan University of Technology School of Mechanical and Electronic Engineering Wuhan China

ISBN: (纸本)9798350302332

In order to improve the quality of students' practical training, a real-time detection system experimental platform based on machine vision has been designed. The system has functions of real-time sampling, detection, defective product removal, result display and data storage, and its structure covers three parts: hardware platform, detection algorithm, and software function implementation. The hardware platform includes image acquisition module, material transportation module and defective product removal module, and the control circuit is based on the development of Arduino and STM32. The detection algorithm is developed based on OPENCV, and it is designed to detect three types of defects: cup rim concavity, cracking, and out-of-roundness. The software system is jointly developed using Visual Studio 2019 and Qt Creator 4.9.1, and it has good interactivity. With this experimental platform, teaching work such as image acquisition system construction, dynamic sampling problem analysis, image detection algorithm development, and interactive interface implementation can be carried out, so as to improve students' engineering design ability in many aspects. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Animal Species image Classification 3

Animal Species Image Classification

引用

3rd international conference on Artificial Intelligence and Signal processing, AISP 2023

作者： Prudhivi, Likhith Narayana, M. Subrahmanyam, Ch Gopi Krishna, M. Chavan, Salim Infosys Ltd Hyderabad India Anurag University Electronics & Communication Engineering Hyderabad India Vignan Institute of Technology and Science. Electronics & Communication Engineering Telangana India Vardhaman College of Engineering Electronics & Communication Engineering Shamshabad India Govindrai Wanjari College of Engineering and Technology Nagpur India

ISBN: (纸本)9798350320749

In forests, in order to protect wild animals, real-time animal species identification is done via picture recognition. Many computer vision approaches were first presented in the past, however they couldn't meet the demands since accuracy decreased as technology evolved. Nonetheless, accuracy in the categorization, identification, and segmentation of pictures was significantly improved as a consequence of the inclusion of multiple approaches. In order to achieve a high degree of accuracy, this study intends to provide an effective approach for animal species picture categorization. Convolutional neural networks have been developed specifically for the categorization of images. To achieve high accuracy, final layer features are learned and synchronised to the pre-trained model. With the dataset, a variety of architectures for deep learning are evaluated. © 2023 IEEE.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Research on Information processing System Under Computer Artificial Intelligence Big Data Technology 3

Research on Information Processing System Under Computer Art...

引用

3rd international Signal processing, Communications and engineering Management conference, ISPCEM 2023

作者： Peng, Lei Fu, Qiang Li, Zhi Lin, Musong Qian, Yihua Electric Power Research Institute of Guangdong Power Grid Co. Ltd. Guangdong Key Laboratory of Electric Power Equipment Reliability Guangzhou China

ISBN: (纸本)9798350307023

In this paper, a virtual view image post-processing method using background information is proposed. Firstly, a depth-based method is used to deal with overlapping between two images. Secondly, the artifacts of the left and right virtual view are located by the motion direction of the observation point, and the artifacts are eliminated by the background pixels in the supplementary view Angle. Then the background image is filled with holes and combined with the foreground image to form a virtual perspective image. The experimental results show that the peak signal noise of this method is 0.6357 dB better than that of the traditional method. Experiments show that the method proposed in this paper can improve the rendering effect significantly. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

TR-Former: Token Based Residual Transformer for Single image Denoising 3

TR-Former: Token Based Residual Transformer for Single Image...

引用

3rd international conference on Consumer Electronics and Computer engineering, ICCECE 2023

作者： Li, Yihan School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350331578

In recent years, people's demand for photography has been increasing with the development of smartphones and cameras. In order to get higher-quality photos, more and more people pay attention to the field of image restoration, especially the image denoising task. The recently proposed vision transformer model, accompanied by the breakthrough of deep learning, has also been successfully applied to image restoration problems. In this paper, we first design the TokenWin Transformer Block with a local branch and a global branch to capture both the local and global features of an image. In order to improve the denoising performance of the network, we then add a Gate-Residual structure on the existing basis to obtain richer features of samples. This scheme selects more effective features of denoising to feed forward, which strengthens the network's information capture capability. Finally, the effectiveness of this method is verified by our experimental tests. © 2023 IEEE.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

Improving CNN Model for Residential Building image Classification: Enhancing Parameter Estimation Accuracy Through Transfer Learning and Reducing Model Complexity with MobileNet 3

Improving CNN Model for Residential Building Image Classific...

