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

4,493 篇 会议
49 篇 期刊文献
18 册 图书
1 篇 学位论文

馆藏范围

4,561 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,605 篇 工学
- 1,695 篇 计算机科学与技术...
- 1,111 篇 信息与通信工程
- 987 篇 软件工程
- 700 篇 电气工程
- 279 篇 光学工程
- 126 篇 电子科学与技术（可...
- 119 篇 生物工程
- 116 篇 控制科学与工程
- 103 篇 仪器科学与技术
- 97 篇 网络空间安全
- 95 篇 生物医学工程（可授...
- 72 篇 机械工程
- 45 篇 化学工程与技术
- 30 篇 动力工程及工程热...
- 30 篇 安全科学与工程
- 26 篇 轻工技术与工程
1,245 篇 医学
- 1,236 篇 临床医学
- 35 篇 基础医学(可授医学...
- 29 篇 药学(可授医学、理...
1,041 篇 理学
- 746 篇 物理学
- 337 篇 数学
- 128 篇 生物学
- 103 篇 统计学（可授理学、...
- 48 篇 系统科学
- 47 篇 化学
188 篇 管理学
- 102 篇 管理科学与工程(可...
- 97 篇 图书情报与档案管...
- 32 篇 工商管理
77 篇 军事学
- 74 篇 军队指挥学
38 篇 法学
- 30 篇 社会学
10 篇 文学
8 篇 经济学
6 篇 农学
5 篇 教育学

主题

552 篇 image coding
468 篇 image processing
353 篇 visual communica...
313 篇 visualization
273 篇 image segmentati...
258 篇 feature extracti...
181 篇 image compressio...
168 篇 video coding
165 篇 image reconstruc...
157 篇 cameras
154 篇 humans
136 篇 image quality
133 篇 image retrieval
125 篇 training
123 篇 image color anal...
121 篇 image edge detec...
115 篇 image enhancemen...
114 篇 signal processin...
114 篇 image analysis
110 篇 motion estimatio...

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
28 篇 school of electr...
24 篇 school of electr...
21 篇 university of sc...
18 篇 shanghai jiao to...
17 篇 shanghai jiao to...
16 篇 tianjin univ sch...
16 篇 beijing universi...
14 篇 institute for in...
11 篇 school of comput...
11 篇 university of el...
11 篇 cas key laborato...
11 篇 tsinghua univ de...
10 篇 univ sci & techn...
10 篇 zhejiang univers...
10 篇 peking univ inst...
10 篇 institute of ima...
9 篇 microsoft resear...
9 篇 tsinghua univ de...

作者

34 篇 zhai guangtao
26 篇 sumei li
25 篇 song li
22 篇 li sumei
21 篇 guangtao zhai
19 篇 li song
18 篇 li li
17 篇 min xiongkuo
16 篇 dong liu
16 篇 wen gao
16 篇 shan liu
15 篇 andré kaup
15 篇 yang xiaokang
14 篇 chen zhibo
13 篇 m. vetterli
13 篇 xie rong
13 篇 xiongkuo min
13 篇 gao wen
11 篇 heming sun
11 篇 zhibo chen

语言

4,494 篇 英文
49 篇 土耳其文
23 篇 中文
10 篇 其他

检索条件"任意字段=Conference on Visual Communications and Image Processing 2003"

共 4561 条记录，以下是4521-4530 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：

A Review on Feature Extraction Techniques in Content Based image Retrieval

A Review on Feature Extraction Techniques in Content Based I...

引用

International conference on Wireless communications, Signal processing and Networking

作者： Jigisha M. Patel Nikunj C. Gamit Department of Computer Engineering C.G.P.I.T Uka Tarsadia University Bardoli India

ISBN: (纸本)9781467393393

The Content Based image retrieval (CBIR) is a very important for retrieving the most visual relevant images from the large image database. The various low level features are extracted based on their visual content which are color, shape, texture etc. The paper gives the overview of color and texture feature extraction techniques like color histogram, color correlogram, color co-occurrence matrix and tamura texture feature, steerable pyramid, wavelet transform, Gabor wavelet transform respectively and also the comparative analysis of this techniques is shown in the paper.

