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

863 篇 会议
353 篇 期刊文献
27 篇 学位论文
19 册 图书
1 篇 资讯

馆藏范围

1,263 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

835 篇 工学
- 619 篇 计算机科学与技术...
- 306 篇 软件工程
- 205 篇 电气工程
- 94 篇 信息与通信工程
- 68 篇 光学工程
- 54 篇 电子科学与技术（可...
- 49 篇 控制科学与工程
- 38 篇 生物医学工程（可授...
- 36 篇 仪器科学与技术
- 32 篇 机械工程
- 32 篇 测绘科学与技术
- 26 篇 生物工程
- 17 篇 环境科学与工程（可...
- 15 篇 材料科学与工程（可...
- 13 篇 化学工程与技术
- 12 篇 土木工程
327 篇 理学
- 163 篇 物理学
- 117 篇 数学
- 44 篇 生物学
- 24 篇 地球物理学
- 22 篇 统计学（可授理学、...
- 18 篇 化学
- 16 篇 天文学
- 12 篇 系统科学
115 篇 医学
- 89 篇 临床医学
- 28 篇 基础医学(可授医学...
- 17 篇 特种医学
68 篇 管理学
- 55 篇 管理科学与工程(可...
- 15 篇 工商管理
- 13 篇 图书情报与档案管...
11 篇 农学
4 篇 经济学
2 篇 教育学
2 篇 艺术学
1 篇 法学
1 篇 文学

主题

145 篇 image processing
99 篇 parallel process...
49 篇 image segmentati...
49 篇 feature extracti...
44 篇 image reconstruc...
41 篇 distributed comp...
35 篇 image edge detec...
35 篇 computational mo...
34 篇 deep learning
34 篇 computer archite...
34 篇 computer vision
34 篇 training
31 篇 concurrent compu...
30 篇 image analysis
27 篇 neural networks
26 篇 hardware
25 篇 graphics process...
24 篇 algorithm design...
24 篇 parallel computi...
23 篇 graphics process...

机构

7 篇 national laborat...
6 篇 natl univ def te...
6 篇 natl univ def te...
5 篇 college of compu...
5 篇 natl univ def te...
5 篇 nanjing univ sci...
4 篇 natl univ def te...
4 篇 univ chinese aca...
3 篇 school of comput...
3 篇 hong kong polyte...
3 篇 king saud univer...
3 篇 natl univ def te...
3 篇 department of co...
3 篇 school of comput...
3 篇 school of cyber ...
3 篇 university of fl...
3 篇 sensetime res pe...
3 篇 science and tech...
3 篇 univ naples fede...
3 篇 univ stuttgart i...

作者

14 篇 dou yong
12 篇 qiao peng
8 篇 zhigang luo
8 篇 naiyang guan
7 篇 xu kele
6 篇 yong dou
5 篇 luo zhigang
5 篇 xiang zhang
5 篇 li bo
5 篇 shi hc
5 篇 niu xin
5 篇 zhang xiang
5 篇 wang huaimin
5 篇 zhang yi
5 篇 dacheng tao
5 篇 li hz
4 篇 camps-valls gust...
4 篇 peng qiao
4 篇 plaza antonio
4 篇 huang xuhui

语言

1,182 篇 英文
44 篇 中文
36 篇 其他
1 篇 俄文

检索条件"任意字段=Parallel and Distributed Methods for Image Processing II"

共 1263 条记录，以下是1221-1230 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：

A parallel distributed algorithm for feature extraction and disparity analysis of computer images 2

A parallel distributed algorithm for feature extraction and ...

引用

2nd IEEE Symposium on parallel and distributed processing, SPDP 1990

作者： Mousavi, M.S. Schalkoff, R.J. AT and T Bell Laboratories MiddletownNJ07748 United States Department of Electrical and Computer Engineering Clemson University ClemsonSC29631 United States

ISBN: (纸本)0818620870

A parallel distributed processing method for extracting features in stereo images is presented. The algorithm is edge-based and employs the epipolar constraint. First edges are detected in a multilayered network using two methods of locating the magnitude of directional first derivatives and the zero-crossing of second derivatives of smoothed images. The combined edge detection process helps to eliminate 'phantom' edges. Then features that are likely to be detectable in both images are selected. These features are edge intervals and edge orientation, that is, the intersection of image edges with the epipolar line and the corresponding slope of the edges at those points. The feature extraction process is implemented in a two-layered parallel distributed processing model. The first layer provides edge interval representations. The second layer computes a similarity of measure for each pair of primitive matches which are then forwarded to the second stage of the algorithm. The purpose of the second stage is to turn the difficult pixel correspondence problem into a constraint satisfaction problem by imposing relational constraints. This constraint satisfaction is then solved using a neural network. The results of computer simulations are presented to demonstrate the effectiveness of the approach. © 1990 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Joint International Conference on Vector and parallel processing, CONPAR 1990

