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

37 篇 会议
4 篇 期刊文献

馆藏范围

41 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

34 篇 工学
- 26 篇 计算机科学与技术...
- 23 篇 软件工程
- 11 篇 控制科学与工程
- 10 篇 信息与通信工程
- 8 篇 光学工程
- 4 篇 电气工程
- 3 篇 机械工程
- 3 篇 化学工程与技术
- 2 篇 仪器科学与技术
- 2 篇 交通运输工程
- 2 篇 生物医学工程（可授...
- 2 篇 生物工程
- 1 篇 冶金工程
- 1 篇 建筑学
- 1 篇 土木工程
- 1 篇 航空宇航科学与技...
26 篇 理学
- 20 篇 数学
- 8 篇 物理学
- 3 篇 统计学（可授理学、...
- 2 篇 生物学
- 2 篇 系统科学
- 1 篇 化学
- 1 篇 大气科学
6 篇 管理学
- 4 篇 图书情报与档案管...
- 3 篇 管理科学与工程(可...
1 篇 法学
- 1 篇 社会学
1 篇 医学
- 1 篇 基础医学(可授医学...
- 1 篇 临床医学
- 1 篇 药学(可授医学、理...

主题

4 篇 graph theory
3 篇 image segmentati...
3 篇 topology
2 篇 statistics
2 篇 mobile robots
2 篇 stereo image pro...
2 篇 computers
1 篇 image enhancemen...
1 篇 musculoskeletal ...
1 篇 motion estimatio...
1 篇 trees (mathemati...
1 篇 technological ad...
1 篇 face recognition
1 篇 cameras
1 篇 ancient
1 篇 tracking
1 篇 excavation
1 篇 visualization
1 篇 software testing
1 篇 semantics

机构

4 篇 pattern recognit...
2 篇 pattern recognit...
2 篇 dipartimento di ...
2 篇 pattern recognit...
2 篇 pattern recognit...
1 篇 school of biomed...
1 篇 wirtschaftsunive...
1 篇 state key labora...
1 篇 institute of com...
1 篇 yatiris group pl...
1 篇 vienna universit...
1 篇 university of lj...
1 篇 institute for co...
1 篇 pattern recognit...
1 篇 department of pa...
1 篇 pattern recognit...
1 篇 saudi electronic...
1 篇 the institute of...
1 篇 vienna universit...
1 篇 pattern recognit...

作者

14 篇 kropatsch walter...
8 篇 sablatnig robert
6 篇 haxhimusa yll
5 篇 menard christian
5 篇 kampel martin
5 篇 bischof horst
5 篇 kampel m.
4 篇 glantz roland
3 篇 wildenauer horst
3 篇 langs georg
3 篇 leonardis aleš
2 篇 jogan matjaž
2 篇 ion adrian
2 篇 pták pavel
1 篇 sigut josé
1 篇 matas jiri
1 篇 mara h.
1 篇 zaharieva m.
1 篇 xu xinxing
1 篇 goebel peter mic...

语言

41 篇 英文

检索条件"机构=Pattern Recognition and Image Processing Group 183/2"

共 41 条记录，以下是31-40 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：

Classification of archaeological fragments using a description language 9

Classification of archaeological fragments using a descripti...

引用

9th European Signal processing Conference, EUSIPCO 1998

作者： Sablatnig, Robert Menard, Christian Kropatseh, Walter Pattern Recognition and Image Processing Group Institute of Automation Vienna University of Technology Treitlstraße 3/183/2 ViennaA-1040 Austria

This paper presents an application of 3D-reconstruction and graph theory in the field of archaeology. The classification and reconstruction of ancient pots and vessels out of fragments (so-called sherds) is an important aspect of archaeological research work. Up to now this is a time consuming, inaccurate, and subjective task which leads to tons of unclassified fragments in archives. Computer aided classification could help to get a better understanding of ancient cultures, since all data of an excavation would be accessible to the public, not only- selected parts as it is now. We propose a bottom-up strategy to classify fragments. The profile section (which is a section a the fragment in the direction of the rotational axis) is segmented into its primitives (with certain properties like length) and relations among this primitives (like position and curvature of connecting points). These primitives and the relations form a description language, different profiles have different descriptions.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Minimizing the topological structure of line images 7th

引用

7th Joint IAPR International Workshop on Structural and Syntactic pattern recognition, SSPR 1998 and 2nd International Workshop on Statistical Techniques in pattern recognition, SPR 1998

