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

1,444 篇 会议
30 篇 期刊文献
16 册 图书

馆藏范围

1,490 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,167 篇 工学
- 933 篇 计算机科学与技术...
- 396 篇 软件工程
- 164 篇 电气工程
- 137 篇 光学工程
- 121 篇 信息与通信工程
- 96 篇 生物医学工程（可授...
- 91 篇 控制科学与工程
- 90 篇 生物工程
- 70 篇 机械工程
- 69 篇 仪器科学与技术
- 44 篇 电子科学与技术（可...
- 35 篇 化学工程与技术
- 32 篇 材料科学与工程（可...
- 15 篇 土木工程
- 14 篇 力学（可授工学、理...
- 13 篇 建筑学
394 篇 理学
- 220 篇 数学
- 181 篇 物理学
- 103 篇 生物学
- 74 篇 统计学（可授理学、...
- 37 篇 化学
- 13 篇 系统科学
330 篇 医学
- 323 篇 临床医学
- 33 篇 基础医学(可授医学...
- 25 篇 药学(可授医学、理...
107 篇 管理学
- 69 篇 图书情报与档案管...
- 42 篇 管理科学与工程(可...
37 篇 艺术学
- 37 篇 设计学（可授艺术学...
15 篇 农学
- 12 篇 作物学
10 篇 法学
- 10 篇 社会学
5 篇 教育学
3 篇 经济学
2 篇 军事学

主题

142 篇 pattern recognit...
110 篇 image segmentati...
94 篇 feature extracti...
83 篇 image processing
63 篇 image analysis
56 篇 image color anal...
41 篇 principal compon...
40 篇 face recognition
38 篇 image recognitio...
31 篇 support vector m...
30 篇 deep learning
30 篇 local binary pat...
30 篇 image reconstruc...
29 篇 computer vision
29 篇 shape
27 篇 image classifica...
26 篇 image enhancemen...
26 篇 pattern matching
25 篇 training
24 篇 neural networks

机构

7 篇 institute of aut...
5 篇 inesc tec porto
5 篇 univ porto fac e...
4 篇 guangdong univer...
4 篇 univ porto fac c...
4 篇 south china univ...
4 篇 microsoft resear...
4 篇 king fahd univer...
4 篇 shanghai jiao to...
3 篇 córdoba
3 篇 comp vis ctr bar...
3 篇 department of co...
3 篇 tarbiat modares ...
3 篇 univ porto fac e...
3 篇 inst res fundame...
3 篇 chitkara univers...
3 篇 universidade de ...
3 篇 harvard univ sch...
3 篇 ryerson univ dep...
3 篇 univ alicante ui...

作者

11 篇 cardoso jaime s.
9 篇 vidal enrique
8 篇 calvo-zaragoza j...
8 篇 oliveira helder ...
6 篇 lee seong-whan
6 篇 suen c.y.
5 篇 casacuberta fran...
5 篇 marques jorge s.
5 篇 pina pedro
4 篇 shengli xie
4 篇 pietikainen matt...
4 篇 bioucas-dias jos...
4 篇 dongbin zhao
4 篇 c.y. suen
4 篇 forero manuel g.
4 篇 yuanqing li
4 篇 el-sayed m. el-a...
4 篇 derong liu
4 篇 weickert joachim
4 篇 singh s

语言

1,454 篇 英文
33 篇 其他
6 篇 中文
1 篇 日文

检索条件"任意字段=3rd Iberian Conference on Pattern Recognition and Image Analysis"

共 1490 条记录，以下是1381-1390 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：

Nonlinear shape restoration of distorted images with Coons transformation

Nonlinear shape restoration of distorted images with Coons t...

引用

International conference on Document analysis and recognition

作者： Seong-Whan Lee Eun-Soon Kim Y.Y. Tang Department of Computer Science Korea University Seoul South Korea R & D Center POSDATA Company Limited Seoul South Korea CENPARMI Concordia University Montreal QUE Canada

image shape restoration based on mathematical transformation is a successful approach to nonlinear distortions in computer vision, robot vision and pattern recognition. The key of this process is to find the distortion function and its inverse function. Usually, the distortion function is unknown or unclear. Even in the case where the function is known, it remains difficult to compute or estimate the parameters necessary for the restoration. To overcome this problem, Coons transformation utilizing boundary functions for the distorted images have been used to approximate the exact distortion function. The boundary functions are calculated using B-spline curve interpolation which is coincided with the necessary condition of major elements that constitute a Coons transformation.

