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

471 篇 会议
253 篇 期刊文献

馆藏范围

724 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

565 篇 工学
- 505 篇 计算机科学与技术...
- 467 篇 软件工程
- 165 篇 光学工程
- 50 篇 生物医学工程（可授...
- 43 篇 生物工程
- 40 篇 电气工程
- 37 篇 信息与通信工程
- 25 篇 控制科学与工程
- 22 篇 材料科学与工程（可...
- 19 篇 仪器科学与技术
- 12 篇 建筑学
- 10 篇 电子科学与技术（可...
- 10 篇 航空宇航科学与技...
- 7 篇 土木工程
- 5 篇 力学（可授工学、理...
- 5 篇 机械工程
- 4 篇 轻工技术与工程
- 3 篇 冶金工程
- 2 篇 化学工程与技术
- 2 篇 交通运输工程
263 篇 理学
- 176 篇 物理学
- 140 篇 数学
- 42 篇 生物学
- 31 篇 统计学（可授理学、...
- 2 篇 地球物理学
12 篇 管理学
- 8 篇 图书情报与档案管...
- 4 篇 管理科学与工程(可...
4 篇 医学
- 4 篇 临床医学
2 篇 农学
- 2 篇 作物学
2 篇 军事学

主题

336 篇 image processing
217 篇 pattern recognit...
62 篇 pattern recognit...
6 篇 satellites
6 篇 computer vision
5 篇 computer graphic...
5 篇 imaging techniqu...
5 篇 remote sensing
4 篇 data processing
4 篇 biomedical engin...
4 篇 robots
4 篇 image coding
4 篇 computer program...
4 篇 systems science ...
4 篇 vision
4 篇 image reconstruc...
3 篇 computational mo...
3 篇 automata theory
2 篇 learning systems
2 篇 noise reduction

机构

8 篇 artificial intel...
7 篇 univ of michigan...
6 篇 univ of southern...
5 篇 harvard univ cam...
5 篇 univ of maryland...
4 篇 univ chinese aca...
4 篇 chinese acad sci...
4 篇 peng cheng lab p...
4 篇 columbia univ ny
3 篇 univ sci & techn...
3 篇 michigan state u...
3 篇 state univ of ne...
3 篇 univ of illinois...
3 篇 new york univ ny
2 篇 univ of massachu...
2 篇 comput & inf sci...
2 篇 inria le chesnay
2 篇 hebrew univ of j...
2 篇 mit cambridge ma
2 篇 dept of comput s...

作者

13 篇 anon
11 篇 haralick robert ...
11 篇 fu k.s.
8 篇 pavlidis theodos...
8 篇 shapiro stephen ...
7 篇 rosenfeld azriel
7 篇 huang thomas s.
7 篇 hall ernest l.
6 篇 mitchell o.r.
6 篇 hall e.l.
6 篇 jain anil k.
6 篇 schunck brian g.
6 篇 toussaint godfri...
6 篇 sklansky j.
5 篇 peleg shmuel
5 篇 davis larry s.
5 篇 chien y.t.
5 篇 shapiro linda g.
5 篇 srihari sargur n...
5 篇 oosterlinck a.

语言

470 篇 英文
254 篇 其他

检索条件"任意字段=IEEE Comput Soc Conf on Pattern Recognition and Image Process, Proc"

共 724 条记录，以下是221-230 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：

Edge reinforcement using parametrized relaxation labeling

Edge reinforcement using parametrized relaxation labeling

引用

proceedings CVPR '89: ieee computer society conference on computer Vision and pattern recognition

作者： Duncan, James S. Birkholzer, Thomas Yale Univ New Haven CT USA

ISBN: (纸本)081861952x

The problem of reinforcing local evidence of edges while suppressing unwanted information in noisy images is considered using a form of relaxation labeling. The methodology is based on parameterizing a continuous set of edge orientation labels using a single vector. A sigmoidal thresholding function similar to that used in artificial neural networks to bias neighborhood-influence and insure convergence to meaningful stable states is also utilized. A global optimization function is defined, and a decentralized parallel algorithm is derived that uses a steepest-gradient-descent approach to arrive at the optimal point on the functional surface, corresponding to desirable edge-reinforced and noise-suppressed labelings. In addition, a modification to the functional is presented which incorporates a thinning operation to insure that each edge is marked by only a single-pixel-wide response. Results from several image data sets indicate that the algorithm performs as well as or better than other relaxation labeling methods, and with improved computational efficiency.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Quantization error in spatial sampling: comparison between square and hexagonal pixels

Quantization error in spatial sampling: comparison between s...