作者： Kropatsch, Walter G. Burge, Mark Vienna University of Technology Institute of Automation 183/2 Pattern Recognition and Image Processing Group Treitlstr.3 WienA-1040 Austria Johannes Kepler University Institute of Systems Science Computer Vision Laboratory LinzA-4040 Austria

ISBN: (纸本)3540648585

We present a new algorithm based on Dual Graph Contraction (DGC) to transform the Run Graph into its Minimum Line Property Preserving (MLPP) form which, when implemented in parallel, requires O(log(longestcurve)) steps. A MLPP graph of a line image compliments the structural information in geometric graph representations like the run graph. Using such a graph and its dual, line image analysis systems can efficiently detect topological features like loops and holes and make use of relations like containment. © Springer-Verlag Berlin Heidelberg 1998.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

The path-connectedness in Z2 and Z3 and classical topologies 7th

引用

7th Joint IAPR International Workshop on Structural and Syntactic pattern recognition, SSPR 1998 and 2nd International Workshop on Statistical Techniques in pattern recognition, SPR 1998

作者： Kropatsch, Walter Pták, Pavel Pattern Recognition and Image Proc. Group – PRIP Vienna University of Technology Treitlstr. 3 183/2 ViennaA-1040 Austria Center for Machine Perception CMP - Czech Technical University Karlovo nám. 13 Praha 2121 35 Czech Republic

ISBN: (纸本)3540648585

The main problem we persue in this paper is the question of when a given path-connectedness in Z2 and Z3 coincides with a topological cormectedness. We answer this question provided the path--connectedness is induced by a homogeneous and symmetric neighbourhood structure. On the way we make a study of topological structures, arguing that the point-neighbourhood formalism can be well applied in the digital picture investigations. © Springer-Verlag Berlin Heidelberg 1998.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Object-detection with a varying number of eigenspace projections

Object-detection with a varying number of eigenspace project...

引用

14th International Conference on pattern recognition, ICPR 1998

作者： Reiter, Michael Matas, Jiri Pattern Recognition and Image Processing Group Institute for Automation Vienna University of Technology A-1040 Vienna Austria CVSSP School of EE IT and Mathematics University of Surrey Guildford Surrey GU2 5XH United Kingdom

ISBN: (纸本)0818685123

We present a method allowing a significant speed-up of the eigen-detection method (detection based on principle component analysis). We derive a formula for an upper bound on the class-conditional probability (or equivalently a lower bound on the Mahalanobis distance) on which detection is based. Often, the lower bound of Mahalanobis distance (MD) reaches a preset threshold after computation of only a few eigen-projections. In this case the computation of MD can be immediately terminated. Regardless of the precise value of MD, the detection hypothesis (object from class Ω is detected) can be rejected. While provably obtaining results identical to the standard technique, we achieved a two- to three-fold speed-up in face detection experiments on images from the CMU database. © 1998 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Stereo correspondences in scale space 3rd

Stereo correspondences in scale space

引用

3rd Asian Conference on Computer Vision, ACCV 1998

作者： Menard, Christian Pattern Recognition and Image Processing Group Vienna University of Technology TreitlstraBe 3/183/2 ViennaA-1040 Austria

ISBN: (纸本)3540639306

A central problem in stereo matching using correlation techniques lies in selecting the size of the search window. Small windows contain only a small number of data points, and thus are very sensitive to noise and therefore result in false matches. Whereas large search windows contain data from two or more different objects or surfaces, thus the estimated disparity is not accurate due to different projective distortions in the left and the right image. The new method introduces a continuous scale parameter for the matching process. It allows the adaption of the scale for every individual region and overcomes the drawbacks of fixed window sizes which is impressively demonstrated by the experimental results. © Springer-Verlag Berlin Heidelberg 1997.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Adaptive stereo matching in correlation scale-space 9th

Adaptive stereo matching in correlation scale-space

引用

9th International Conference on image Analysis and processing, ICIAP 1997

作者： Menard, Christian Kropatsch, Walter G. Pattern Recognition and Image Processing Group Vienna University of Technology Treitlstraße 3/183/2 ViennaA-1040 Austria

