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

59 篇 会议
17 篇 期刊文献

馆藏范围

76 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

42 篇 工学
- 26 篇 计算机科学与技术...
- 25 篇 软件工程
- 10 篇 机械工程
- 5 篇 电子科学与技术（可...
- 5 篇 信息与通信工程
- 3 篇 控制科学与工程
- 3 篇 生物工程
- 2 篇 化学工程与技术
- 2 篇 生物医学工程（可授...
- 1 篇 光学工程
- 1 篇 仪器科学与技术
- 1 篇 电气工程
- 1 篇 石油与天然气工程
- 1 篇 交通运输工程
19 篇 理学
- 12 篇 数学
- 6 篇 物理学
- 4 篇 生物学
- 2 篇 化学
- 1 篇 系统科学
7 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 艺术学
- 1 篇 设计学（可授艺术学...

主题

23 篇 pattern recognit...
17 篇 machine intellig...
17 篇 character recogn...
10 篇 image segmentati...
9 篇 handwriting reco...
8 篇 feature extracti...
7 篇 computer science
7 篇 face recognition
7 篇 text analysis
6 篇 neural networks
6 篇 optical characte...
5 篇 image analysis
4 篇 databases
4 篇 fractals
4 篇 image recognitio...
4 篇 pattern analysis
4 篇 shape
3 篇 hidden markov mo...
3 篇 application soft...
3 篇 pixel

机构

10 篇 center for patte...
8 篇 center for patte...
6 篇 center for patte...
4 篇 department of co...
4 篇 center for patte...
4 篇 department of co...
4 篇 department of ma...
4 篇 center for patte...
3 篇 center for patte...
2 篇 laboratory for i...
2 篇 center of patter...
2 篇 center for artif...
2 篇 center of patter...
2 篇 deptartment of c...
2 篇 school of mathem...
2 篇 center for patte...
2 篇 centre for patte...
2 篇 department of co...
2 篇 department of ma...
2 篇 center of patter...

作者

20 篇 c.y. suen
15 篇 suen ching y.
8 篇 vinay a.
7 篇 s natarajan
7 篇 y.y. tang
6 篇 natarajan s.
6 篇 ching y. suen
6 篇 suen c.y.
5 篇 vinay a
4 篇 t.d. bui
4 篇 k n balasubraman...
4 篇 kim soo h.
3 篇 murthy k.n. bala...
3 篇 hong ma
3 篇 j. sadri
3 篇 ma hong
3 篇 tang y.y.
3 篇 s.h. kim
2 篇 zhou jie
2 篇 meghana

语言

76 篇 英文

检索条件"机构=Center of Pattern Recognition and Machine Intelligence"

共 76 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：

Error-correcting output coding for the convolutional neural network for optical character recognition

Error-correcting output coding for the convolutional neural ...

引用

ICDAR2009 - 10th International Conference on Document Analysis and recognition

作者： Deng, Huiqun Stathopoulos, George Suen, Ching Y. Center for Pattern Recognition and Machine Intelligence Concordia University Canada

ISBN: (纸本)9780769537252

It is known that convolutional neural networks (CNNs) are efficient for optical character recognition (OCR) and many other visual classification tasks. This paper applies error-correcting output coding (ECOC) to the CNN for segmentation-free OCR such that: 1) the CNN target outputs are designed according to code words of length N;2) the minimum Hamming distance of the code words is designed to be as large as possible given N. ECOC provides the CNN with the ability to reject or correct output errors to reduce character insertions and substitutions in the recognized text. Also, using code words instead of letter images as the CNN target outputs makes it possible to construct an OCR for a new language without designing the letter images as the target outputs. Experiments on the recognition of English letters, 10 digits, and some special characters show the effectiveness of ECOC in reducing insertions and substitutions. © 2009 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Isolated handwritten Farsi numerals recognition using sparse and over-complete representations

Isolated handwritten Farsi numerals recognition using sparse...

引用

ICDAR2009 - 10th International Conference on Document Analysis and recognition

作者： Pan, W.M. Bui, T.D. Suen, C.Y. Center for Pattern Recognition and Machine Intelligence Concordia University Canada

ISBN: (纸本)9780769537252

A new isolated handwritten Farsi numeral recognition algorithm is proposed in this paper, which exploits the sparse and over-complete structure from the handwritten Farsi numeral data. In this research, the sparse structure is represented as an over-complete dictionary, which is learned by the K-SVD algorithm. These atoms in this dictionary are adopted to initialize the first layer of the Convolutional Neural Network (CNN), the latter is then trained to do the classification task. Data distortion techniques are also applied to promote the generalization capability of the trained classifier. Experiments have shown that good results have been achieved in CENPARMI handwritten Farsi numeral database. © 2009 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Error-Correcting Output Coding for the Convolutional Neural Network for Optical Character recognition

Error-Correcting Output Coding for the Convolutional Neural ...

