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

15,153 篇 会议
233 篇 期刊文献
229 册 图书
3 篇 学位论文

馆藏范围

15,618 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

8,092 篇 工学
- 5,417 篇 计算机科学与技术...
- 2,792 篇 软件工程
- 2,445 篇 电气工程
- 1,573 篇 信息与通信工程
- 1,006 篇 控制科学与工程
- 833 篇 光学工程
- 572 篇 电子科学与技术（可...
- 552 篇 生物医学工程（可授...
- 549 篇 机械工程
- 507 篇 仪器科学与技术
- 414 篇 生物工程
- 285 篇 测绘科学与技术
- 204 篇 航空宇航科学与技...
- 189 篇 交通运输工程
- 180 篇 材料科学与工程（可...
- 145 篇 安全科学与工程
- 119 篇 化学工程与技术
4,111 篇 理学
- 2,774 篇 物理学
- 1,130 篇 数学
- 467 篇 生物学
- 325 篇 系统科学
- 271 篇 统计学（可授理学、...
- 146 篇 化学
1,618 篇 医学
- 1,440 篇 临床医学
- 215 篇 特种医学
- 201 篇 基础医学(可授医学...
- 134 篇 药学(可授医学、理...
858 篇 管理学
- 515 篇 管理科学与工程(可...
- 378 篇 图书情报与档案管...
- 130 篇 工商管理
77 篇 法学
68 篇 农学
42 篇 经济学
40 篇 教育学
27 篇 文学
25 篇 军事学
20 篇 艺术学
1 篇 哲学

主题

2,703 篇 image processing
1,407 篇 image segmentati...
1,150 篇 signal processin...
805 篇 real-time system...
750 篇 feature extracti...
748 篇 cameras
552 篇 image edge detec...
540 篇 signal processin...
478 篇 image reconstruc...
470 篇 image coding
447 篇 algorithm design...
377 篇 deep learning
370 篇 object detection
345 篇 hardware
344 篇 computer vision
339 篇 accuracy
337 篇 image color anal...
335 篇 real time system...
333 篇 clustering algor...
317 篇 computer archite...

机构

22 篇 signal and image...
19 篇 samara national ...
17 篇 school of electr...
12 篇 information syst...
11 篇 samara national ...
11 篇 univ texas san a...
11 篇 department of el...
11 篇 school of electr...
10 篇 department of el...
10 篇 electrical compu...
9 篇 school of electr...
9 篇 institute of ima...
9 篇 tongji universit...
9 篇 purdue univ sch ...
9 篇 university of ch...
9 篇 center for signa...
8 篇 shanghai jiao to...
8 篇 information syst...
8 篇 university of to...
8 篇 image processing...

作者

22 篇 anon
13 篇 de-shuang huang
12 篇 jagdish chand ba...
11 篇 jie yang
11 篇 p. pirsch
10 篇 hannig frank
10 篇 panetta karen
10 篇 c.-c.j. kuo
10 篇 j.m. mendel
10 篇 plaza antonio
10 篇 r. chellappa
9 篇 semenishchev e.
9 篇 zelensky a.
9 篇 bovik alan c.
9 篇 wei li
8 篇 frank hannig
8 篇 yves wiaux
8 篇 a.s. willsky
8 篇 mahalanobis a
8 篇 ilias maglogiann...

语言

14,979 篇 英文
539 篇 其他
90 篇 中文
26 篇 土耳其文
4 篇 俄文
3 篇 葡萄牙文
2 篇 法文
1 篇 西班牙文

检索条件"任意字段=Conference on Image Processing - Algorithms and Systems VI"

共 15618 条记录，以下是4161-4170 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：

What Makes an image Tagger Fair? Proprietary Auto-tagging and Interpretations on People images 27

What Makes an Image Tagger Fair? Proprietary Auto-tagging an...