引用

Joint International Conference on Vector and parallel processing, CONPAR 1990

ISBN: (纸本)9783540530657

The proceedings contain 82 papers. The special focus in this conference is on Vector and parallel processing. The topics include: A decoupled data-driven architecture with vectors and macro actors;a novel paradigm of parallel computation and its use to implement simple high performance hardware;a bus-connected multiprocessor for a rete-based production system;a model for performance prediction of message passing multiprocessors achieving concurrency by domain decomposition;workloads, observables, benchmarks and instrumentation;a method for performance prediction of parallel programs;sparse matrix algorithms for SUPRENUM;parallel givens factorization on a shared memory multiprocessor;study of a parallel lnference machine for paraliei execution of logic programs;parallel lmplementation of logic languages;prolog implementations on parallel computers;performance evaluation of parallel programs in parallel and distributed systems;the ELAN performance analysis environment;monitoring and debugging transputer-networks with NETMON-ii;an adaptive blocking strategy for matrix factorizations;factorizations of band matrices using level 3 BLAS;on the computation of breeding values;code parallelization for the LGDG large-grain dataflow computation;development of portable parallel programs with large-grain data flow 2;a latency tolerant code generation algorithm for a coarse grain dataflow machine;cedar fortran and its compiler;optimizing communication in superb;a design of performance-optimized control-based synchronization;interprocess analysis and optimization in the equational language compiler;transputer based distributed cartograptic lmage processing;parallel implementation of the convolution method in image reconstruction;analysis and design of circuit switching interconnection networks using 4x4 nodes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel algorithms for determining k-width- connectivity in binary images 2

Parallel algorithms for determining k-width- connectivity in...

引用

2nd IEEE Symposium on parallel and distributed processing, SPDP 1990

作者： Dehnc, Frank Hambrusch, Susanne E. School of Computer Science Carleton University OttawaK1S 5B6 Canada Department of Computer Sciences Purdue University West LafayetteIN47907 United States

ISBN: (纸本)0818620870

In this paper we consider a new form of connectivity in binary images, called k-width-connectivity. Two pixels a and 6 of value are in the same k-width- component if and only if there exists a path of width k such that a is one of the k start pixels and b is one of the k end pixels of this path. We present characterizations of the k-width-components and show how to determine the k-width-components of an n x n image in O(n) and 0(log2 n) time on a mesh of processors and hypercube, respectively, when the image is stored with one pixel per processor. Our methods use a reduction of the k-width-connectivity problem to the 1-width-connectivity problem. A distributed, space-efficient encoding of the k-width-components of small size allows us represent the solution using O(l) registers per processor. Our hypercube algorithm also implies an algorithm for the shuffle-exchange network. © 1990 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Applications of smart neuromorphic focal planes

Applications of smart neuromorphic focal planes

引用

Materials, Devices, Techniques, and Applications for Z-Plane Focal Plane Array Technology ii

作者： Forsell Jr., Robert Thornbrugh, Allison Preyer, Carl Martin Marietta Space Systems Denver United States

Space-based sensors currently transmit large amounts of raw data to their receiving stations, forcing large bandwidths to be used and large data archives maintained. One possible solution to this data management problem is the use of more intelligent processing onboard the spacecraft. Neural networks are proposed as a trainable, mutable means of achieving sensor signal processing, sorting, and classification before infrared (IR) focal plane data leaves the cryogenic seal. Two questions arise: (1) can a neural network of appropriate size learn a sensor processing classification problem, and (2) will there be devices to implement that neural network as a smart focal plane. In this paper we concentrate on the first issue and show successful results in simulation for a massively parallel, distributed neural network solution to the closely spaced object (CSO) recognition problem, using a defocused IR sensor model with noise, and an uncooperative object or CSO at large distance. The back-propagation learning method is used to train the network. Architectural issues regarding the construction of a prototype neuromorphic focal plane device are also discussed.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

CONSTRUCTING OCTREES FROM MULTIPLE VIEWS - A parallel IMPLEMENTATION

CONSTRUCTING OCTREES FROM MULTIPLE VIEWS - A PARALLEL IMPLEM...

引用

CONF ON SENSOR FUSION 2 : HUMAN AND MACHINE STRATEGIES

作者： CHIEN, CH Carnegie-Mellon Univ United States

ISBN: (纸本)0819402370

Inferring 3D information from 2D images has been one of the major concerns of researchers in computer vision community. A single view of an object usually conveys insufficient 3D information about the object. The integration of these partial information from multiple views, however, very often yields fairly good approximation of the 3D structure of the observed object. In the past, we have developed efficient (sequential) algorithms for constructing the octrees of 3D objects from their multiple views. In this paper, we present the parallel implementation of these sequential algorithms using PARADIGM, a mechanism for composing spatial-oriented distributed programs. Alternative strategies for each phase of octree generation are discussed in the context of data partitioning and task allocation. We have implemented our proposed algorithms on Nectar, a fiber-optic based network computer currently being developed at Carnegie Mellon. It is expected that the results and experiences obtained from this research work will be beneficial to future research into real-time multi-sensor fusion.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

A parallel distributed algorithm for feature extraction and disparity analysis of computer images

A parallel distributed algorithm for feature extraction and ...

