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

252 篇 会议
17 篇 期刊文献

馆藏范围

269 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

153 篇 工学
- 96 篇 计算机科学与技术...
- 68 篇 电气工程
- 53 篇 软件工程
- 26 篇 信息与通信工程
- 13 篇 机械工程
- 13 篇 光学工程
- 13 篇 生物医学工程（可授...
- 12 篇 仪器科学与技术
- 8 篇 控制科学与工程
- 6 篇 电子科学与技术（可...
- 6 篇 生物工程
- 5 篇 力学（可授工学、理...
- 5 篇 材料科学与工程（可...
- 3 篇 建筑学
- 2 篇 土木工程
- 2 篇 安全科学与工程
73 篇 理学
- 41 篇 物理学
- 33 篇 数学
- 6 篇 生物学
- 5 篇 统计学（可授理学、...
- 4 篇 系统科学
- 2 篇 化学
- 2 篇 天文学
38 篇 医学
- 35 篇 临床医学
- 7 篇 特种医学
- 4 篇 基础医学(可授医学...
- 2 篇 药学(可授医学、理...
3 篇 管理学
- 2 篇 图书情报与档案管...
2 篇 农学
1 篇 法学
- 1 篇 社会学
1 篇 教育学
- 1 篇 教育学
1 篇 军事学
1 篇 艺术学

主题

27 篇 image processing
25 篇 image reconstruc...
20 篇 noise reduction
20 篇 image segmentati...
18 篇 approximation al...
17 篇 approximation me...
14 篇 image denoising
12 篇 cameras
11 篇 vectors
10 篇 image coding
10 篇 image analysis
9 篇 image edge detec...
9 篇 visualization
9 篇 feature extracti...
8 篇 signal processin...
8 篇 pixel
8 篇 optimization
8 篇 shape
7 篇 noise measuremen...
7 篇 databases

机构

5 篇 department of si...
3 篇 tampere univ tec...
2 篇 electronics and ...
2 篇 institute of sig...
2 篇 von karman inst ...
2 篇 czech tech univ ...
2 篇 czech acad sci i...
1 篇 mitsubishi elect...
1 篇 karlsruhe inst t...
1 篇 department of ma...
1 篇 epfl sb mathaa c...
1 篇 aerodyne researc...
1 篇 univ rome tre de...
1 篇 old dominion uni...
1 篇 univ waterloo fa...
1 篇 university of lj...
1 篇 interregional ac...
1 篇 univ lancaster s...
1 篇 department of ap...
1 篇 friedrich alexan...

作者

3 篇 karen egiazarian
3 篇 ali h. sayed
3 篇 alessandro foi
2 篇 milanfar peyman
2 篇 k. egiazarian
2 篇 egiazarian k.
2 篇 foi alessandro
2 篇 burova i.g.
2 篇 dudak j.
2 篇 philip ogunbona
2 篇 yuichi tanaka
2 篇 tanaka yuichi
2 篇 scarano f
2 篇 r. venkatesh bab...
2 篇 zemlicka j.
2 篇 andré kaup
2 篇 egiazarian karen
2 篇 zaid j. towfic
2 篇 guillemot christ...
2 篇 wanqing li

语言

265 篇 英文
4 篇 其他

检索条件"任意字段=International Workshop on Local and Non-Local Approximation in Image Processing, LNLA"

共 269 条记录，以下是201-210 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：

Object Pose Estimation in the Presence of local Illumination Changes Using Scale Manipulation Transform

Object Pose Estimation in the Presence of Local Illumination...

引用

IEEE international workshop on Multimedia Signal processing

作者： Bentolila, Kobi Francos, Joseph M. Ben Gurion Univ Negev Dept Elect & Comp Engn IL-84105 Beer Sheva Israel

ISBN: (纸本)9781424444632

We present a novel image transform called Scale Manipulation (SMT). The transform can be used for object pose estimation and registration of affine transformed images in the presence of non homogenous illumination changes. The transform calculates affine invariant features of objects in a global manner and avoids using any sort of edge detection. The computational load of the method is relatively low since it is linear in the data size. In this paper we introduce the transform and demonstrate its applications for pose estimation in the presence of non uniform varying illumination.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

High-Entropy Hamming Embedding of local image Descriptors Using Random Projections

High-Entropy Hamming Embedding of Local Image Descriptors Us...