引用

proceedings CVPR '89: ieee computer society conference on computer Vision and pattern recognition

作者： Kamgar-Parsi, Behzad Kamgar-Parsi, Behrooz Sander, William A. Univ of Maryland College Park MD USA

ISBN: (纸本)081861952x

Square and hexagonal spatial samplings, because of their processing ease, are used most widely in image and signal processing. The authors developed mathematical tools for estimating quantization error in hexagonal sensory configurations. These include analytic expressions for the average error and the error distribution of a function of an arbitrarily large number of hexagonally quantized variables. The two quantities (the average error and the error distribution) are essential in assessing the reliability of a given algorithm. The corresponding expressions for square spatial sampling are presented for comparison;they can be used to determine which sampling technique would result in less quantization error for a particular algorithm. Such a comparison is important due to the paramount role that quantization error plays in computational approaches to computer vision. Some general observations in regard to the relative accuracy of hexagonal vs. square quantization are also presented.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Model-based two-dimensional industrial part recognition

Model-based two-dimensional industrial part recognition

引用

Eighth Annual International Phoenix conference on computers and Communications - 1989 conference proceedings

作者： Kung, Fu K. Mehrotra, Rajiv Grosky, William I. Univ of South Florida Tampa FL USA

Consideration is given to the problem of two-dimensional industrial part recognition. A novel data-driven technique for part recognition is proposed. This technique models an object or a scene as a composition of several meaningful components. A component of the unanalyzed portion of the scene is identified using a component-index. The objects that contain the identified component are hypothesized to be present in the scene. A given hypothesis is verified by matching the transformed boundary of the hypothesized object against the scene. The performance of the proposed technique is demonstrated by several examples.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

NEW ALGORITHMS FOR pattern-recognition OF ATRIAL-FIBRILLATION AND SINUS RHYTHM

NEW ALGORITHMS FOR PATTERN-RECOGNITION OF ATRIAL-FIBRILLATIO...

引用

1989 ANNUAL INTERNATIONAL conf OF THE ieee ENGINEERING IN MEDICINE AND BIOLOGY soc : imageS OF THE TWENTY-FIRST CENTURY

作者： SEIREG, RH MARVASTI, FA Illinois Inst of Technol Electr & Comput Eng Dep Chicago IL USA

Various zero-crossing techniques are used to distinguish between sinus rhythm and atrial fibrillation of different patients. The methods are threshold crossings, sine-wave crossings, threshold crossings of the derivative of the signal, and fast Fourier transform (FFT) analysis. The comparison shows that the sine-wave crossing method is best, because there is no need to normalize or to differentiate the signal (differentiation as a means to remove the DC component is a noisy process).Also, the algorithm is in real time (unlike the FFT procedure) and simple to implement.

关键词： Biomedical Engineering

来源：评论

学校读者我要写书评

暂无评论

Region-based optical flow estimation

Region-based optical flow estimation

引用

proceedings CVPR '89: ieee computer society conference on computer Vision and pattern recognition

作者： Fuh, Chiou-Shann Maragos, Petros Harvard Univ Cambridge MA USA

ISBN: (纸本)081861952x

A correspondence method is developed for determining optical flow where the primitive motion tokens to be matched between consecutive time frames are regions. The computation of optical flow consists of three stages: region extraction, region matching, and optical flow smoothing. For region extraction, in each image frame the regions are extracted either from the sign of the bandpass operator or by thresholding the output of morphological image transformations for peak/valley detection. For region matching, a general correspondence approach is applied to region tokens by using an affinity measure based on region features. Optical flow is then identified as the spatial vector displacements among centroids of corresponding regions. The computation is completed by smoothing the initial optical flow, where the sparse velocity data are either a smoothed with a vector median filter or interpolated to obtain dense velocity estimates by using a motion-coherence regularization. The proposed region-based method for optical flow is simple, computationally efficient, and (as experiments on real images indicate) more robust than iterative gradient methods, especially for medium-range motion.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Registration of multiple overlapping range images: scenes without distinctive features

Registration of multiple overlapping range images: scenes wi...

引用

proceedings CVPR '89: ieee computer society conference on computer Vision and pattern recognition

作者： Kamgar-Parsi, Behrooz Jones, Jeffrey L. Rosenfeld, Azriel Univ of Maryland College Park MD USA

ISBN: (纸本)081861952x

A scheme is developed to match range images in an environment where distinctive features are scarce. When each image overlaps with several other images, the match must also be performed at the global level. This is particularly challenging, because of the possibility of bending and compression in range images (i.e., the relative position of data points on the image reference surface may be inaccurate). The primitives used for local matching contours of constant range which are extracted from data are represented by means of a modified chain-code method. All best matches of pairs of contours are considered tentative until their geometrical implications are evaluated and a consistent majority has emerged. To do global matching a cost function is constructed and minimized. Terms contributing to the cost include violation of local matches as well as compression and bending in range images. The present global scheme is valid for any set of multiple overlapping range images, they contain distinctive features or not. This scheme has been used to map the floor of the ocean, where the range data are obtained by a multibeam echo-sounder system.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Knowledge-guided left ventricular boundary detection