关键词： Shape image restoration Nonlinear distortion Computer vision Robot vision systems pattern recognition Predistortion Parameter estimation Spline Interpolation

来源：评论

学校读者我要写书评

暂无评论

A new system for reading handwritten zip codes

A new system for reading handwritten zip codes

引用

International conference on Document analysis and recognition

作者： N.W. Strathy C.Y. Suen Centre for Pattern Recognition and Machine Intelligence Concordia University Montreal QUE Canada

A new method of reading the handwritten zip codes in the U.S. Postal Services CD-ROM database is presented. Zip code images are binarized, segmented and recognised. A recognition driven method for splitting multiple connected digits has been developed; for grouping together of broken digits, the system targets components with near-touching stroke tips, 5-hats, and 4-Ls. The digit recogniser is a majority vote combination of 3 neural networks with a zero rejection performance of 96.53% on the 2711 imperfectly segmented digits in the cedarbs test set. With digit splitting capability disabled, the system performance on the 930 whole zip codes of the test set is 61.0% correct with no errors when up to two rejected symbol positions are allowed. With digit splitting enabled the performance rises to 66.3%.

关键词： Postal services CD-ROMs image databases image segmentation image recognition Target recognition Voting Neural networks Testing System performance

来源：评论

学校读者我要写书评

暂无评论

Integrated segmentation and recognition of connected handwritten characters with recurrent neural network

Integrated segmentation and recognition of connected handwri...

引用

International conference on Document analysis and recognition

作者： Seong-Whan Lee Eung-Jae Lee Department of Computer Science Korea University Seoul South Korea Department of Computer Science Chungbuk National University Cheonghu Chungbuk South Korea

ISBN: (纸本)0818671289

In this paper, we propose an integrated segmentation and recognition method for recognizing connected handwritten characters with recurrent neural network. It has been developed to both integrate segmentation and recognition within a single recurrent neural network and recognize connected handwritten characters using the spatial dependencies in the images of connected handwritten characters. In order to verify the performance of the proposed method, experiments with the NIST database have been carried out and the performance of the proposed method has been compared with those of the previous integrated segmentation and recognition methods.

关键词： Character recognition Handwriting recognition Recurrent neural networks image recognition image segmentation Neural networks Data preprocessing pattern recognition Computer science NIST

来源：评论

学校读者我要写书评

暂无评论

A personal handwritten Chinese character recognition algorithm based on the generalized Hough transform

A personal handwritten Chinese character recognition algorit...

引用

International conference on Document analysis and recognition

作者： Ming-Jing Li Ru-Wei Dai Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)0818671289

The generalized Hough transform is a useful method for detecting arbitrary 2-dimensional shapes. Based on the consideration that handwritten Chinese characters are complex 2-dimensional shapes, we make an attempt to recognize them by using the generalized Hough transform. Features extracted from the parameter space are used to calculate the similarity measure between two character images. The algorithm is implemented in a look-up-table scheme which can be extended to other applications of pattern recognition. Experimental results on personal (writer-dependent) handwritten Chinese character recognition show that this algorithm is suitable for the pre-classification of personal handwritten Chinese character recognition.

关键词： Character recognition Shape Handwriting recognition Voting pattern recognition Feature extraction Application software Automation Analytical models image processing

来源：评论

学校读者我要写书评

暂无评论

A background based adaptive page segmentation algorithm

A background based adaptive page segmentation algorithm

引用

International conference on Document analysis and recognition

作者： N. Normand C. Viard-Gaudin Laboratoire Systèmes Electroniques et Informatiques IRESTE Nantes France

A novel page segmentation algorithm is provided in this paper. Based on the extraction of the background, it offers the benefit of being adaptive to the context of the document and to be insensitive to the orientation of the text blocks. It involves a two-dimensional isotropic structuring element used to characterized the white streams. This element is a disk approximated by a regular octagon which can be recursively generated. Another advantage of the proposed method is that a hierarchical segmentation can be derived from the image built upon the octagonal pattern. This tree allows to perform an isotropic multi-scale smearing, which leads to a physical segmentation. The algorithms are based on an input-time tracing principle and use a single scan of the image, they are very well suited to a real-time implementation.

关键词： Smoothing methods image segmentation Shape image coding Streaming media Character generation Real time systems Optical character recognition software Optical filters Character recognition

来源：评论

学校读者我要写书评

暂无评论

Modelling polyfont printed characters with HMMs and a shift invariant Hamming distance

Modelling polyfont printed characters with HMMs and a shift ...

