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111-120 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：

Underwater image color correction and adaptive contrast algorithm improvement based on fusion algorithm 3

Underwater image color correction and adaptive contrast algo...

引用

3rd international conference on image processing and Intelligent Control, IPIC 2023

作者： Zhu, Hengjun Wang, Tianluo Ma, Lihao School of Communication and Electronic Engineering Qiqihar University Qiqihar China

ISBN: (纸本)9781510668140

Due to the characteristics of water and the particles in water, the underwater images will have problems of color deviation, low contrast and uneven brightness. Therefore, a statistical approach based on variance is proposed in this paper to correct color-biased images and then equalize the image brightness using the Gamma algorithm. Secondly, a local adaptive contrast enhancement algorithm improved by contrast code images and a restricted contrast adaptive histogram equalization algorithm are used to improve the contrast of underwater images. Finally, two different contrast-enhanced images after color correction are fused by a multi-scale fusion algorithm to obtain high-quality underwater images. The results of the comparison experiments with some existing underwater image enhancement algorithms show that our algorithm can effectively improve the quality of underwater images. © 2023 SPIE.

关键词： Luminance

来源：评论

学校读者我要写书评

暂无评论

3D Feature Extraction Network Based on Self-supervision for Micro-expression Spotting 3

3D Feature Extraction Network Based on Self-supervision for ...

引用

3rd international conference on image processing and Media Computing (ICIPMC)

作者： Wang, Yuhan Guo, Xupeng Xia, Zhaoqiang Northwestern Polytech Univ Sch Elect & Informat Xian Peoples R China

ISBN: (纸本)9798350386660;9798350386677

Micro-expression is an important tool to analyze real human emotions. As the upstream task of micro-expression analysis, video spotting needs to obtain accurate video frame position. At present, it mainly relies on manual calibration by experts, which is not suitable for processing massive videos in real scenes. Due to the short duration and weak intensity of micro-expression, traditional manual feature extraction methods are difficult to capture the weak change of micro-expression, while deep learning based methods are not robust enough. Therefore, this paper proposes a self-supervised facial feature extraction network to constructs a more robust facial feature extractor through self-supervised methods to capture the weak change in micro-expression. Concretely,we split raw long video into clips for model training and introduce a pixel-level-based mask operation to improve the effect of the model reconstruction. Then we reconstruct the optical flow sequence and original face sequence through two 3D feature extraction networks with identical structure and different parameters, and optimize the parameters by self-supervision. The results show that the proposed model captures robust subtle facial change features and improves the accuracy of micro-expression spotting on two datasets CAS(ME)(2) and SAMM-LV.

关键词： Micro-expression spotting Feature extraction network Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Distance image piecewise adaptive weighted fusion algorithm based on TOF and binocular vision 3

Distance image piecewise adaptive weighted fusion algorithm ...

引用

3rd international Computing Imaging conference, CITA 2023

作者： Yong, Zhang Jinmeng, Zhang Manguo, Liu Wei, Yuan Zhen, Yang Dan, Jiao Jianlong, Zhang National Key Laboratory of Science and Technology on Tunable Laser Harbin Institute of Technology Harbin China Xi'an Modern Control Technology Research Institute Xi'an China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (纸本)9781510671409

3D imaging technology has wide applications in fields such as autonomous driving and engineering surveying. Among them, TOF (Time of Flight) 3D and binocular vision 3D imaging technology are the two most commonly used methods. This study investigated the influence of distance and light intensity on the ranging accuracy of TOF and binocular vision imaging methods theoretically and experimentally. An adaptive weighting-based high-precision range image generation method for the entire range was proposed. The basic idea was to assign different weights to the TOF range image and binocular vision range image at different distance intervals and use the prior weight fitting results at different light intensities and distances to guide the weighted processing of each point of the range image. And then high-precision range imaging results with higher ranging accuracy than the original TOF image and binocular vision imaging were obtained. The PSNR value increased by an average of 7.15% compared to binocular vision and increased 1.17% compared to TOF. Distance error MSE value decreased by an average of 34.76% compared to binocular vision and decreased 7.87% compared to TOF. Experimental results demonstrated the effectiveness of the proposed method, which provided a useful idea and means for further improving the ranging accuracy of existing range imaging methods. © 2023 SPIE.

关键词： Binocular vision

来源：评论

学校读者我要写书评

暂无评论

Enhancing Facial Emotion Recognition through Deep Learning and image Pre-processing 3

Enhancing Facial Emotion Recognition through Deep Learning a...