Knowledge-guided left ventricular boundary detection

引用

proceedings CVPR '89: ieee computer society conference on computer Vision and pattern recognition

作者： Tehrani, Saeid Weymouth, Terry E. Mancini, G.B.John Univ of Michigan Ann Arbor MI USA

ISBN: (纸本)081861952x

Interpolation of X-ray motion pictures of the heart (cineventiculograms of the left ventricle) is complicated by the low contrast of the images and the elastic motion of the heart. Here, the problem of placing the heart boundary in each frame of the motion sequence is described by a framework for the application of knowledge in the form of diagnostically relevant models of the heart in motion. A blackboard architecture is utilized as a basis for the image interpretation. In this architecture, local features such as edges are grouped to build a complete description of the moving heart;the knowledge is organized in a hierarchy with knowledge sources (KSs) operating on different levels of the hierarchy and opportunistic problem-solving techniques are used to control the order of activation of both data-directed and goal-driven sources. A series of experiments show how the extracted edge points are linked to form boundary fragments, how these overlapping fragments are collected and combined to form a larger fragment with higher confidence, how the models of the left ventricle boundaries are derived, how these fragments are matched against the models, and how the boundary movements are tracked in the image sequence.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Optimal motion and structure estimation

Optimal motion and structure estimation

引用

proceedings CVPR '89: ieee computer society conference on computer Vision and pattern recognition

作者： Weng, Juyang Ahuja, Narendra Huang, Thomas S. Univ of Illinois Urbana IL USA

ISBN: (纸本)081861952x

The problem of estimating motion and structure of a rigid scene from two perspective monocular views is studied. The optimization approach presented is motivated by the following observations of linear algorithms: (1) for certain types of motion, even pixel-level perturbations (such as digitization noise) may override the information characterized by epipolar constraint;(2) existing linear algorithms do not use the constraints in the essential parameter matrix E in solving for this matrix. The authors present approaches to estimating errors in the optimal solutions, investigate the theoretical lower bounds on the errors in the solutions and compare them with actual errors, and analyze two types of algorithms of optimization: batch and sequential. The analysis and experiments show that, in general, a batch technique performs better than a sequential technique for any nonlinear problems. A recursive batch processing technique is proposed for nonlinear problems that require recursive estimation.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Integrated modelling of thermal and visual image generation

Integrated modelling of thermal and visual image generation

引用

proceedings CVPR '89: ieee computer society conference on computer Vision and pattern recognition

作者： Oh, Chanhee Nandhakumar, N. Aggarwal, J.K. Univ of Texas Austin TX USA

ISBN: (纸本)081861952x

A unified approach for modeling objects which are imaged by thermal (infrared) and visual cameras is presented. The model supports the generation of both infrared (8-μm-12-μm wavelength) images and monochrome visual images under different viewing and ambient-scene conditions. A modified octree data structure is used for object modeling. The octree serves two different purposes: (1) surface information encoded in boundary nodes and efficient tree-traversal algorithms facilitate the generation of monochrome visual images;and (2) the compact volumetric representation facilitates simulation of heat flow in the object which gives rise to surface temperature variation, which in turn is used to synthesize the thermal image. The detailed object model allows for more accurate prediction of thermal and visual images of objects. It also predicts the values of discriminatory features used in classification. The model developed is designed to be used in a model-based vision system which uses a hypothesize-and-verify strategy to interpret thermal and visual images of scenes. Several blocks-world examples are presented to show typical images generated by the approach.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

Generalized neighborhoods: a new approach to complex parameter feature extraction

Generalized neighborhoods: a new approach to complex paramet...

引用

proceedings CVPR '89: ieee computer society conference on computer Vision and pattern recognition

作者： Califano, A. Bolle, R.M. Taylor, R.W. IBM T.J. Watson Research Cent Yorktown Heights NY USA

ISBN: (纸本)081861952x

A generalized neighborhood concept is presented which extends the usual techniques for feature extraction using parameter transforms. Generalized neighborhoods allow operators to use the joint information contained in distant portions of the same feature;i.e., to utilize the long-distance correlation present in the image. The generalized neighborhood techniques, by correlating local information over different portions of the image, produce up to two orders of magnitude improvement in accuracy over conventional techniques. Unfortunately, the response also becomes more complicated;false features may be detected due to a peculiar form of correlated noise. A general framework, motivated by connectionist networks, is presented which eliminates this behavior by introducing competitive processes in the parameter spaces. A novel approach to the generation of lateral inhibition links in the networks is proposed which is consistent with generalized neighborhoods. Experiments are provided that show results on range data. Complex surfaces and 3-D surface-intersection curves are reconstructed from the data.

关键词： image processing

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73页 << < 19 20 21 22 23 24 25 26 27 28 > >>

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：