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

674 篇 会议
5 篇 期刊文献

馆藏范围

679 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

451 篇 工学
- 322 篇 计算机科学与技术...
- 258 篇 软件工程
- 196 篇 信息与通信工程
- 138 篇 电气工程
- 84 篇 生物工程
- 72 篇 光学工程
- 64 篇 生物医学工程（可授...
- 34 篇 电子科学与技术（可...
- 24 篇 化学工程与技术
- 22 篇 控制科学与工程
- 19 篇 材料科学与工程（可...
- 17 篇 仪器科学与技术
- 13 篇 机械工程
- 12 篇 安全科学与工程
- 9 篇 动力工程及工程热...
- 8 篇 交通运输工程
- 6 篇 网络空间安全
235 篇 理学
- 110 篇 物理学
- 87 篇 生物学
- 85 篇 数学
- 22 篇 化学
- 19 篇 统计学（可授理学、...
- 9 篇 系统科学
104 篇 医学
- 102 篇 临床医学
- 23 篇 基础医学(可授医学...
- 20 篇 药学(可授医学、理...
- 6 篇 公共卫生与预防医...
72 篇 管理学
- 43 篇 图书情报与档案管...
- 31 篇 管理科学与工程(可...
6 篇 法学
6 篇 教育学
- 6 篇 教育学
5 篇 农学
2 篇 军事学

主题

98 篇 signal processin...
58 篇 image segmentati...
58 篇 image processing
54 篇 signal processin...
43 篇 conferences
41 篇 deep learning
38 篇 image enhancemen...
33 篇 image recognitio...
29 篇 feature extracti...
28 篇 training
24 篇 image edge detec...
24 篇 convolution
24 篇 visualization
24 篇 image color anal...
24 篇 image reconstruc...
22 篇 image coding
22 篇 image classifica...
20 篇 neural networks
18 篇 robustness
17 篇 object detection

机构

6 篇 school of inform...
6 篇 college of elect...
5 篇 key laboratory o...
5 篇 university of ch...
5 篇 nanyang technol ...
5 篇 school of mathem...
4 篇 shanghai jiao to...
4 篇 laboratory of be...
4 篇 school of electr...
3 篇 shanghai jiao to...
3 篇 michigan state u...
3 篇 college of mathe...
3 篇 tsinghua shenzhe...
3 篇 shanghai jiao to...
3 篇 national laborat...
2 篇 university of sc...
2 篇 school of comput...
2 篇 school of cyber ...
2 篇 school of mathem...
2 篇 huazhong univers...

作者

6 篇 wang chao
6 篇 yang chuansheng
5 篇 yang yueting
5 篇 wen bihan
5 篇 yang jian
4 篇 jian wang
4 篇 tan anhui
4 篇 anil kumar
4 篇 bo feng
4 篇 chao xu
3 篇 ravishankar saip...
3 篇 zhou jiantao
3 篇 li min
3 篇 zhai guangtao
3 篇 nguyen trong-the
3 篇 feng bo
3 篇 parthasarathy ra...
3 篇 xiaotao huang
3 篇 wang liu
3 篇 fan zhun

语言

679 篇 英文

检索条件"任意字段=2021 International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2021"

共 679 条记录，以下是321-330 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：

Research on wavelet transform technology and image processing performance based on matlab 2

Research on wavelet transform technology and image processin...

引用

2021 2nd international conference on signal processing and Computer Science, SPCS 2021

作者： Xie, Wendi Zhao, Yurong Wang, Yang Communication AnHui XinHua University AnHui HeFei230088 China

This paper first introduces the basic concept, principle and application of wavelet transform. Then, the performance characteristics of Haar wavelet, dbN wavelet and symN wavelet, two different threshold shrinkage algorithms Visushrink and Bayesshrink, and two common threshold functions are described in detail. Finally, Matlab software programming is used to realize the simulation of the original image based on different wavelet bases in the influence of Gaussian noise, Poisson noise and salt and pepper noise, different threshold acquisition algorithm, different threshold function, and compare their peak signal to noise ratio (PSNR) value to complete the image processing performance analysis. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

The influence of different preprocessing on radar signal recognition based on time-frequency analysis and deep learning 3

The influence of different preprocessing on radar signal rec...