引用

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

作者： Singh, Ekta Nand, Parma Sharda University Department of Computer Science & Engineering Greater Noida India

ISBN: (纸本)9798350303360

Humans frequently communicate effectively using their faces in addition to their words. The use of computer vision techniques to categorize face emotion has been extensively studied. Given the difficulties and restrictions of databases, such as the use of static data or facial capture in artificial contexts, these have had different degrees of success. As a result, we think that novel preprocessing methods are necessary to increase the precision of facial expression detection models. In this study, we suggest a novel, yet straightforward, approach to improving the precision of face emotion identification. Our research was done using the FER2013 dataset, which includes static facial photos of 7 basic emotions. Resizing and Normalization image preprocessing techniques were applied on the dataset prior to the splitting into train and test sets. The training images were split into train and test sets in the ratios of 75% and 25% respectively. The facial expressions in the photos were classified using Convolution Neural Networks [CNNs], with an accuracy of 76.75% on the test set. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Effects of image Augmentation Techniques for Rice Leaf Disease Detection 3

Effects of Image Augmentation Techniques for Rice Leaf Disea...

引用

3rd IEEE international conference on Intelligent Technologies, CONIT 2023

作者： Talati, Trusha Bhat, Akshat Kalbande, Dhananjay Sardar Patel Institute of Technology Department of Computer Engineering University of Mumbai India Sardar Patel Institute of Technology Department of Computer Science and Engineering University of Mumbai India

ISBN: (纸本)9798350338607

Rice leaf diseases substantially reduce crop yield, resulting in food shortages and financial losses. Early identification and control of these diseases can be aided and enhanced by automated computer vision-based detection systems. However, existing techniques suffer from low accuracy and inconsistency due to several issues. To improve model resilience against corrupted inputs and adversarial cases, this study examines the effects of image augmentation techniques on three transfer learning models for diagnosing rice leaf diseases. A consolidated dataset, which includes rice leaf images of five different classes, was used to train these models. The VGG-16 model trained on images augmented using the Random Flip technique achieves a maximum accuracy of 99.47%. However, we present the lightweight EfficientNet-B0 model, trained on MixUp augmented images, with an accuracy of 98.01%, as an alternative model that is more robust and suitable for deployment in mobile/web applications. Our results demonstrate that image augmentation techniques can enhance the model's robustness against synthetically altered images without affecting its ability to detect and predict rice leaf diseases. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

An Elevator Forbidden Target Discovery Method Based on Computer vision 3

An Elevator Forbidden Target Discovery Method Based on Compu...

引用

3rd IEEE international conference on Computer Systems, ICCS 2023

作者： Xia, Zhihao Soochow University School of Mechanical and Electrical Engineering Suzhou China

ISBN: (纸本)9798350313666

Intelligent monitoring has been widely used in the field of object detection and pedestrian detection. At the same time, its application in elevator monitoring is gradually increasing. One such application is the discovery of forbidden targets. There are challenges to this task: 1) Lack of datasets;2) The image size that can be handled is small;3) Uncertain angle and spatial position of the object;4) The object has partial occlusion. To improve the prediction effect of the model on such images, this paper proposes a new vision transformer model. The standard vision transformer often uses class tokens or patch tokens to design classification heads. We believe that both tokens contain unique and valuable information. Therefore, in this paper, we propose a convolution-based classification head with dual inputs. Our classification head uses both class token and patch tokens to focus on more features for effectively handle the occlusion. We introduce convolution into transformer to enhance the perception of 2D spatial locations. We made a new dataset to train our model. The results show that our model achieves 97.78% accuracy on the dataset, which is 1.51% better than the standard vision transformer. © 2023 IEEE.

关键词： Elevators

来源：评论

学校读者我要写书评

暂无评论

A Pharmacology Toolkit for Animal Pose Estimation, Tracking and Analysis 3

A Pharmacology Toolkit for Animal Pose Estimation, Tracking ...

引用

3rd international Mobile, Intelligent, and Ubiquitous Computing conference, MIUCC 2023

作者： Saleh, Dema Ahmed, Moemen Zaafan, Mai Farouk, Yasmine Atia, Ayman Giza Egypt HCI-LAB Faculty of Computers and Artificial Intelligence Helwan University Egypt

ISBN: (纸本)9798350306231

Pose estimations have increased dramatically in the realm of computer vision since the introduction of sensor camera technology and the development of deep networks. Since predicting animal poses is a critical first step in understanding animal behaviour, animal position studies are included in the research on pose estimations. Two different studies were used to identify the crossing, rearing and grooming behaviours in an open field experiment. The first concentrated on crossing while the second concentrated on grooming and rearing. After employing various picture processing techniques, both trials were able to count the behaviours. Through the use of computer vision, deep learning networks, euclidean distance matching algorithms, and image processing, The desired output of classifying and tracking several mouse behaviours like crossing and rearing in an open-field experiment are achieved. The rearing experiment resulted in an accuracy of 97% across all mice. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Impact of image Restoration on Digital image processing Using compression Technique 3

Evaluating the Impact of Image Restoration on Digital Image ...