引用

IEEE international workshop on Multimedia Signal processing

作者： Sibiryakov, Alexander Mitsubishi Elect Res Ctr Europe Guildford Surrey England

ISBN: (纸本)9781424444632

We present a method of transformingloca I iniagedescriptors into a compact form of bit-sequences whose similarity is determined by Hamming distance. Following the locality-Sensitive Hashing approach, the descriptors are projected on a set ofrandoin directions that are learned from a set of non-matching data. The learned random projections result in high-entropy binary codes (H E 2) that outperform codes based on standard random projections in niatch/non-match classification and nearest neighbor search. Despite of data compression and granularity of Hamming space, HE--descriptor outperforms the original descriptor in the classification task. In nearest neighbor search task, the performance of the H E2 -descriptor is asymptotic to the performance of the original descriptor. As a supporting result, we obtain another descriptor, HE 2+1, and demonstrate that the performance of the original descriptor can be improved by adding a few bits derived from the descriptor itself.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Phonological context approximation and homophone treatment for NEWS 2009 English-Chinese transliteration shared task

Phonological context approximation and homophone treatment f...

引用

2009 Named Entities workshop: Shared Task on Transliteration, NEWS 2009 at the Joint Conference of the 47th Annual Meeting of the ACL and the 4th international Joint Conference on Natural Language processing of the AFNLP, ACL-IJCNLP 2009

作者： Kwong, Oi Yee Department of Chinese Translation and Linguistics City University of Hong Kong Tat Chee Avenue Kowloon Hong Kong

This paper describes our systems participating in the NEWS 2009 Machine Transliteration Shared Task. Two runs were submitted for the English-Chinese track. The system for the standard run is based on graphemic approximation of local phonological context. The one for the non-standard run is based on parallel modelling of sound and tone patterns for treating homophones in Chinese. Official results show that both systems stand in the mid range amongst all participating systems. © 2009 ACL and AFNLP.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A fast NL-Means method in image denoising based on the similarity of spatially sampled pixels

A fast NL-Means method in image denoising based on the simil...

引用

2009 IEEE international workshop on Multimedia Signal processing, MMSP '09

作者： Pang, Chao C.Au, Oscar Dai, Jingjing Yang, Wen Zou, Feng Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong

ISBN: (纸本)9781424444649

As one of the best image denoising methods, the non-local Means(NL-Means)algorithm[5] proposed by Buades et al. generates state-of-the-art performance. However, due to the high computational complexity, it is difficult to be directly used in practical applications. In this paper, a novel fast algorithm based on the similarity of spatially sampled pixels is introduced. Compared with other fast approaches, the result has shown that our method always uses the shortest time. Meanwhile, it keeps a similar or even better visual results. A maximum of 0.9dB improvement can be attained in comparison with the original method when the noise variance is small. © 2009 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Proceedings of SPIE-IS and T Electronic Imaging - image processing: Algorithms and Systems VII

Proceedings of SPIE-IS and T Electronic Imaging - Image Proc...

引用

image processing: Algorithms and Systems VII

ISBN: (纸本)9780819474957

The proceedings contain 43 papers. The topics discussed include: texture preservation in de-noising UAV surveillance video through multi-frame sampling;fast geodesic distance approximation using mesh decimation and front propagation;image object removal in redundant wavelet transform domain;nonlinear mapping of the luminance in dual-layer high dynamic range displays;color enhancement in a high dynamic range environment;active contours that grow and compete driven by local region descriptors;a fast intensity based non-rigid 2D-3D-registration using statistical shape models with application in radiotherapy;a Kernel representation for exponential splines with global tension;compression of multispectral fluorescence microscopic images based on a modified set partitioning in hierarchal trees;robust measurement of the blocking artefact;and image pixel guided tours: a software platform for non-destructive X-ray imaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SIFT-based local image description using sparse representations

SIFT-based local image description using sparse representati...

引用

IEEE workshop on Multimedia Signal processing

作者： Joaquin Zepeda Ewa Kijak Christine Guillemot INRIA-Centre Inria Rennes Bretagne Atlantique Rennes France INRIA Centre Rennes-Bretagne Atlantique Université de Rennes 1 Rennes France

This paper addresses the problem of efficient SIFT-based image description and searches in large databases within the framework of local querying. A descriptor called the bag-of-features has been introduced previously which first vector quantizes SIFT descriptors and then aggregates the set of resulting codeword indices (so-called visual words) into a histogram of occurrence of the different visual words in the image. The aim is to make the image search complexity tractable by transforming the set of local image descriptor vectors into a single sparse vector as sparsity particularly permits efficient inner product calculations. However, aggregating local descriptors into a single histogram decreases the discerning power of the system when performing local queries. In this paper, we propose a new approach that aims to enjoy the complexity benefits of sparsity while at the same time retaining the local quality of the input descriptor vectors. This is accomplished by searching for a sparse approximation of the input SIFT descriptors. The sparse approximation yields a sparse vector per local SIFT descriptor, and helps preserving local description properties by using each sparse-transformed descriptor independently in a voting system to retrieve indexed images. Our system is shown experimentally to perform better than histogram based systems under query locality, albeit at an increased complexity.