引用

3rd international Signal processing, Communications and engineering Management conference, ISPCEM 2023

作者： Pengyu, Li Zhenkun, Zhou Haiyan, Li Yajing, Zhu Guangxi Eco- Engineering Vocational and Technical College Liuzhou Guangxi545000 China Guangxi Technician College of Machinery and Electricity Liuzhou Guangxi545000 China

ISBN: (纸本)9798350307023

With the widespread application of deep learning and Convolutional Neural Networks (CNN) in image classification, how to effectively improve model performance and reduce its complexity has become a significant research direction. This study presents an improved CNN model for residential building image classification, which incorporates transfer learning and the MobileNet architecture. Through transfer learning, we effectively enhance parameter estimation accuracy, and by adopting the MobileNet architecture, we reduce the computational complexity and size of the model. Experimental results demonstrate that this approach achieves superior performance on the Cultural Heritage Apps dataset, verifying its efficacy in residential building image classification. © 2023 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Staged Progressive Single image Generative Adversarial Network 3

Staged Progressive Single Image Generative Adversarial Netwo...

引用

3rd international conference on Electronic Information engineering and Computer Communication, EIECC 2023

作者： Cai, Qiang Xiong, Shaohua Wang, Chen Li, Ziyao School of Computer and Artificial Intelligence Beijing Technology and Business University Beijing China

ISBN: (纸本)9798350359961

This paper focuses on exploring unconditional generative model training methods for single image learning and proposes a new staged progressive single image generative adversarial network (SPSI-GAN). By conducting staged multiscale training on a single image, we gradually learn the feature block information of different areas within the image and pay more systematic attention to the overall structure of the image, the basic outline of the scene, and the details of the content. Experiments verified the application effect of this method in multiple image tasks and compared it with other mainstream methods. This method shows excellence in generated image quality and feature distribution and could improve training efficiency and performance metrics while maintaining high quality generated images. © 2023 IEEE.

关键词： Generative Adversarial Network image processing Single-image learning

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network-Based Method for Real- Time Eye State Identification in Driver Drowsiness Detection 3

A Convolutional Neural Network-Based Method for Real- Time E...

引用

3rd international conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Gill, Kanwarpartap Singh Anand, Vatsala Chauhan, Rahul Thapliyal, Siddhant Gupta, Rupesh Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350319125

The use of Convolutional Neural Networks (CNNs) for drowsiness detection is an AI-based method for detecting and warning of human drowsiness or weariness. Deep learning models like convolutional neural networks (CNNs) learn by analysing images or videos, often focusing on human faces or eyes. Drowsiness cues may be recognised by these models, including drooping eyelids, yawning, and altered facial expressions. CNN-based sleepiness detection may be used to generate alarms or cautions using economic resources in real-time applications, such as driver monitoring systems, to help avoid accidents and improve safety. Artificial intelligence and computer vision access are at the heart of this technology, which aims to alleviate major safety risks associated with sleepiness and exhaustion. In this research, drowsiness detection and classification are accomplished with the help of a Sequential Convolutional Neural Network (CNN) model. The graphics processing unit (GPU) is used for producing preliminary data processing. The Deep Learning model is then shown graphically by analysing the Loss and Accuracy curves. With a predicted accuracy of 96%, the suggested model would pave the way for more research into sleepiness detection and categorization. © 2023 IEEE.

关键词： Artificial Intelligence Classification CNN Computer vision Deep Learning Deep Learning Drowsiness Detection image processing Model Training Remote Sensing Sequential Model

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169页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：