ISBN: (纸本)3540635076

Stereo computes the distance of objects, "their depth", from two images of two cameras using the triangulation principle. Points of imaged objects are mapped in different locations in the two stereo images. A central problem in stereo matching using correlation techniques lies in selecting the size of the search window. Small windows contain only a small number of data points, and thus are very sensitive to noise and therefore result in false matches. Whereas large search windows contain data from two or more different objects or surfaces, thus the estimated disparity is not accurate due to different projective distortions in the left and the right image. The new method introduces a continuous scale parameter for the matching process. It allows the adaption of the scale for every individual region and overcomes the drawbacks of fixed window sizes which is impressively demonstrated by the experimental results. © Springer-Verlag Berlin Heidelberg 1997.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Stereo matching using M-estimators 7th

Stereo matching using M-estimators

引用

7th International Conference on Computer Analysis of images and patterns, CAIP 1997

作者： Menard, Christian Leonardis, Aleš Pattern Recognition and Image Processing Group Vienna University of Technology Treitlstraße 3/183/2 Vienna Austria University of Ljubljana Slovenia

ISBN: (纸本)3540634606

Stereo computation is just one of the vision problems where the presence of outliers cannot be neglected. Most standard algorithms make unrealistic assumptions about noise distributions, which leads to erroneous results that cannot be corrected in subsequent processing stages. In this work the standard area-based correlation approach is modified so that it can tolerate a significant number of outliers. The approach exhibits a robust behaviour not only in the presence of mismatches but also in the case of depth discontinuities. Experimental results are given on synthetic and real images. © Springer-Verlag Berlin Heidelberg 1997.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Flexible automatic visual inspection based on the separation of detection and analysis

Flexible automatic visual inspection based on the separation...

引用

13th International Conference on pattern recognition, ICPR 1996

作者： Sablatnig, Robert Department of Pattern Recognition and Image Processing Technical University Vienna Treitlsrr. 3/183-2 A-1040 Vienna Austria

ISBN: (纸本)081867282X

Since the mid-1970s, a large number of visual inspection systems and algorithms for industrial inspection have been developed. To be acceptable in industry, vision systems must be inexpensive, within the speed of the production-line flow, and very accurate. Furthermore the system should be flexible enough to accommodate changes in products. This flexibility can only be achieved by a modular concept that allows a quick and inexpensive adaption of the inspection process to changes in production. This paper presents a concept for visual inspection where the detection of primitives is separated from the model-based analysis process. Existing pattern recognition software is re-used in the detection stage and therefore the use of any detection algorithm is possible without changing the analysis process. The visual inspection of analog display measuring instruments serves as a demonstration of this concept. Results concerning time, accuracy, and reliability for the specific inspection task are given at the end of the paper. © 1996 IEEE.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Visual inspection of watermeters used for automatic calibration 3rd

引用

3rd International Computer Science Conference (ICSC 95) - image Analysis Applications and Computer Graphics

作者： Sablatnig, R Dept. of Pattern Recognition and Image Processing Technical University Vienna Treitlstr. 3/183-2 Vienna A-1040 Austria

ISBN: (纸本)3540606971

To be acceptable in industry, automatic visual inspection systems must be inexpensive, very accurate and should be flexible enough to accommodate changes in products. This flexibility can be reached if a modular concept that allows a quick and inexpensive adaption of the inspection process to any changes is used. This paper presents a concept where the detection of primitives is separated from the model-based analysis process. Existing pattern recognition software is re-used in the detection stage, allowing any detection algorithm to be tested and used without changing the analysis process. The visual inspection of analog watermeters serves for a demonstration of this concept.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Towards higher decimation ratios 6th

引用

6th International Conference on Computer Analysis of images and patterns, CAIP 1995

作者： Kropatsch, Walter G. Technical University of Vienna Institute for Automation 183/2 Department for Pattern Recognition and Image Processing Treitlstr. 3 WienA-1040 Austria

ISBN: (纸本)3540602682

The structural component of a computer vision model expresses qualitative image and scene properties. In our approach a hierarchy of plane graphs forms the structure to represent a variety of different levels of abstraction. Repeated parallel application of dual graph contractions generates a stack of successively smaller graphs bottom-up: an irregular pyramid. This process preserves topological relations among the 'surviving' components. The decimation ratio determines the pyramid's height and, as a consequence, the speed of top-down retrieval of visual features stored in the cells of the pyramid. The new version can contract dual image graphs gradually from the elimination of a single vertex per step up to a complete contraction into a single (top) vertex. Decimation parameters control one single dual contraction of the graph. Equivalent contraction kernels combine several sets of decimation parameters. They can generate the same result in one single dual contraction. © Springer-Verlag Berlin Heidelberg 1995.

关键词： Computers

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5页 << < 1 2 3 4 5 > >>

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：