引用

3rd international conference on advanced Information Science and System, AISS 2021

作者： Li, Qin Liu, Wei Niu, Chaoyang Wang, Yanyun Gao, Ouyang Bao, Yintu Zou, Weiqi Zhang, Haobo Hu, Qing Lin, Zhikang Pan, Chaofan PLA Strategic Support Force Information Engineering University China

ISBN: (纸本)9781450385862

Aiming at the problem of the lack of rigorous comparative analysis in the preprocessing step in the classification and recognition of radar signals based on time-frequency diagrams and deep learning, this paper analyzes the influence of signal denoising, different time-frequency analysis, and time-frequency graph denoising in preprocessing on the classification and recognition of radar signals through control variables. Lay the foundation for further research on radar signal classification and recognition. © 2021 ACM.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Detecting Fake Faces In Smart Cities Security Surveillance Using image Recognition And Convolutional Neural Networks 1

Detecting Fake Faces In Smart Cities Security Surveillance U...

引用

1st international conference on Technologies for Smart Green Connected Society 2021, ICTSGS 2021

作者： Daya Sagar, K.V. Kamesh, D.B.K. Srinivasa Rao, T. Krishna, Chinta Venkata Murali Department of Electronics and Computer Engineering Koneru Lakshmaiah Education Foundation Vadeswaram Andhra Pradesh Guntur522502 India Dept.of CSE Mallareddy Engineering for Woen Hyderabad India Koneru Lakshmaiah Education Foundation India Department of C.S.E. NRI Institute of Technology India

ISBN: (纸本)9781607685395

Smart cities are planned to have millions of Internet-connected sensors and devices. Sensors can create a huge amount of data in a range of applications. In modern urban environments, quality of life in a Smart City is heavily dependent on the safety of its residents. For a long time, public safety has been a major source of anxiety. For everyone, stopping a breach of private space security has become a priority. Traditional security systems raise an alarm whenever they detect a breach of safety. It is possible to find a breach of an advanced model by using image processing and a deep analysis of convolutional neural networks to classify images. Because of the ability to reduce complicated aspects from photographs using exact algorithms for facial and body detection. The results of specific machine learning, such as deep learning techniques are outstanding. The processing time of the proposed system is reduced, and true rate of face recognition is 72.7% under varying distance from 2m to *** paper aims to show that when used together the security sector, the two can achieve more than might have been previously assumed models. © The Electrochemical Society

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Action Recognition with Domain Invariant Features of Skeleton image 17

Action Recognition with Domain Invariant Features of Skeleto...

引用

17th IEEE international conference on advanced Video and signal Based Surveillance (AVSS)

作者： Chen, Han Jiang, Yifan Ko, Hanseok Korea Univ Sch Elect Engn 145 Anam Ro Seoul South Korea

ISBN: (纸本)9781665433969

Due to the fast processing-speed and robustness it can achieve, skeleton-based action recognition has recently received the attention of the computer vision community. The recent Convolutional Neural Network (CNN)-based methods have shown commendable performance in learning spatio-temporal representations for skeleton sequence, which use skeleton image as input to a CNN. Since the CNN-based methods mainly encoding the temporal and skeleton joints simply as rows and columns, respectively, the latent correlation related to all joints may be lost caused by the 2D convolution. To solve this problem, we propose a novel CNN-based method with adversarial training for action recognition. We introduce a two-level domain adversarial learning to align the features of skeleton images from different view angles or subjects, respectively, thus further improve the generalization. We evaluated our proposed method on NTU RGB+D. It achieves competitive results compared with state-of-the-art methods and 2.4%, 1.9% accuracy gain than the baseline for cross-subject and cross-view.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Non-Local Means Based Multiplicative Denoising Method for image processing 6th

A Non-Local Means Based Multiplicative Denoising Method for ...

引用

6th international conference on Computing, Control, and Industrial Engineering, CCIE 2021

作者： Yu, Bowen Zhou, Yangfan Liu, Xin Wang, Xuguang School of Nano-Tech and Nano-Bionics University of Science and Technology of China 96 Jinzhai Road Anhui Hefei230026 China Chinese Academy of Sciences 398 Ruoshui Road Suzhou Industrial Park Jiangsu Suzhou215123 China Gusu Laboratory of Materials 388 Ruoshui Road Suzhou Industrial Park Jiangsu Suzhou215123 China