引用

27th ACM conference on User Modeling, Adaptation and Personalization (ACM UMAP)

作者： Barlas, Pinar Kyriakou, Kyriakos Kleanthous, Styliani Otterbacher, Jahna Res Ctr Interact Media Smart Syst & Emerging Tech Nicosia Cyprus Open Univ Cyprus Cyprus Ctr Algorithm Transparency Nicosia Cyprus

ISBN: (纸本)9781450360210

image analysis algorithms have been a boon to personalization in digital systems and are now widely available via easy-to-use APIs. However, it is important to ensure that they behave fairly in applications that involve processing images of people, such as dating apps. We conduct an experiment to shed light on the factors influencing the perception of "fairness:" Participants are shown a photo along with two descriptions (human- and algorithm-generated). They are then asked to indicate which is "more fair" in the context of a dating site, and explain their reasoning. We vary a number of factors, including the gender, race and attractiveness of the person in the photo. While participants generally found human-generated tags to be more fair, API tags were judged as being more fair in one setting - where the image depicted an "attractive," white individual. In their explanations, participants often mention accuracy, as well as the objectivity/subjectivity of the tags in the description. We relate our work to the ongoing conversation about fairness in opaque tools like image tagging APIs, and their potential to result in harm.

关键词： algorithmic bias computer vision fairness image analysis

来源：评论

学校读者我要写书评

暂无评论

Autofocusing of SAR images Using Quadratic MM-Method

Autofocusing of SAR Images Using Quadratic MM-Method

引用

Wave Electronics and its Application in Information and Telecommunication systems (WECONF)

作者： Monakov, A. A. St Petersburg State Univ Aerosp Instrumentat St Petersburg Russia

ISBN: (纸本)9781728122885

Phase errors produced by trajectory instabilities of a radar carrier vehicle cause significant deterioration in the quality of images in synthetic aperture radar. Onboard navigation systems do not provide necessary accuracy of measuring trajectory instabilities to compensate the phase errors. Therefore, in modern synthetic aperture radars, autofocusing is an obligatory stage in the processing of received signals, which is performed by estimating and subsequent compensation of phase errors. Methods of searching for the optimum of some function of the quality of the radar image are often used to estimate phase errors. Despite the fact that the search methods are quite effective, this method of estimation is difficult to implement due to limited power of onboard computational tools. Therefore, the actual problem is the synthesis of direct algorithms for estimating phase errors. The article proposes an algorithm based on the optimization of surrogate quadratic quality functions. The essence of the proposed approach is to use at each step the estimating procedure a quadratic function, which is the majorant (minorant) for the quality function of radar images, which is selected for optimization. The proposed algorithm can be used with any quality function and allows to implement direct estimation of phase errors without organizing a search in the multidimensional space of the estimated parameters. Using the method of mathematical simulation, the article shows that this algorithm is highly efficient even with large phase errors and can be used for signal processing in synthesized aperture radars.

关键词： synthetic aperture radar radar image phase errors autofocusing radar image quality function surrogate quality function

来源：评论

学校读者我要写书评

暂无评论

Embedded Landmark implementation for Deep Learning pre-processing

Embedded Landmark implementation for Deep Learning pre-proce...

引用

International conference on Advanced Technologies for Signal and image processing (ATSIP)

作者： Hedi Choura Tarek Frikha Mouna Baklouti Faten Chaabane CES-Lab Sfax National Engineering School of Sfax University of Sfax Tunisia Regim-Lab Sfax National Engineering School of Sfax University of Sfax Tunisia

ISBN: (数字)9781728175133

ISBN: (纸本)9781728175140

Due to the evolution of information technology, it is becoming increasingly easy to use new platforms in order to set up efficient systems that are well adapted to the expected needs. As part of improving security and facilitating the detection of potentially dangerous persons, an intelligent application for on-board facial recognition is being developed. It is within this framework that we propose this paper. The objective of the proposed work is twofold. On the one hand, we propose to develop a module for the detection of relevant facial characteristics, which is the first step of an intelligent video surveillance application. Based on the detection of points of interest of the Landmark algorithm, a software optimization of the work is proposed. On the other hand, this application will be decomposed in order to be embedded on a multiprocessor architecture. In order to validate the multiprocessor-based approach, a comparison with other existing powerful processor architectures will allow to validate the best approach. This work will be the input for an intelligent embedded face detection application based on Machine Learning.