关键词： CBIR Feature extraction Color histogram Color correlogram DCD CCM Tamura feature Wavelet transform GWT

来源：评论

学校读者我要写书评

暂无评论

Machine Vision Aided Adaptive Beamforming Decision for IRS-Assisted Wireless Networks

Machine Vision Aided Adaptive Beamforming Decision for IRS-A...

引用

European conference on Networks and communications (EuCNC)

作者： M. Munawar M. Guenach I. Moerman IMEC Leuven IDLab Ghent University

ISBN: (数字)9798350344998

ISBN: (纸本)9798350345001

This study leverages machine vision to assist communication in wireless networks, with a specific focus on intelligent reflecting surface (IRS)-assisted wireless networks. Instead of depending on traditional schemes such as alternating optimization or semidefinite relaxation to maximize signal strength in an IRS-assisted network, which are computationally expensive and impractical, we use visual data to make low-complexity beamforming decisions for users. Our approach involves employing a ceiling camera with a fish-eye view, covering a wide communication area. The user within the network is initially detected using the YOLOv2 object detection method. Subsequently, we propose closed-form analytical expressions to determine the distances between the access point (AP), user, and IRS. Accounting for the non-uniform nature of the fish-eye image, we introduce a novel method to determine non-uniform pixel weightages using trigonometric techniques. Based on the calculated distances, we make beamforming decisions depending on the user’s proximity to the AP or IRS. The proposed method significantly reduces computational complexity, making it nearly independent of the number of reflecting elements at the IRS. Simulation results indicate that the proposed approach exhibits extremely lower computational costs compared not only to conventional schemes such as alternating optimization and semidefinite relaxation-based convex solvers but also to low-complexity heuristic schemes.

关键词： Degradation visualization Array signal processing Wireless networks Machine vision Simulation Object detection

来源：评论

学校读者我要写书评

暂无评论

An intricate spectrogram processing in speech enhancement using machine learning with cloud computing

An intricate spectrogram processing in speech enhancement us...

引用

International conference on image Information processing

作者： Yenna Geetha Reddy G Mahendran Ameer Al-Khaykan Omar A. Alkawak S. A. Kalaiselvan A. Priya Department of Computer Science and Engineering MAlla Reddy Engineering College for Women (UGC Autonomous)Kompally Secunderabad Telangana India Department of Mechancal Engineering R.M.K Engineering Collegekavaraipettai Chennai Tamil Nadu India Department of Electronic and Communications Engineering University of Kufa Najaf Iraq Department of Air Conditioning and Refrigeration Technical Engineering Al-Mustaqbal University College Hilla Babil Iraq Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Science (SIMATS) Chennai Tamil Nadu India School of Architecture Koneru Lakshmaiah Educational Foundation Guntur Andhra Pradesh India

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

The spectrogram is defined as the visual representation of the signal strength with a particular interval of time regarding frequencies in the appropriate waveform. It is demonstrated using the Fourier transform. It is illustrated in a three-dimensional plot of signal composed with amplitude versus frequency and time. They are classified as long signal sections and short signal sections with filters. It demonstrates the consecutive spectacle of the sound signal at a particular interval of time. The time-frequency representation of audio signals is obtained through spectrograms. This helps in the understanding of the speech data. Machine learning plays an important role in the identification of the relevant features in the spectrogram. The intricate patterns in the time and frequency domains are represented through CNN and RNN. These models are trained and tested through a large dataset which includes both clean and noisy speech samples. This helps to learn complex interrelationships and patterns associated with varied environmental conditions and interference systems. The computational demands of these systems are handled through the cloud computing techniques. They provide a platform for effective solutions for performing real-time interference. These cloud services provide various collaborations to numerous models to achieve desired outcomes. The proposed system provides higher adaptability in varied environmental and noisy profiles. Thus the integration of cloud computing with machine learning provides real-time processing with a natural seamless user experience.