关键词： Histograms image retrieval Vector quantization image databases Content based retrieval Region 7 Visual databases Aggregates Voting Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Contextual unmixing of geospatial data based on Markov random fields and conditional random fields

Contextual unmixing of geospatial data based on Markov rando...

引用

workshop on Hyperspectral image and Signal processing: Evolution in Remote Sensing, WHISPERS

作者： Ryuei Nishii Tomohiko Ozaki Faculty of Mathematics Kyushu University Fukuoka Japan Graduate School of Mathematics Kyushu University Fukuoka Japan

In supervised and unsupervised image classification, it is known that contextual classification methods based on Markov random fields (MRFs) improve the performance of non-contextual classifiers. In this paper, we consider the unsupervised unmixing problem based on MRFs. The exact solutions maximizing local conditional densities are derived, and they show excellent performance for unximing of data sets. Furthermore a new stochastic model based on conditional random fields is proposed for unmixing of hyperspectral data. The approximation formula of its normalizing factor is also derived.

关键词： Markov random fields Training data Mathematics Pixel Multispectral imaging image classification Stochastic processes Hyperspectral imaging Logistics Machine learning

来源：评论

学校读者我要写书评

暂无评论

High-entropy Hamming embedding of local image descriptors using random projections

High-entropy Hamming embedding of local image descriptors us...

引用

IEEE workshop on Multimedia Signal processing

作者： Alexander Sibiryakov Mitsubishi Electric Research Centre Europe Guildford UK

We present a method of transforming local image descriptors into a compact form of bit-sequences whose similarity is determined by Hamming distance. Following the locality-sensitive hashing approach, the descriptors are projected on a set of random directions that are learned from a set of non-matching data. The learned random projections result in high-entropy binary codes (HE 2 ) that outperform codes based on standard random projections in match/non-match classification and nearest neighbor search. Despite of data compression and granularity of Hamming space, HE 2 -descriptor outperforms the original descriptor in the classification task. In nearest neighbor search task, the performance of the HE 2 -descriptor is asymptotic to the performance of the original descriptor. As a supporting result, we obtain another descriptor, HE 2 + 1, and demonstrate that the performance of the original descriptor can be improved by adding a few bits derived from the descriptor itself.

关键词： Hamming distance Data mining Binary codes Nearest neighbor searches image retrieval image storage Learning systems Entropy Europe Code standards

来源：评论

学校读者我要写书评

暂无评论

Object pose estimation in the presence of local illumination changes using Scale Manipulation Transform

Object pose estimation in the presence of local illumination...

引用

IEEE workshop on Multimedia Signal processing

作者： Kobi Bentolila Joseph M. Francos Electrical and Computer Engineering Department Ben-Gurion University of the Negev Beersheba Israel

We present a novel image transform called scale manipulation (SMT). The transform can be used for object pose estimation and registration of affine transformed images in the presence of non homogenous illumination changes. The transform calculates affine invariant features of objects in a global manner and avoids using any sort of edge detection. The computational load of the method is relatively low since it is linear in the data size. In this paper we introduce the transform and demonstrate its applications for pose estimation in the presence of non uniform varying illumination.

关键词： Lighting Surface-mount technology image edge detection image resolution Jacobian matrices image registration Light sources image analysis Hyperspectral sensors Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Tracking occluded targets in high-similarity background: An online training, non-local appearance model and periodic hybrid particle filter with projective transformation

Tracking occluded targets in high-similarity background: An ...

引用

IEEE international Conference on image processing

作者： Yi Wang Richard R. Schultz Department of Electrical Engineering University of North Dakota USA

Two main challenges lie in tracking the partially occluded targets in a high-similarity background: 1) similar intensities increase the difficulty of discriminating targets from the background, and 2) occlusion (illumination and shape) decreases the relativity of targets to templates. In this paper, a novel eigenspace-based hybrid particle filter tracking method combined with online non-local appearance model is proposed to track the objects under highly similar environment with occlusions. By on-line training of the templates through non-local methods to generate the active appearance model, it is more likely find the maximum-likelihood distribution correctly. The projective transformation is utilized to cover all of the possible motion factors between the templates. The extended and unscented Kalman filters are switched to update the particles according to the linearity of the motion parameters. The experiment results show the effectiveness of our algorithm while dealing with occluded target in a high-similarity background.

关键词： Target tracking Particle tracking Particle filters Least squares approximation Motion estimation Linearity Uncertainty Covariance matrix State-space methods Equations

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27页 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：