引用

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

作者： Sohal, Jagmeet Sahoo, Girija Shankar Hr, Manjunatha Jain, Sandeep Kumar Kalpana, B. Wawage, Pawan S. Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Basic Science Faculty of Engineering and Technology Karnataka Bangalore India Vivekananda Global University Department of Electrical Engineering Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai127 India Vishwakarma Institute of Information Technology Department of Information Technology Pune India

ISBN: (纸本)9798350319125

This technical summary gives a scientific technique to evaluate the effect of photograph healing on virtual image processing with the usage of a compression technique. First, a contrast among specific strategies of compression is carried out. It includes an analysis of Lossy and Lossless compression tactics for various photo report codecs, which include JPEG, PNG, GIF, and TIFF. This paper aims to evaluate the impact of image restoration on digital image processing by applying a compression technique. The study proposes a novel method that combines image compression and restoration processes to enhance image quality while reducing storage requirements. Various measures, including peak signal-to-noise ratio, structural similarity index, and compression ratio, are used to evaluate the effectiveness of the proposed method. The experimental results show that the joint approach of compression and restoration not only improves the image quality but also significantly reduces the file size. This indicates the potential of using image restoration as a preprocessing step in digital image processing to improve the overall performance of image compression algorithms. Additionally, the study discusses the computational efficiency of the proposed method and provides insights for further improvements. The results obtained offer a perception of the general impact of photo restoration on virtual photo processing, which might be beneficial for exceptional aspects, inclusive of excellent management, analysis, and recordspushed evaluation. © 2023 IEEE.

关键词： Collectively Compression Performance Recuperation Sequence

来源：评论

学校读者我要写书评

暂无评论

A Shuffling Building Block and Augmentation Parameter Tuning Techniques to Handle Small Medical Dataset 3

A Shuffling Building Block and Augmentation Parameter Tuning...

引用

3rd international conference on Electrical, Computer and Communication engineering, ECCE 2023

作者： Nehal, Tasnemul Hasan Khan, Ahmad Ali Shifa, Shifat Ara Saiyara, Lamia Hossain, Udoy Islam, A.K.M Ehtesanul Ahsanullah University of Science & Tech Bangladesh

ISBN: (纸本)9798350345360

The recent COVID-19 outbreak showed us the importance of faster disease diagnosis using medical image processing as it is considered the most reliable and accurate diagnostic tool. In a CNN architecture, performance improves with the increasing number of trainable parameters at the cost of processing time. We have proposed an innovative approach of combining efficient novel architectures like Inception, ResNet, and ResNet-Xt and created a new CNN architecture that benefits Extreme Cardinal dimensions. We have also created four variations of the same base architecture by varying the position of each building block and used X-Ray, Microscopic, MRI, and pathMNIST datasets to train our architecture. For learning curve optimization, we have applied learning rate changing techniques, tuned image augmentation parameters, and chose the best random states value. For a specific dataset, we reduced the validation loss from 0.22 to 0.18 by interchanging the architecture's building block position. Our results indicate that image augmentation parameters can help to decrease the validation loss. We have also shown rearrangement of the building blocks reduces the number of parameters, in our case, from 5,689,008 to 3,876,528. © 2023 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Description Model of Dunhuang Murals Based on Multi-Scale and Multi-Level Aggregation 3

A Description Model of Dunhuang Murals Based on Multi-Scale ...

引用

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

作者： Zhang, Tian'ai Keystone Academy Beijing China

ISBN: (纸本)9798350307023

The study and preservation of Dunhuang murals is a major archaeological endeavor. With advances in computer technology and artificial intelligence, the use of deep learning techniques to further understand the context of Dunhuang murals and automatically generate descriptions with historical archaeological and cultural significance can help aid in the study of historical documents, inscriptions on Dunhuang murals, and the broader historical context to understand the significance of the murals, as well as the cultural and religious practices of the time. In addition, this work can assist in interpreting archaeological data, summarizing findings, and developing hypotheses about the creation and cultural significance of Dunhuang murals. This paper proposes an image description generation method that combines multi-scale and multi-level aggregation. AC-PPM-ResNet is adopted as the encoder to improve the utilization of image spatial information through AC block module, and the PPM module is used to obtain the multi-scale contextual information of the image, which provides the decoder with a feature representation of rich semantic information in generating the text description. In the decoding stage, the Transformer decoder embedded with LSTM as an aggregator is designed to fully utilize the multi-scale semantic spatial information obtained in the encoding stage, so that the model can fully take into account the information at different levels of the sentence, improve the accuracy of the description generation, and effectively solve the problems of insufficient performance of the text generation model and the loss of information. The experimental results on Dunhuang mural dataset show that the model proposed in this paper has better image description ability and certain generalization ability, the evaluation metrics outperform the other models. © 2023 IEEE.

关键词： image enhancement

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 << < 8 9 10 11 12 13 14 15 16 17 > >>

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：