关键词： Cloud computing Time-frequency analysis visualization Computational modeling Machine learning Interference Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Detection Using CNN With Res-LSTMDN

Diabetic Retinopathy Detection Using CNN With Res-LSTMDN

引用

International conference on communications and Signal processing

作者： R. Gayathri S Karthikeyan T KausheekRaj S Keerthana Department of Electronics and Communication Rajalakshmi Engineering College Chennai India

ISBN: (数字)9798350353068

ISBN: (纸本)9798350353075

For diabetic patients, early diagnosis and treatment of diabetic retinopathy (DR) are essential since they can avert irreversible visual loss. The ways we currently find DR aren't very accurate or fast, so we need better ways to do it automatically. CNNs, a type of machine learning algorithm, have been shown to work well for analyzing medical images and could be a good option for detecting DR. Among CNN architectures, ResNet-152 has gained reputation for its depth and effectiveness in image classification tasks. However, to further enhance its performance in DR detection, this study does a modification to the final layer of ResNet-152. Specifically, the final layer is replaced with Long-Short Term Memory (LSTM) and Deep Neural Network (DNN) components, resulting in an ensemble approach termed Res-LSTMDN. This novel architecture aims to improve the hierarchical feature learning of ResNet-152 while integrating the sequential memory capabilities of LSTM and the flexibility of DNN. Res-LSTMDN uses advanced technology to study eye images, specifically those from people with diabetes. By finding unique patterns in these images, this technique aims to improve the accuracy of detecting diabetes-related eye problems. This will allow for early intervention, potentially preventing vision loss. As part of the ongoing efforts to develop advanced computer tools for diabetes diagnosis, Res-LSTMDN has the potential to significantly impact global diabetes management strategies.

关键词： Representation learning Diabetic retinopathy visualization Machine learning algorithms Memory management Signal processing Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classifications of Citrus Fruit Using image processing -GLCM Parameters

Classifications of Citrus Fruit Using Image Processing -GLCM...

引用

International conference on communications and Signal processing

作者： Chandan Kumar Siddharth Chauhan R. Narmadha Alla Harika Mounica Gurram National Institute of Standards and Technology Department of Physics Colorado State University Electrical Engineering Department University of Colorado

ISBN: (纸本)9781479980826

In recent years, automatic visual inspection system has become useful tool in industrial process. The citrus fruit sorting and grading process has now been completely automated with the exception of the final stage of classification concerned with visual inspection. Due to the growing demand of quality citrus fruit, an automated and reliable identification and classification mechanism in order to handle the bulk of data is implemented. Human vision sometimes leads to mismatch between the fruits. Using machine vision system, it will be simple to reduce human effort and achieve a better output. The objective of this project is to assess the fruit by color grading. In this paper we describe an integrated system developed for the sorting on citrus fruit and for the color grading of the defected fruits. The result suggests that the performance is adequate to provide the basis for a viable commercial visual inspection system. The following project aims at implementing such an automated system using image processing with images of citrus fruit as a basis of classification depending on its color. The goal of the inspection is not to give a statistical analysis of the production but to classify every citrus fruit into quality constant batches.

关键词： Quality inspection Machine vision image processing GLCM parameters Citrus fruits Sorting and grading

来源：评论

学校读者我要写书评

暂无评论

Smart Sorting: Enhancing Almond Quality with DenseNet-201-Based image Classification

Smart Sorting: Enhancing Almond Quality with DenseNet-201-Ba...

