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

626 篇 会议
16 篇 期刊文献
8 册 图书

馆藏范围

650 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

373 篇 工学
- 289 篇 计算机科学与技术...
- 148 篇 软件工程
- 79 篇 信息与通信工程
- 77 篇 电气工程
- 46 篇 控制科学与工程
- 30 篇 生物医学工程（可授...
- 26 篇 电子科学与技术（可...
- 25 篇 光学工程
- 21 篇 仪器科学与技术
- 16 篇 生物工程
- 14 篇 机械工程
- 10 篇 网络空间安全
- 9 篇 测绘科学与技术
- 5 篇 材料科学与工程（可...
- 5 篇 化学工程与技术
- 4 篇 土木工程
- 4 篇 交通运输工程
120 篇 理学
- 52 篇 数学
- 44 篇 物理学
- 21 篇 生物学
- 13 篇 系统科学
- 6 篇 统计学（可授理学、...
- 5 篇 化学
74 篇 医学
- 54 篇 临床医学
- 23 篇 基础医学(可授医学...
- 16 篇 特种医学
- 8 篇 药学(可授医学、理...
35 篇 管理学
- 21 篇 管理科学与工程(可...
- 15 篇 图书情报与档案管...
- 6 篇 工商管理
1 篇 教育学
1 篇 文学
1 篇 农学

主题

93 篇 image processing
58 篇 signal processin...
50 篇 image segmentati...
29 篇 parallel process...
29 篇 algorithm design...
28 篇 clustering algor...
27 篇 cameras
24 篇 image reconstruc...
21 篇 deep learning
21 篇 computer archite...
21 篇 hardware
20 篇 image color anal...
20 篇 robustness
19 篇 computer vision
18 篇 concurrent compu...
17 篇 image edge detec...
17 篇 machine learning
17 篇 testing
16 篇 feature extracti...
15 篇 signal processin...

机构

2 篇 city university ...
2 篇 computer science...
2 篇 integrated elect...
2 篇 guilin univ elec...
2 篇 otto-von-guerick...
2 篇 vishwakarma inst...
2 篇 univ chinese aca...
2 篇 airbnb
2 篇 university of ap...
2 篇 department of co...
2 篇 school of engine...
2 篇 migu co ltd peop...
2 篇 centre of intell...
2 篇 ist school of mo...
2 篇 123 cheomdangwag...
2 篇 moscow state uni...
2 篇 haikou coll econ...
2 篇 school of electr...
2 篇 department of in...
2 篇 college of mecha...

作者

3 篇 song li
3 篇 bustince humbert...
3 篇 montero javier
3 篇 magoules frederi...
3 篇 ho yo-sung
3 篇 perfilieva irina
3 篇 voronin v.
2 篇 lukin vladimir
2 篇 conglei shi
2 篇 mohamed f
2 篇 l.e. garey
2 篇 kyamakya kyandog...
2 篇 dong-in kang
2 篇 semenishchev e.
2 篇 chang yong-jun
2 篇 a.j.m. traina
2 篇 christos mousas
2 篇 zelensky a.
2 篇 pan hang
2 篇 r.e. shaw

语言

642 篇 英文
4 篇 中文
3 篇 其他
1 篇 德文

检索条件"任意字段=16th Image Processing: Algorithms and Systems Symposium 2018"

共 650 条记录，以下是151-160 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：

Color facial image representation with new quaternion gradients 16

Color facial image representation with new quaternion gradie...

引用

16th image processing: algorithms and systems symposium 2018

作者： Grigoryan, Artyom Agaian, Sos Department of Electrical and Computer Engineering University of Texas at San Antonio United States Computer Science Department College of Staten Island and the Graduate Center Staten IslandNY United States

this paper proposes a new color image representation and multiple feature fusion based method for improving color face recognition performance under different lighting conditions. First, a new image color image representation has been derived. Second, a quaternion gradient has been given to enhance and extract the faces/object's edges, contours, and texture. Also, we propose a novel feature representation based on Quaternion Gradient-based LBP tool for color face recognition. Finally, we present a concept of combining the color facial recognition system, which is based on the local quaternion gradients based binary patterns LBP image Representation, and a new color-to-gray new mapping. the presented concept can be used for surveillance, security systems, computer animation, face tagging, human- computer interface, biometric identification, behavioral analysis, content-based image and video indexing applications. © 2018 Society for Imaging Science and Technology.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Computing image Intersection and Union Regions for Drosophila Neurons Based on Multi-core CPUs 16th

Computing Image Intersection and Union Regions for Drosophil...