关键词： Program processors Computer architecture Shape Face recognition Deep learning Software Software algorithms

来源：评论

学校读者我要写书评

暂无评论

High-Throughput image Alignment for Connectomics using Frugal Snap Judgments

High-Throughput Image Alignment for Connectomics using Fruga...

引用

IEEE conference on High Performance Extreme Computing (HPEC)

作者： Tim Kaler Brian Wheatman Sarah Wooders MIT CSAIL Johns Hopkins University UC Berkeley

ISBN: (数字)9781728192192

ISBN: (纸本)9781728192208

The accuracy and computational efficiency of image alignment directly affects the advancement of connectomics, a field which seeks to understand the structure of the brain through electron microscopy. We introduce the algorithms Quilter and Stacker that are designed to perform 2D and 3D alignment respectively on petabyte-scale data sets from connectomics. Quilter and Stacker are efficient, scalable, and can run on hardware ranging from a researcher's laptop to a large computing cluster. On a single 18-core cloud machine each algorithm achieves throughputs of more than 1 TB/hr; when combined the algorithms produce an end-to-end alignment pipeline that processes data at a rate of 0.82 TB/hr - an over 10x improvement from previous systems. This efficiency comes from both traditional optimizations and from the use of “Frugal Snap Judgments” to judiciously exploit performance-accuracy trade-offs. A high-throughput image-alignment pipeline was implemented using the Quilter and Stacker algorithms and its performance was evaluated using three datasets whose size ranged from 550 GB to 38 TB. The full alignment pipeline achieved a throughput of 0.6-0.8 TB/hr and 1.4-1.5 TB/hr on an 18-core and 112-core shared-memory multicore, respectively. On a supercomputing cluster with 200 nodes and 1600 total cores, the pipeline achieved a throughput of 21.4 TB/hr. We introduce the algorithms Quilter and Stacker that are designed to perform 2D and 3D alignment respectively on petabyte-scale data sets from connectomics. Quilter and Stacker are efficient, scalable, and can run on hardware ranging from a researcher's laptop to a large computing cluster. On a single 18-core cloud machine each algorithm achieves throughputs of more than 1 TB/hr; when combined the algorithms produce an end-to-end alignment pipeline that processes data at a rate of 0.82 TB/hr - an over 10x improvement from previous systems. This efficiency comes from both traditional optimizations and from the use of “Frugal Sn

关键词： Three-dimensional displays Multicore processing Pipelines Two dimensional displays Clustering algorithms Throughput Hardware

来源：评论

学校读者我要写书评

暂无评论

CHARACTERIZATION OF THERMALS IN A HEATED TURBULENT BOUNDARY LAYER 8

CHARACTERIZATION OF THERMALS IN A HEATED TURBULENT BOUNDARY ...

引用

ASME-JSME-KSME Joint Fluids Engineering conference (AJK-FED 2019)

作者： Dennis, Kadeem Siddiqui, Kamran University of Western Ontario London ON Canada

ISBN: (纸本)9780791859025

The hydrodynamic boundary layer encountered in many practical engineering systems is turbulent in nature and known to play a significant role in governing the inducedfriction drag and species transport. In turbulent boundary layer flows, heat transfer is often involved which increases flow complexity due to the influence of buoyancy. When the buoyantforce is sufficiently large in magnitude, thermals carrying heatedfluid are known to detach and rise from the wall. Literature review shows that in mixed convection, thermals have been primarily identified through qualitative flow visualizations and there is a scarcity of their quantitative assessment. Furthermore, the evolution of thermals in the boundary layer with respect to flow inertia and viscous shear is not well-understood Hence, there is a needfor a better understanding of the dynamics of thermals in mixed convection turbulent boundary layer flow. The objective of this study is to experimentally investigate the three-dimensional nature of thermals risingfrom a turbulent boundary layer flow over a heated smooth horizontal flat plate. Experiments were performed in a closed loop low -disturbance wind tunnel with a test section featuring a 1 m long heated bottom wall. The multi-plane particle image velocimetry (PIV) technique was used to capture images in multiple planes with respect to the turbulent boundary layer mean flow direction for three-dimensional characterization. The measurements were conducted at Richardson numbers (Ri) of 0.3, 1.0, and 2.0. Flow visualization images are used to describe the nature of thermals and the dynamical proceSses involved during their interaction with bulk boundary layer flow. An image processing algorithm to detect thermals is then detailed and applied to experimental images. The performance of the new algorithm is then assessed in its ability to detect thermals.