引用

International conference on Information Science and communications Technologies (ICISCT)

作者： Arpanpreet Kaur Amit Kumar Mishra Bura Vijay Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Computer Science and Engineering Graphic Era Hill University Dehradun Graphic Era Deemed to be University Dehradun Uttarakhand India School of Computer Science and Artificial Intelligence SR University Warangal India

ISBN: (数字)9798331527921

ISBN: (纸本)9798331527938

Considered as two varieties: damaged and undamaged, almonds are a rather consumed agricultural product. Maintaining consumer satisfaction and industry standards depends on good detection of damaged almonds., which could be influenced by mechanical damage., mold, or pests. On the other hand, slow, labor-intensive hand inspection methods prone to mistake demand automated classification systems. This work meets that demand by automating the categorization process using DenseNet-121, a convolutional neural network (CNN), therefore lowering labor expenses and increasing accuracy. Particularly considering the tiny dataset of 1,000 photos split equally between damaged and undamaged almonds, DenseNet-121's architecture-with its dense connections and capacity to reuse features-is well-suited for the almond classification challenge. Pre-trained on imageNet and polished for this particular purpose, the model-trained across 60 epochs using a 32-batch size-achieved an accuracy of 95.27%. Random horizontal flips, resizing., and center cropping among other data augmentation techniques improved the model's generalizing capability. This work demonstrates the model's ability to substitute human methods in actual environments by showing how well it employs little visual information to classify almonds. Automating almond sorting speeds and provides higher consistency in quality control as well as efficiency of sorting. This work opens the road for further research of machine learning techniques in agricultural processing with possible applications in food quality assurance.

关键词： Accuracy Quality assurance Process control Quality control Machine learning Data augmentation Data models Convolutional neural networks Sorting image classification

来源：评论

学校读者我要写书评

暂无评论

A Review towards Enhancing Authentication Scheme Using image Fusion and Multishared Cryptography

A Review towards Enhancing Authentication Scheme Using Image...

引用

International conference on communications and Signal processing

作者： V.B. Gadicha A.S. Alvi Department of Computer Sci. & Engg P.R.Patil College of Engg & Tech Amravati (MH) Department of Computer Sci. & Engg PRMIT&R Badnera Amravati (MH).

ISBN: (纸本)9781479980826

Passwords are used for user authentication, validation, and verification in various software applications (may be Commercial, or Research based). All the existing schemes which are used to generate the password will always provide enough scope for the Intruder (Cracker) to crack or guess the password. All the existing schemes of password generation works on a basic assumption that the resultant password should be easy to remember for a user. This ultimately brings the downfall of the scheme. Therefore, a Password Generator Scheme is proposed here which will restrict the Intruders to crack the password or a scheme should exist which will cause sufficient delay in cracking of a password so that the Generator of the password will change the previous password. Here a strong password generator scheme is proposed by using image Fusion & visual key Cryptography.

关键词： visual Crypto Algorithm image Fusion Two-Share Cryptography

来源：评论

学校读者我要写书评

暂无评论

An Industrial Instrument Panel Identification System Design Based on an Improved YOLOv7 and UAV

An Industrial Instrument Panel Identification System Design ...

引用

International conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Miao Ye Yuejin Huang Qiuxiang Jiang Peng Wen Hongwen Hu Jin Cheng School of Information and Communications Guilin University of Electronic Technology China

Industrial production often requires collecting and reading visual information on instrument panels. Traditional manual inspection and identification methods require considerable work, resulting in inefficient and inaccurate inspections. It is important to design an industrial instrument panel inspection and recognition system that can be applied in real time. In this paper, an industrial instrument panel recognition system is designed by combining an unmanned aerial vehicle (UAV) platform and deep learning techniques. For mobile UAVs, an ultrawideband (UWB) positioning module is used to implement the real-time UAV positioning and its fixed-point cruising function at each instrument panel location point. As the UAV moves around the instrument panel, a modified YOLOv7 model, compressed through a combination of pruning and quantization, is loaded to perform initial detection and recognition of the instrument panel image to ensure real-time transmission of the captured raw image to the ground side. On the ground-side server, the original YOLOv7 model is deployed to perform instrument panel detection on the initially captured images, filter out redundant background information, and then extract the tick marks and pointer information on the instrument panel through the U-Net semantic segmentation model, after which the tick marks and pointer information are processed using traditional image-processing methods. Finally, the instrument panel is identified through the angle method. This method can alleviate the accuracy loss caused by a lightweight model on the mobile side, thus ensuring the quality of accuracy. Finally, a web client is designed using Flask technology to display the uploaded instrument panel images and recognition results via a web terminal. A series of test experiments and their results show that the designed industrial instrument panel detection and recognition system is reliable and efficient in reading industrial instrument panel information in real tim