ISBN: (纸本)9789811939266

image denoising is one of the most important and critical issues in the field of digital image processing. Its purpose is to keep the edge and detail information as much as possible while removing the noise in the image. Numerous current denoising methods have poor performance when dealing with multiplicative noise, and they usually cannot well preserve the detail and edge information in the image. For this reason, we propose a Non-Local Means (NLM) based multiplicative denoising method. Firstly, the image is logarithmically transformed to convert the noise into multiplicative additive noise that is easier to handle. Secondly, a new square root kernel function is used to replace the original exponential kernel function for Non-Local Means filtering. Finally, the denoised image is obtained through the inverse exponential transformation. By comparing with a variety of classical denoising algorithms, we make the conclusions that the proposed method can not only effectively remove the multiplicative noise, but also better preserve the detail and edge information in the image, which will lay the foundation for more advanced image processing. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Visual Data Compression 21

Deep Learning for Visual Data Compression

引用

29th ACM international conference on Multimedia (MM)

作者： Lu, Guo Yang, Ren Wang, Shenlong Liu, Shan Timofte, Radu Beijing Inst Technol Beijing Peoples R China Swiss Fed Inst Technol Zurich Switzerland UIUC Urbana IL USA Tencent Palo Alto CA USA Univ Wurzburg Wurzburg Germany

ISBN: (纸本)9781450386517

In this paper, we will introduce the recent progress in deep learning based visual data compression, including image compression, video compression and point cloud compression. In the past few years, deep learning techniques have been successfully applied to various computer vision and image processing applications. However, for the data compression task, the traditional approaches (i.e., block based motion estimation and motion compensation, etc.) are still widely employed in the mainstream codecs. Considering the powerful representation capability of neural networks, it is feasible to improve the data compression performance by employing the advanced deep learning technologies. To this end, the deep leaning based compression approaches have recently received increasing attention from both academia and industry in the field of computer vision and signal processing.

关键词： image compression video compression point cloud compression

来源：评论

学校读者我要写书评

暂无评论

An improved measurement pixel selection method of GB-MIMO radar image applied for bridge vibration measurement

An improved measurement pixel selection method of GB-MIMO ra...

引用

IET international Radar conference 2023, IRC 2023

作者： Gao, Jiake Li, Xiaoxiao Zhou, Hanpu Li, Wenyu Deng, Yunkai Tian, Weiming Radar Research Lab School of Information and Electronics Bejing Institute of Technology Bejing China Beijing Building Research Institute Co. Ltd. CSCEC Beijing100076 China Chongqing Innovation Center Beijing Institute of Technology China Advanced Technology Research Institute Beijing Institute of Technology Jinan250300 China

ISBN: (纸本)9781839539954

Ground-based multi-input multi-output (GB-MIMO) radar has significant advantages in bridge structural vibration parameter measurement due to its non-contact, high frame rate, and high-precision measurement characteristics. Due to the complexity of the environment, traditional methods of selecting pixels based on permanent scatterers (PS) cannot accurately obtain bridge structure pixels. This article proposes an improved classification method of the PS deformation curves to accurately select vibration pixels of bridge structures. Firstly, prescreen those PSs with small deformation amplitude as the first category. Secondly, for the screened PSs, the principal component analysis method is used to reduce the data dimension of their deformation curves to reduce the time consumption of clustering. Finally, the K-medoids algorithm is used to classify the screened PSs based on the dimensionality reduction data, and the Davis-Bouldin index is adopted to overcome the problem of local optimization. The experimental results of a large-scale bridge prove that the method proposed in this paper can effectively improve the speed of data processing while ensuring accurate pixel selection of the bridge structure. © The Institution of Engineering & Technology 2023.

关键词： Vibration measurement

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Foot Contact Position on a Smart Fitness Trampoline with a Upward Looking Wide View Imaging System 12

Three-Dimensional Foot Contact Position on a Smart Fitness T...

引用

12th international conference on Ubiquitous and Future Networks (ICUFN)

作者： Park, Sekyung Park, Junkyu Ahn, Jongsik Cho, Boram Lee, Suwoong Kim, Minyoung Korea Inst Ind Technol Adv Mechatron Grp Cheonan South Korea Kyungpook Natl Univ Dept Elect & Elect Engn Daegu South Korea