关键词： Boundary layer turbulence Flow (Dynamics) Boundary layers algorithms Mixed convection Flow visualization Shear (Mechanics) Inertia (Mechanics) Dynamics (Mechanics) Engineering systems and industry applications Buoyancy Friction Heat transfer Fluids Particulate matter Turbulence Drag (Fluid dynamics) Flat plates image processing Wind tunnels

来源：评论

学校读者我要写书评

暂无评论

Fast robust matching algorithm based on BRISK and GMS 4

Fast robust matching algorithm based on BRISK and GMS

引用

2019 4th International conference on Intelligent Computing and Signal processing, ICSP 2019

作者： Cen, Chen Li, Runqi Xu, Xi Beijing Engineering Research Center for IoT Software and Systems Beijing University of Technology Beijing100124 China

In the image stitching technology, traditional feature extraction algorithms have uneven feature points distribution, many redundant features, time-consuming feature points precision matching and low image registration accuracy. In view of these problems, this paper proposes an improved image registration algorithm based on BRISK and GMS. In this method, the image is first divided into meshes and BRISK algorithm is used for extracting image features, then the Brute Force matching algorithm is used for rough image matching. Finally, the mesh motion estimation method is used for feature quantity statistics, and error matching is removed to obtain a set of fine matching feature points for image registration. This paper verified the robustness of the improved algorithm by comparing it with other methods in the Mikolajczyk data set. The experimental results show that this algorithm achieves higher matching accuracy on the basis of maintaining speed compared with the original algorithm, and the average accuracy is improved by 8.02%. It has better performance than the traditional algorithm, which can be used for occasions with higher requirements on registration accuracy and real-time performance. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Analysis and Application Based on GTF Infrared and visible image Fusion

Analysis and Application Based on GTF Infrared and Visible I...

引用

International conference on Computers, Communications, and systems (ICCCS)

作者： Tingting Lu Lei Zhang Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China MOE International Joint Lab of Trustworthy Software East China Normal University Shanghai China

ISBN: (数字)9781728161365

ISBN: (纸本)9781728161372

From 1997 to 2006, China's railway has undergone six large-scale speed-raising reconstruction, and some of the speed has reached 250KM/h. With the development of train speed, the pantograph-cantenary system becomes more and more important. Since infrared image has light penetration, this paper fuses infrared and visible images to get more information about the pantograph-cantenary so that train drivers can learn more about the pantograph-cantenary situation. Existing fusion methods typically use the same representations and extract the similar characteristics for different source images. However, it may don't work for infrared and visible images. In this paper, we use the fusion algorithm named Gradient Transfer Fusion (GTF), which can keep the thermal radiation and appearance information simultaneously. To prove the effectiveness of the GTF method, it is compared with other 17 fusion algorithms from quantitative aspects. Furthermore, the parameter in the GTF method is analyzed and selected for better fusion results. Finally, color image fusion which is an improvement to the GTF method preserving the color information of the visible image in the fused image is proposed and it is tested on publicly available data sets to prove its availability.

关键词： Standards image quality image fusion Discrete wavelet transforms Entropy Minimization

来源：评论

学校读者我要写书评

暂无评论

FAdeML: Understanding the Impact of Pre-processing Noise Filtering on Adversarial Machine Learning 22

FAdeML: Understanding the Impact of Pre-Processing Noise Fil...