引用

International conference on Document analysis and recognition

作者： A.J. Elms J. Illingworth Department of Electronic and Electrical Engineering University of Surrey Guildford UK

Rumours of the death of the problem of machine-printed text recognition have been greatly exaggerated. Reported results can be good enough to lead one to believe that this is a "solved problem". Closer analysis reveals test data that is often limited in its range of fonts and point sizes. Worse still, results are commonly quoted for noise-free images, ignoring the problems of recognising "real" documents such as faxes. Various methods have been proposed for modelling characters with Hidden Markov Models. The authors, amongst others, have suggested representing a character by analysing the pixel pattern in columns of its image, and linking sequential column patterns together with a HMM. In this paper we propose a method of quantising the patterns by means of a Shift Invariant Hamming Distance. A full experimental evaluation (45 fonts, 5 point sizes) in typical noise results in a recognition accuracy of 99% in the top-3 choices, and 94% top-choice for the best font. The method has a significant advantage in recognising noisy word images, due to classification being achieved without a prior segmentation of the word into characters.

关键词： Hidden Markov models image recognition Text recognition Data analysis Testing image analysis pattern analysis Pixel Joining processes Hamming distance

来源：评论

学校读者我要写书评

暂无评论

A B-spline surface interpolation technique for reconstructing 3D objects from serial arbitrary shaped planar contours 3rd

引用

3rd International Computer Science conference (ICSC 95) - image analysis Applications and Computer Graphics

作者： Xu, MH Tang, ZS Deng, JH CAD Center Dept. of Computer Science and Technology Tsinghua University Beijing 100084 China

ISBN: (纸本)3540606971

A new method is presented to the B-spline surface presentation of an object defined by a set of parallel slices. For the application of B-spline inversion procedure, the methods about the data points generated are mainly introduced. The mesh of the data points is generated from interpolation curves of the vertex of the contour, which enable the interpolating surface to approximate the original object. It has the advantage that the reconstructed surface keep the smoothness in total longitudinal direction. The proposed method is also capable of handling the branching problem. Several experimental results corroborate the theory. The results show the image with high fidelity and the rendering speed are satisfactory and pleasing.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

A new approach to document analysis based on modified fractal signature

A new approach to document analysis based on modified fracta...

引用

International conference on Document analysis and recognition

作者： Y.Y. Tang Hong Ma Xiaogang Mao Dan Liu C.Y. Suen Center for Pattern Recognition and Machine Intelligence Concordia University Montreal West QUE Canada Department of Mathematics Sichuan University Chengdu Sichuan China

This paper presents a new approach to document analysis. The proposed approach is based on modified fractal signature. Instead of the time-consuming traditional approaches (top-down and bottom-up approaches) where iterative operations are necessary to break a document into blocks to extract its geometric (layout) structure, this new approach can divide a document into blocks in only one step. This approach can be used to process documents with high geometrical complexity. Experiments have been conducted to prove the proposed new approach for document processing.

关键词： Text analysis Fractals pattern recognition Iterative methods Size measurement image coding Equations Upper bound Machine intelligence Biological information theory

来源：评论

学校读者我要写书评

暂无评论

The deformed cube: A visualization technique for 3D velocity vector field 3rd

引用

3rd International Computer Science conference (ICSC 95) - image analysis Applications and Computer Graphics

作者： Liang, XD Li, B Liu, SQ CAD Lab Institute of Computing Technology Academia Sinica Beijing China

ISBN: (纸本)3540606971

This paper presents a visualization method called the deformed cube for visualizing 3D velocity vector field. Based on the decomposition of the tensor which describes the changes of the velocity, it provides a technique for visualizing local how. A deformed cube,a cube transformed by a tensor in a local coordinate frame, shows the local stretch, shear and rigid body rotation of the local flow corresponding to the decomposed component of the tenser. User can interactively view the local deformation or any component of the changes. The animation of the deformed cube moving along a streamline achieves a more global impression of the flow field. This method is intended as a complement to global visualisation methods.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Off-line recognition of Korean scripts using distance matching and neural network classifiers

Off-line recognition of Korean scripts using distance matchi...

引用

International conference on Document analysis and recognition

作者： Soo Hyung Kim Jeong-In Doh S W Group Multimedia Center Samsung Electronics Company Limited Yongin si Kyunggi South Korea

ISBN: (纸本)0818671289

An off-line recognition engine is proposed for handwritten Korean characters based on a distance matching and the neural network technique. The distance matching selects a set of several candidates from the large set of character classes, and the neural network performs a detailed classification on the candidates. As an approach for combining the two methodologies, a clustering method based on sample distributions has been devised. recognition accuracy of the engine on a public database, PE92, is 84.1%. About four character patterns can be processed in a second on PC.

关键词： Neural networks image segmentation Engines Character recognition pattern recognition Handwriting recognition Pixel Electronic mail Clustering methods Databases

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149页 << < 135 136 137 138 139 140 141 142 143 144 > >>

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：