ISBN: (纸本)9781728164762

This study estimates the position and depth of the user's foot contacts of playing on a trampoline by acquiring the image of the footprint shadow and processing it to enable quantitative analysis of jumping (as a fitness exercise) or to link it to computer games. First, a hardware prototype of a jumping fitness monitoring system is proposed, consisting of a trampoline, an upward-looking wide-angle fish-eye camera module, and a signal processing embedded board. Second, image-based three-dimensional foot contact position estimation (I3D-FCE) algorithms are proposed, comprising the foot contact position estimation algorithm in the transverse plane and the foot contact depth estimation algorithm in the vertical direction. The foot contact positions were estimated using the binary image of the foot shadow obtained by extracting the binary masks of the trampoline and foot. The foot contact depth was estimated using the similarity ratio of the footprint shadow sizes. To verify the usefulness of the proposed system and the accuracy of the proposed contact position estimation algorithms, a series of experiments were conducted using a robotic manipulator. The experimental results show that the X and Y coordinates of the foot contact position and the Z coordinate of the foot contact depth were successfully estimated within an average error of 3.40 (mm), 3.26 (mm), and 4.49 (mm), respectively.

关键词： image processing Embedded board Smart Fitness

来源：评论

学校读者我要写书评

暂无评论

Time-frequency image-based signal recognition by using improved CenterNet 12

Time-frequency image-based signal recognition by using impro...

引用

12th international conference on Information Optics and Photonics (CIOP)

作者： Weng, Junhui Yu, Lei Zhu, Hongna Ye, Jin Cheng, Le Sui, Hao Li, Zhilong Zhang, Jinli Southwest Jiaotong Univ Sch Phys Sci & Technol Chengdu 610031 Peoples R China Natl Key Lab Sci & Technol Blind Signal Proc Chengdu 610031 Peoples R China

ISBN: (数字)9781510649903

ISBN: (纸本)9781510649903;9781510649897

An improved CenterNet is proposed for signal recognition with time-frequency image input. The signal is transformed into time-frequency image by short-time Fourier transform, hence, the signal recognition is transformed into investigating the object detection problem in the field of image detection. Then, the advanced achievements of image detection are adopted to enhance the performance of signal recognition. Here, an improved CenterNet-based object detection network, which demonstrates great advantages in detection speed, is proposed. The results show that the proposed method identifies the signal modulation format with high speed. After training and testing on the self-collected data set with 6 types and 7800 samples, the mean average precision achieves 98.38% and the frame per second reaches 21.4. Compared with the original CenterNet, the detection speed increases more than 4 times while only reducing recognition accuracy by 0.3%, where this algorithm gives a promising way for applications of real-time signal recognition.

关键词： Short-time Fourier transform CenterNet multi-scale pyramid convolution deformable convolution pyramid feature fusion structure

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of image Dehazing using image processing and Deep Learning Techniques 6

A Comparative Analysis of Image Dehazing using Image Process...

引用

6th IEEE international conference on Communication and Electronics Systems, ICCES 2021

作者： Likhitaa, Palagiri Sai Anand, R. Amrita School of Engineering Bengaluru Department of Electrical and Electronics Engineering Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9781665435871

The haziness presence in atmosphere now poses to be a critical issue, especially in terms of visibility and visual quality. The major challenge faced in the present day scenario is to stitch a technique that detects the presence of haziness and to provide an efficient method to remove it as well. This process is known as image dehazing. Although different dehazing algorithms has been introduced, still better performances can be achieved which is addressed in this paper. This challenge is overcome by using a suitable classification algorithm to detect hazy images and then cleaning it to get corresponding clear image. In this method, two goals are presented and executed, Initial one be a comparative analysis between the machine learning and deep learning models is presented for the classification of hazy and clear images and then the hazy images are processed by a robust deep neural network for the removal process. In order to classify, two ML algorithms, namely, SVM and Logistic Regression are used and two CNN standard models Resnet, Vgg are also used and their performances are compared to obtain best classification algorithm for this problem. In classification model, standard CNN models outperforms Machine Learning models by a fair margin by proving to be more accurate. Similarly for dehazing also DCP image processing algorithm is implemented with a proposed CNN de-hazing network and their performances are also compared to prove the efficiency of proposed CNN model. ITS, HSTS, Indoor SOTS Dataset are used as inputs. The performance of CNN network is compared with an image processing technique called Dark Channel Prior (DCP) algorithm. Comparatively the CNN model outperforms the DCP algorithm by attaining higher image quality metrics. To evaluate the image quality, two metrics are compared, they are Structural-similarity-index (SSIM) and peak-signal-to-noise-ratio (PSNR). © 2021 IEEE.

关键词： image quality

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68页 << < 29 30 31 32 33 34 35 36 37 38 > >>

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：