引用

16th International symposium on Pervasive systems, algorithms and Networks, I-SPAN 2019

作者： Guo, Ming-Yan Cheng, Hui-Jun Lin, Chun-Yuan Lin, Yen-Jen Chiang, Ann-Shyn Department of Computer Science and Information Engineering Chang Gung University Taoyuan33302 Taiwan AI Innovation Research Center Chang Gung University Taoyuan33302 Taiwan Division of Rheumatology Allergy and Immunology Chang Gung Memorial Hospital Taoyuan33302 Taiwan National Center for High-Performance Computing Hsinchu30076 Taiwan Brain Research Center National Tsing Hua University Hsinchu30013 Taiwan Institute of Biotechnology and Department of Life Science National Tsing Hua University Hsinchu30013 Taiwan Kavli Institute for Brain and Mind University of California at San Diego La Jolla San DiegoCA United States Department of Biomedical Science and Environmental Biology Kaohsiung Medical University Kaohsiung80708 Taiwan Genomics Research Center Academia Sinica NankangTaipei11529 Taiwan

ISBN: (纸本)9783030301422

With more and more Drosophila Driver and Neuron images, it is an important work to find the similarity relationships among them as the functional inference. there is a general problem that how to find a Drosophila Driver image, which can cover a set of Drosophila Neuron images. In order to solve this problem, the intersection/union region for a set of Drosophila Neuron images should be computed at first, then a comparison work is used to calculate the similarities between the region and Drosophila Driver image(s). In this paper, three encoding schemes, namely Integer, Boolean, Decimal, are proposed to encode each Drosophila Driver and Neuron image as a one-dimensional structure, respectively. then, the intersection/union region from these images can be computed by using the various operations, such as Boolean operators and lookup-table search method. Finally, the comparison work is done as the union region computation, and the similarity score can be calculated by the definition of Tanimoto coefficient. the above methods for the region computation are also implemented in the multi-core CPUs environment with the OpenMP. From the experimental results, in the encoding phase, the performance by Boolean scheme is the best than that by others;in the region computation phase, the performance by Decimal is the best when the number of images is large. the speedup ratio can achieve 13 based on 16 CPUs. © 2019, Springer Nature Switzerland AG.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Sharpening image details using local phase congruency analysis 16

Sharpening image details using local phase congruency analys...

引用

16th image processing: algorithms and systems symposium 2018

作者： Shcherbinin, Andrey Kolchin, Konstantin Glazistov, Ivan Rychagov, Mikhail Han, Seung-Hoon Samsung R and D Institute Russia Moscow Russia Samsung Research Seoul Korea Republic of

We suggest a method for sharpening an image or video stream without using convolution, as in unsharp masking, or deconvolution, as in constrained least-squares filtering. Instead, our technique is based on a local analysis of phase congruency and hence focuses on perceptually important details. the image is partitioned into overlapping tiles, and is processed tile by tile. We perform a Fourier transform for each of the tiles, and define congruency for each of the components in such a way that it is large when the component's neighbours are aligned with it, and small otherwise. We then amplify weak components with high phase congruency and reduce strong components with low phase congruency. Following this method, we avoid strengthening the Fourier components corresponding to sharp edges, while amplifying those details that underwent a slight or moderate defocus blur. the tiles are then seamlessly stitched. As a result, the image sharpness is improved wherever perceptually important details are present. © 2018 Society for Imaging Science and Technology.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

SANVis: Visual Analytics for Understanding Self-Attention Networks

SANVis: Visual Analytics for Understanding Self-Attention Ne...

引用

16th IEEE symposium on Visualization for Cyber Security (VizSec) / IEEE Visualization Conference (IEEE VIS)

作者： Park, Cheonbok Na, Inyoup Jo, Yongjang Shin, Sungbok Yoo, Jaehyo Kwon, Bum Chul Zhao, Jian Noh, Hyungjong Lee, Yeonsoo Choo, Jaegul Korea Univ Seoul South Korea Univ Maryland College Pk MD 20742 USA IBM Res Yorktown Hts NY USA Univ Waterloo Waterloo ON Canada NCSOFT Co LTD Seongnam South Korea FXPAL Palo Alto CA USA

ISBN: (纸本)9781728149417

Attention networks, a deep neural network architecture inspired by humans' attention mechanism, have seen significant success in image captioning, machine translation, and many other applications. Recently, they have been further evolved into an advanced approach called multi-head self-attention networks, which can encode a set of input vectors, e.g., word vectors in a sentence, into another set of vectors. Such encoding aims at simultaneously capturing diverse syntactic and semantic features within a set, each of which corresponds to a particular attention head, forming altogether multi-head attention. Meanwhile, the increased model complexity prevents users from easily understanding and manipulating the inner workings of models. To tackle the challenges, we present a visual analytics system called SANVis, which helps users understand the behaviors and the characteristics of multi-head self-attention networks. Using a state-of-the-art self-attention model called Transformer, we demonstrate usage scenarios of SANVis in machine translation tasks. Our system is available at http://***.