引用

22nd Design, Automation and Test in Europe conference and Exhibition (DATE)

作者： Khalid, Faiq Hanif, Muhammad Abdullah Rehman, Semeen Qadir, Junaid Shafique, Muhammad Vienna Univ Technol Vienna Austria Informat Technol Univ Lahore Pakistan

ISBN: (纸本)9783981926323

Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large datasets. The discovery of a number of well-known attacks such as dataset poisoning, adversarial examples, and network manipulation (through the addition of malicious nodes) has, however, put the spotlight squarely on the lack of security in DNN-based ML systems. In particular, malicious actors can use these well-known attacks to cause random/targeted misclassification, or cause a change in the prediction confidence, by only slightly but systematically manipulating the environmental parameters, inference data, or the data acquisition block. Most of the prior adversarial attacks have, however, not accounted for the pre-processing noise filters commonly integrated with the ML-inference module. Our contribution in this work is to show that this is a major omission since these noise filters can render ineffective the majority of the existing attacks, which rely essentially on introducing adversarial noise. Apart from this, we also extend the state of the art by proposing a novel pre-processing noise Filter-aware Adversarial ML attack called FAdeML. To demonstrate the effectiveness of the proposed methodology, we generate an adversarial attack image by exploiting the "VGGNet" DNN trained for the "German Traffic Sign Recognition Benchmarks (GTSRB)" dataset, which despite having no visual noise, can cause a classifier to misclassify even in the presence of preprocessing noise fiters.

关键词： Security Hardware Filtering Training Data models Optimization Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

On the Practicality of Subspace Tracking in Information systems

On the Practicality of Subspace Tracking in Information Syst...

引用

World conference on Information systems and Technologies (WorldCIST)

作者： Ahmed, Noor Hasseler, Gregory AFRL RI Rome NY 13441 USA PAR Govt Syst Corp Rome NY 13440 USA

ISBN: (纸本)9783030161804;9783030161811

Modeling and characterizing information systems' observation data (i.e., logs) is fundamental for proper system configuration, security analysis, and monitoring system status. Due to the underlying dynamics of such systems, observations can be viewed as high-dimensional, time-varying, multivariate data. One broad class for concisely modeling systems with such data points is low-rank modeling where the observations manifest themselves in a lower-dimensional subspace. Subspace Tracking plays an important role in many applications, such as signal processing, image tracking and recognition, and machine learning. However, it is not well understood which tracker is suitable for a given information system in a practical setting. In this paper, we present a comprehensive comparative analysis of three state-of-the-art low-rank modeling approaches;GROUSE, PETRELS, and RankMin. These algorithms will be compared in terms of their convergence and stability, parameter sensitivity, and robustness in dealing with missing data for synthetic and real information systems data sets, and then summarize our findings.

关键词： Information systems Subspace tracking GROUSE PETRELS RankMin

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Digital images of Aerial Photography 5

Segmentation of Digital Images of Aerial Photography

引用

5th IEEE International conference Actual Problems of Unmanned Aerial Vehicles Developments, APUAVD 2019

作者： Yurchuk, Iryna Kovdrya, Vladyslav Bilyanska, Lolita Taras Shevchenko National University of Kyiv Software Systems and Technologies Department Kyiv Ukraine National Aviation University Applied Mathematics Department Kyiv Ukraine

ISBN: (纸本)9781728125923

For today, autonomous UAVs are a combination of artificial intelligence, mechanical devices, and navigational instruments. To save computing resources and improve the quality of their navigation, motion control systems, recognition, etc., real-time UAV's video has to be preprocessed by segmentation or clustering algorithms. In this work, the analysis of parameters of effective graph-based (EGB) and pyramidal segmentation algorithms (PSA) was obtained for digital images of aerial photography. The authors used RGB, Lab, and HSV (BHS) color models. According to the results of testing EGB algorithm is faster, but its result of segmentation is ordinary. Whereas, PSA produces a result that is closer to human perception but its disadvantage is a long processing time. Authors recommended Lab and HBS formats of image, since their segmentation results are more effective than, for example, at RGB. © 2019 IEEE.

关键词： Aerial photography

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 << < 413 414 415 416 417 418 419 420 421 422 > >>

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：