引用

International Conference on Document Analysis and recognition

作者： Huiqun Deng George Stathopoulos Ching Y. Suen Center of Pattern Recognition and Machine Intelligence Concordia University Canada

ISBN: (纸本)9781424445004

It is known that convolutional neural networks (CNNs) are efficient for optical character recognition (OCR) and many other visual classification tasks. This paper applies error-correcting output coding (ECOC) to the CNN for segmentation-free OCR such that: 1) the CNN target outputs are designed according to code words of length N; 2) the minimum Hamming distance of the code words is designed to be as large as possible given N. ECOC provides the CNN with the ability to reject or correct output errors to reduce character insertions and substitutions in the recognized text. Also, using code words instead of letter images as the CNN target outputs makes it possible to construct an OCR for a new language without designing the letter images as the target outputs. Experiments on the recognition of English letters, 10 digits, and some special characters show the effectiveness of ECOC in reducing insertions and substitutions.

关键词： Convolutional codes Neural networks Optical character recognition software Optical computing Optical fiber networks Character recognition Cellular neural networks Error correction codes Hamming distance Target recognition

来源：评论

学校读者我要写书评

暂无评论

Isolated Handwritten Farsi Numerals recognition Using Sparse and Over-Complete Representations

Isolated Handwritten Farsi Numerals Recognition Using Sparse...

引用

International Conference on Document Analysis and recognition

作者： W.M. Pan T.D. Bui C.Y. Suen Center of Pattern Recognition and Machine Intelligence Concordia University Canada

ISBN: (纸本)9781424445004

A new isolated handwritten Farsi numeral recognition algorithm is proposed in this paper, which exploits the sparse and over-complete structure from the handwritten Farsi numeral data. In this research, the sparse structure is represented as an over-complete dictionary, which is learned by the K-SVD algorithm. These atoms in this dictionary are adopted to initialize the first layer of the convolutional neural network (CNN), the latter is then trained to do the classification task. Data distortion techniques are also applied to promote the generalization capability of the trained classifier. Experiments have shown that good results have been achieved in CENPARMI handwritten Farsi numeral database.

关键词： Handwriting recognition Dictionaries Atomic layer deposition Cellular neural networks Neurons Shape Feature extraction pattern recognition Support vector machines Support vector machine classification

来源：评论

学校读者我要写书评

暂无评论

Text Segmentation from Complex Background Using Sparse Representations

Text Segmentation from Complex Background Using Sparse Repre...

引用

International Conference on Document Analysis and recognition

作者： W. Pan T. Bui C. Suen Center for Pattern Recognition and Machine Intelligence Concordia University USA Department Computer Science and Software Engineering Concordia University USA

A novel text segmentation method from complex background is presented in this paper. The idea is inspired by the recent development in searching for the sparse signal representation among a family of over-complete atoms, which is called a dictionary. We assume that the image under investigation is composed of two components: the foreground text and the complex background. We further assume that the latter can be modeled as a piece-wise smooth function. Then we choose two dictionaries, where the first one gives sparse representation to one component and non-sparse representation to another while the second one does the opposite. By looking for the sparse representations in each dictionary, we can decompose the image into the two composing components. After that, text segmentation can be easily achieved by applying simple thresholding to the text component. Preliminary experiments show some promising results.

关键词： Dictionaries Image segmentation pattern recognition machine intelligence Signal representations Image analysis Computer science Software engineering Image resolution Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

A New Clustering Method for Improving Plasticity and Stability in Handwritten Character recognition Systems

A New Clustering Method for Improving Plasticity and Stabili...

引用

International Conference on pattern recognition

作者： J. Sadri C.Y. Suen T.D. Bui CENPARMI Center for Pattern Recognition and Machine Intelligence Computer Science and Software Engineering Department Concordia University Montreal QUE Canada

This paper presents a new online clustering algorithm in order to improve plasticity and stability in handwritten character recognition systems. Our clustering algorithm is able to automatically determine the optimal number of clusters in the input data. An incremental learning technique similar to adaptive resonance theory (ART) is used to determine the best cluster for new data. Our technique also allows the previously learned clusters to be merged whenever the newly arrived data points push their centers close together. We also developed new features and similarity measures in order to describe and compare the shapes of handwritten digits to be used in our clustering algorithm. Results of our algorithm on clustering the shapes of the handwritten numerals from the CENPARMI isolated digit database are shown. Our method can incrementally learn new handwriting styles of digits, without forgetting the previous ones, therefore it can improve plasticity and stability