关键词： Deep neural networks visual analytics natural language processing interpretability self-attention networks

来源：评论

学校读者我要写书评

暂无评论

Preliminary Development of an Automatic Breast Tumour Segmentation Algorithm from Ultrasound Volumetric images 6th

Preliminary Development of an Automatic Breast Tumour Segmen...

引用

6th International Conference on Information Technology in Biomedicine (ITIB)

作者： Wieclawek, Wojciech Rudzki, Marcin Wijata, Agata Galinska, Marta Silesian Tech Univ Fac Biomed Engn Roosevelta 40 PL-41800 Zabrze Poland

ISBN: (纸本)9783319912110

Breast tumour is a leading cause for woman mortality. While cancer screening is mostly performed by the use of mammography, 3D ultrasound seems better suited for the purpose. It gives 3D view of the breast structure, is less painful and can be considered less invasive, as the patient is not exposed to x-ray radiation. therefore, the development of automatic algorithms that remove from the diagnostician the tedious and time consuming task of finding suspicious regions in large volumetric images is of key importance. the paper concludes a preliminary study for the development of an automatic method for breast tumour segmentation in ultrasound volumetric images. the method is based on multi-scale blob detector, watershed transform with the final precise segmentation performed by an active contour approach. the method has been evaluated using 16 volumes acquired from a breast phantom containing nodules. the obtained results reached up to 94.68% sensitivity, 100.00% specificity, 92.63% Dice index, 99.95% Accuracy, 92.61% Cohen's Kappa index and 86.28% Jaccard index.

关键词： Breast tumour Ultrasonography Automatic segmentation image processing

来源：评论

学校读者我要写书评

暂无评论

引用

16th image processing: algorithms and systems symposium 2018

作者： Wang, Mengjiao Liu, Rujie Fujitsu R and D Center CO. LTD. Beijing China

Diffuse lung disease (DLD) is difficult to diagnose due to the ambiguity of disease patterns, which motivates the development of image retrieval method to facilitate the physicians in diagnosis by retrieving the similar cases from database. In this paper, we propose a similarity measurement method for diffuse lung disease computed tomography (CT) slice image retrieval. In our method, the DLD patterns and the spatial distribution of the diseased area are both integrated to compute the similarity between query and database image. For this purpose, the powerful GoogLeNet is adopted and fine-tuned to locate the diseased area and classify it into different DLD patterns. Moreover, the spatial distribution of the diseased area is calculated based on the distance to the body center. Our method is verified on 324 CT slice images obtained from 53 subjects. the correct ratio among the top-5 retrieved images achieved 86.2%. Based on this performance, we can draw the conclusion that this method has high potential to improve the efficiency for diagnosis of diffuse lung disease in clinical use. © 2018 Society for Imaging Science and Technology.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

Visualization of Physiologic Signals based on Hjorth Parameters and Gramian Angular Fields 16

Visualization of Physiologic Signals based on Hjorth Paramet...

引用

IEEE 16th World symposium on Applied Machine Intelligence and Informatics (SAMI) Dedicated to the Memory of Pioneer of Robotics Antal (Tony) K. Bejczy

作者： Damasevicius, Robertas Maskeliunas, Rytis Wozniak, Marcin Polap, Dawid Kaunas Univ Technol Dept Software Engn Kaunas Lithuania Silesian Tech Univ Inst Math & Informat Gliwice Poland

ISBN: (纸本)9781538647721

Visual analysis is an important part of interactive data exploration. Visualization is especially important for analysis of physiological signals derived from sensors placed on the human body or implanted. Biomedical signals can provide valuable information about the state of a subject, but usually they are difficult to interpret due to large amount, high complexity and high-dimensionality. Here we present a novel method for two-dimensional visualization of physiological time series based on Gramian Angular Field (GAF) representations of Hjorth parameters of time series. Illustrative examples for electrocardiography (ECG) signals are presented. the practical use of the visualization method is demonstrated on the arrhythmia case classification task. We report 86% accuracy of classification (using KNN) of Premature Ventricular Contraction (PVC) beats vs. normal beats using the statistical features extracted from images generated using the proposed method.