引用

International Symposium on parallel and distributed processing (IPDPS)

作者： M.S. Mousavi R.J. Schalkoff AT and T Bell Laboratories Inc. Middletown NJ USA Department of Electrical & Computer Engineering Clemson University Clemson SC USA

关键词： distributed algorithms Feature extraction image analysis Algorithm design and analysis Concurrent computing distributed computing image edge detection Stereo vision Neural networks distributed processing

来源：评论

学校读者我要写书评

暂无评论

parallel algorithms for determining k-width- connectivity in binary images

Parallel algorithms for determining k-width- connectivity in...

引用

International Symposium on parallel and distributed processing (IPDPS)

作者： F. Dehne S.E. Hambrusch School of Computer Science Carleton University Ottawa Canada Department of Computer Sciences Purdue University West Lafayette IN USA

The authors consider a new form of connectivity in binary images, called k-width-connectivity. Two pixels a and b of value '1' are in the same k-width-component if and only if there exists a path of width k such that a is one of the k start pixels and b is one of the k end pixels of this path. The authors present characterisations of the k-width-components and show how to determine the k-width-components of an n*n image in O(n) and O(log/sup 2/ n) time on a mesh of processors and hypercube, respectively, when the image is stored with one pixel per processor. The methods use a reduction of the k-width-connectivity problem to the 1-width-connectivity problem. A distributed, space-efficient encoding of the k-width-components of small size allows the solution to be represented using O(l) registers per processor. The hypercube algorithm also implies an algorithm for the shuffle-exchange network.< >

关键词： parallel algorithms Pixel Hypercubes Computer science Concurrent computing Encoding Registers Fault tolerance Councils Contracts

来源：评论

学校读者我要写书评

暂无评论

High Speed Computing ii

High Speed Computing II

引用

High Speed Computing ii 1989

The proceedings contain 29 papers. The topics discussed include: the detection and tracking of multiple targets with velocity filters;algorithm for subpixel target detection using cellular automata;a hybrid SIMD/MIMD architecture for image understanding;parallel recirculating pipeline for signal and image processing;macropipelined multicomputer systems for image analysis;the arithmetic Fourier transform calculation using fiber optical parallel processors;the arithmetic Fourier transform calculation using fiber optical parallel processors;state space methods for DOA estimation;and experience using the truncated Newton method for large scale optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A programming environment for distributed realtime applications

A programming environment for distributed realtime applicati...

引用

Annual Hawaii International Conference on System Sciences (HICSS)

作者： P. Holleczek C. Andres Computing Center-Communication Group University of Erlangen Nuremberg Erlangen Germany

An environment based on a specification technique, which provides methods for communication and synchronization between parallel processes, is described. The mainly graphical specification technique can be used for parallel processing, message passing, synchronous and asynchronous communication, and time-out conditions. The specification technique is supported by a number of tools. The programming technique allows for parallel processing and common objects.< >

关键词： Programming environments parallel processing Software tools Control systems Operating systems Computerized monitoring Application software distributed computing Message passing Asynchronous communication

来源：评论

学校读者我要写书评

暂无评论

Generalized vector quantization with optimal connection of elements

Generalized vector quantization with optimal connection of e...

引用

IEEE 1988 International Symposium on Information Theory - Abstracts of papers

作者： Matsuyama, Yasuo Ibaraki Univ Hitachi Jpn

Summary form only given. Generalized algorithms for vector quantization are presented and their convergence to empirical data is proved. The generalized vector quantization allows adjusted variable dimensional vectors covering variable subregions of source data. Therefore, this class of algorithms is called variable region vector quantization. Algorithm I is the generalization of the GLA into the variable region case. This is called full-gain variable region vector quantization. Algorithm ii, on the other hand, is the variable region generalization of the gain-shape type. The formation of each variable subregion is due to the connection or grouping of elements so that the resulting set of variable dimensional super-vectors has the minimum distortion to a codebook. Algorithm iiI considers encoding and decoding for data compression. Algorithm IV gives the suboptimal minimization for the alleviation of computational load. Examples of region optimization on speech and images are given. methods presented here are applicable and matches to various pattern handling such as neural algorithms of parallel distributed processing. Results obtained by fine-grain parallel computation with a guarded Horn clauses front-end is also given.

关键词： Signal 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127页 << < 118 119 120 121 122 123 124 125 126 127 > >>

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：