关键词： Clustering methods Stability Character recognition Shape measurement Clustering algorithms Prototypes machine learning pattern recognition Subspace constraints Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Genetic Binary Particle Swarm Optimization Model

A Genetic Binary Particle Swarm Optimization Model

引用

Congress on Evolutionary Computation

作者： J. Sadri C.Y. Suen CENPARMI (Center for Pattern Recognition and Machine Intelligence) Computer Science and Software Enginneering Concordia University Montreal West QUE Canada Computer Science and Software Engineering Department Concordia University Montreal QUE Canada

In this paper, a genetic binary particle swarm optimization (GBPSO) model is proposed, and its performance is compared with the regular binary particle swarm optimizer (PSO), introduced by Kennedy and Eberhart. In the original model, the size of the swarm was fixed. In our model, we introduce birth and death operations in order to make the population very dynamic. Since birth and mortality rates change naturally with time, our model allows oscillations in the size of the population. Compared to the original PSO model, and genetic algorithms, our strategy proposes a more natural simulation of the social behavior of intelligent animals. The experimental results show that compared to original PSO, our GBPSO model can reach broader domains in the search space and converge faster in very high dimensional and complex environments.

关键词： Particle swarm optimization Multidimensional systems Computer science Software engineering Java Genetic algorithms Animals Adaptive algorithm Birds Educational institutions

来源：评论

学校读者我要写书评

暂无评论

A new method of recognizing Chinese fonts

A new method of recognizing Chinese fonts

引用

8th International Conference on Document Analysis and recognition

作者： Yang, Zhihua Yang, Lihua Suen, Ching Y. School of Mathematical Sciences South China Normal University Guangzhou 510631 China School of Mathematics and Computing Science Sun Yat-sen University Guangzhou 510275 China Center for Pattern Recognition and Machine Intelligence Concordia University Montreal H3G 1M8 Canada

ISBN: (纸本)0769524206

Chinese fonts are recognized by a new method based on Empirical Mode Decomposition. Five basic strokes have been selected to characterize the features of Chinese fonts. Based on them, stroke feature sequences of a given text block are calculated. Once decomposed by EMD, the first two Intrinsic Mode Functions corresponding to each stroke feature sequence are used to calculate the stroke energy of all the five basic strokes. These energies are combined with the five averages of the residues to produce a tendimensional feature vector. Finally, the minimum distance classifier is used to recognize the fonts. Experiments show encouraging recognition rates. © 2005 IEEE.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

A threshlod selection method based on multiscale and graylevel co-occurrence matrix analysis

A threshlod selection method based on multiscale and graylev...

引用

International Conference on Document Analysis and recognition

作者： Yun Li Mohamed Cheriet C.Y. Suen GM606 Center for Pattern Recognition and Machine Intelligence Concordia University Montreal QUE Canada Laboratory for Imagery Vision and Artificial Intelligence Ecole de Technologie Supérieure University of Quebec Montreal QUE Canada

Noise and complex backgrounds often make the thresholding of degraded document images difficult. In this paper, we propose a new threshold selection method to handle severely degraded document images. First, multiscale image description is adopted to analyze the image edge. From this, edge pixel pair information is derived and recorded by a graylevel co-occurrence matrix. An appropriate threshold value is chosen by measuring the edge pixel pair co-occurrence matrix. The new method is tested with degraded document images. The experimental results show it is resistant to noise and complex backgrounds.

关键词： Laplace equations Degradation Image analysis Image storage Text analysis Image edge detection pattern recognition machine intelligence Laboratories Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A threshlod selection method based on multiscale and graylevel co-occurrence matrix analysis

A threshlod selection method based on multiscale and graylev...

引用

8th International Conference on Document Analysis and recognition

作者： Li, Yun Cheriet, Mohamed Suen, Ching Y. Center for Pattern Recognition and Machine Intelligence Concordia University GM606 1455 de Maisonneuve Blvd. West Montreal Que. H3G 1M8 Canada Laboratory for Imagery Vision and Artificial Intelligence Ecole de Technologie Supérieure University of Quebec 1100 Notre-Dame West Montreal Que. H3C 1K3 Canada

ISBN: (纸本)0769524206

Noises and complex backgrounds often make the thresholding of degraded document images a difficult job. In this paper, we propose a new threshold selection method to handle severely degraded document images. First, multiscale image description is adopted to analyze the image edge. From it, edge pixel pair information is derived and recorded by a graylevel co-occurrence matrix. An appropriate threshold value is chosen by measuring the edge pixel pair co-occurrence matrix. The new method is tested with degraded document images. The experimental results show it is resistant to noises and complex backgrounds. © 2005 IEEE.

关键词： Threshold elements

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8页 << < 1 2 3 4 5 6 7 8 > >>

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：