关键词： time series visualization pattern recognition image processing visual analytics

来源：评论

学校读者我要写书评

暂无评论

An Accuracy-Area Tradeoff for Mixed-Signal Computation in Programmable Smart image Sensors 16

An Accuracy-Area Tradeoff for Mixed-Signal Computation in Pr...

引用

16th IEEE International New Circuits and systems Conference (NEWCAS)

作者： Le Hir, Juliette Vinci dos Santos, Filipe Kolar, Anthony UPMC Univ Paris 06 Sorbonne Univ Univ Paris Saclay Univ Paris SudCent SupelecGeePsUMR CNRS 8507 Gif Sur Yvette France Cent Supelec SANA Adv Analog Design Grp Gif Sur Yvette France

ISBN: (纸本)9781538648599

Tightly embedded systems often require low power real time processing of acquired sensor data. this paper presents the design and transistor-level implementation of a mixed-signal processing element for highly area-constrained systems in applications where approximate computing is sufficient. the analog processing unit consists of a switched capacitor circuit whose imperfections such as finite gain or offset errors are evaluated here through theoretical analyses and Monte Carlo simulations for a CMOS 0.35 mu m technology. Transistor-level simulation results further demonstrate that this processing unit is suitable for image pre-processing tasks such as spatial convolution for edge detection.

关键词： lived analog-digital electronics approximate computing algorithm-architecture matching smart image sensor vision system on a chip (VSoC)

来源：评论

学校读者我要写书评

暂无评论

Legendarium Nagyappo: Augmented Reality-based Audiobook Application 16

Legendarium Nagyappo: Augmented Reality-based Audiobook Appl...

引用

IEEE 16th International symposium on Intelligent systems and Informatics (SISY)

作者： Dongolo, Zsolt Kovacs, Kinga Simon, Karoly Szecsi, Zsolt Babes Bolyai Univ Cluj Napoca Romania Codespring LLC Cluj Napoca Romania Babes Bolyai Univ Codespring LLC Cluj Napoca Romania

ISBN: (纸本)9781538668412

the article presents the structure and the functioning of the Nagyappo Android mobile application and its implementation background. the purpose of the project is to create an application that is able to automatically identify legends by image recognition from the Szekelyfoldi Legendarium book and "read" them. To make the audio playback even more interesting, Augmented Reality (AR) elements are integrated into the application. the legends are "read" by the well-known grandfather character from the Legendarium cartoon series. Grandpa (in Hungarian Nagyapo) walks in into the camera view and sitting down on the page of the book tells the story of the legend to which the phone's camera is directed. the application is mainly made for small children. Using the software, they can become acquainted with Transylvania's legends even before they can read. If someone does not have the Szekelyfoldi Legendcirium book, he/she can still listen to the available content: using the Search functionality, it is possible to search among the available audio books. the media materials (animations, audio books, images) which are used within the application are provided by the Szekelyfoldi Legendcirium team.

关键词： Animation image recognition Cameras three-dimensional displays Smart phones Solid modeling Games

来源：评论

学校读者我要写书评

暂无评论

High dynamic range imaging with a single exposure-multiplexed image using smooth contour prior 16

High dynamic range imaging with a single exposure-multiplexe...

引用

16th image processing: algorithms and systems symposium 2018

作者： Rouf, Mushfiqur Ward, Rabab K. Department of Computer Science University of British Columbia VancouverBC Canada Department of Electrical and Computer Engineering University of British Columbia VancouverBC Canada

Photography is an ever-advancing technology: pixels are getting more densely packed, colors are going deeper, and light sensitivity is going higher. But the camera standard dynamic range largely remains less than the full brightness range of a natural scene. In the days of film cameras people have used the multiexposure high dynamic range imaging to capture the full dynamic range although only limited for static scenes. However, with digital photography, the exposure index can be spatially multiplexed on a sensor, which adapts the essence of the multi-exposure technique for single-image high dynamic range imaging. A sophisticated postprocessing is required;and existing techniques either lose final image resolution or take a long time to run. In this paper, we propose a novel method for this postprocessing: we use a robust global optimization method and a fast edge-preserving interpolation technique for full resolution exposure-multiplexed high dynamic range imaging. © 2018 Society for Imaging Science and Technology.

关键词： Photographic films

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65页 << < 12 13 14 15 16 17 18 19 20 21 > >>

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：