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low SNR Sonar image Restoration Based on Mixed Probability Statistical Model in Wavelet Domain

Low SNR Sonar Image Restoration Based on Mixed Probability S...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Ping Xia Qiang Ren Dong-xia Shi Bang-jun Lei Yao-bin Zou Guang-zhu Xv Hubei Key Laboratory of Intelligent Vision based Monitoring for Hydroelectric Engineering College of Computer and Information Technology Three Gorges University YiChang China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Since it is difficult to get texture details for sonar image denoising with strong noise and weak feature information. A sonar image enhancement algorithm in wavelet domain based on Gaussian mixture model and Gaussian mixture model is proposed to preserve the weak feature information of the sonar image. Under strong noise interference, the traditional enhancement method has certain difficulties in measuring the similarity of the details of the sonar image. For this reason, wavelet multi-scale analysis is performed on the sonar image to extract the weak feature information of each resolution. Secondly, a directed probability map model between adjacent scales in the wavelet domain is constructed to realize the similar weak feature information association. According to the parent node state probability and the transition probability matrix, the state values of the corresponding child nodes are determined, and the relationship between the state information of parent and child node is constructed. Thirdly, the Gaussian mixture model is used to fit the wavelet coefficient state distribution, and the neighborhood coefficient correlation is used to describe the relationship between the weak feature information in the scale. Finally, the wavelet coefficient estimation of the restored image signal is calculated by the state probability obtained in the expectation maximization (EM) algorithm, and the sonar image is reconstructed. The results of the contrast experiment are verified by visual effects and objective evaluation. The proposed algorithm can preserve the weak edge and contour information while suppressing the noise of the sonar image. It has better peak signal-to-noise ratio, signal-to-noise ratio and Structural similarity.

关键词： Sonar Wavelet coefficients Wavelet domain Hidden Markov models image enhancement Feature extraction Wavelet analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Sensor Fusion SLAM Based on Fast Euclidean Clustering to Filter Dynamic Targets

Multi-Sensor Fusion SLAM Based on Fast Euclidean Clustering ...

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Ming Geng Yongxing Jia Xiaojian Qian Ziang Zhao College of Communications Engineering Army Engineering University of PLA Nanjing China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

R3LIVE is a new multi-sensor fusion SLAM framework, which mainly uses the three sensors of lidar, camera and IMU to realize the effective fusion of heterogeneous data through the error state iterative Kalman filtering method, so as to achieve the function of efficient and accurate simultaneous positioning and mapping. Specifically, this system uses lidar and IMU to construct laser inertial odometer (LIO) to construct the geometry of the external environment, and also it builds a visual inertial odometer (VIO) with a camera and IMU to reconstruct a dense RGB map of the environment. However, in the face of the environment where dynamic objects appear, the positioning accuracy of the system will be affected due to the point cloud of the sensor on the dynamic objects. Moreover, the continuous point cloud of the dynamic objects will cause continuous “ghost” in the dense RGB map constructed. In order to solve the above problems, a fast Euclidean clustering algorithm is proposed to filter out dynamic targets, that is, before the LIO system laser point cloud registration, the input point cloud is initially classified by using a fast Euclidean clustering algorithm, and the original point cloud is divided into ground points, background points and foreground points, among which the ground points and background points are usually considered static points. The foreground points may be either dynamic or static points. Then, the viewpoint visibility method is used for the foreground points to further verify the existence of dynamic points, and the dynamic points in the foreground points are filtered out. Finally, a widely distributed sparse extraction method is designed to solve the problem of excessive extraction of surface features in scenes with rich structure and texture. This enhances the real-time performance and robustness of the system in dynamic scenarios.

关键词： Point cloud compression visualization Accuracy Simultaneous localization and mapping Heuristic algorithms Clustering algorithms Filtering algorithms

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457页 << < 448 449 450 451 452 453 454 455 456 457 > >>

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：