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

1,448 篇 会议
45 册 图书
43 篇 期刊文献

馆藏范围

1,536 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,217 篇 工学
- 1,047 篇 计算机科学与技术...
- 606 篇 软件工程
- 288 篇 电气工程
- 258 篇 信息与通信工程
- 208 篇 生物工程
- 164 篇 光学工程
- 146 篇 生物医学工程（可授...
- 138 篇 控制科学与工程
- 66 篇 电子科学与技术（可...
- 54 篇 机械工程
- 41 篇 化学工程与技术
- 32 篇 材料科学与工程（可...
- 29 篇 仪器科学与技术
- 25 篇 安全科学与工程
- 22 篇 动力工程及工程热...
497 篇 理学
- 233 篇 数学
- 227 篇 生物学
- 185 篇 物理学
- 80 篇 统计学（可授理学、...
- 39 篇 化学
- 34 篇 系统科学
215 篇 医学
- 199 篇 临床医学
- 85 篇 基础医学(可授医学...
- 61 篇 药学(可授医学、理...
- 29 篇 公共卫生与预防医...
214 篇 管理学
- 140 篇 图书情报与档案管...
- 89 篇 管理科学与工程(可...
- 34 篇 工商管理
43 篇 农学
- 43 篇 作物学
30 篇 法学
- 27 篇 社会学
18 篇 教育学
13 篇 经济学
3 篇 军事学
1 篇 艺术学

主题

144 篇 machine learning
125 篇 deep learning
118 篇 image processing
111 篇 pattern recognit...
70 篇 feature extracti...
64 篇 convolutional ne...
57 篇 image segmentati...
46 篇 face recognition
46 篇 computer vision
41 篇 artificial intel...
39 篇 support vector m...
36 篇 image recognitio...
35 篇 image classifica...
31 篇 neural networks
25 篇 training
24 篇 object detection
24 篇 accuracy
22 篇 machine learning...
22 篇 object recogniti...
21 篇 image enhancemen...

机构

6 篇 institute of ima...
5 篇 centre for inter...
5 篇 chitkara univers...
5 篇 univ south dakot...
4 篇 murdoch universi...
4 篇 indian statistic...
4 篇 university of ca...
4 篇 national researc...
4 篇 boston universit...
3 篇 dept. of compute...
3 篇 city university ...
3 篇 indian institute...
3 篇 shanghai jiao to...
3 篇 peter the great ...
3 篇 natl. lab. of pa...
3 篇 technische unive...
3 篇 graphic era deem...
3 篇 auckland univers...
3 篇 king fahd univer...
3 篇 bangalore

作者

6 篇 santosh k. c.
5 篇 yang jie
4 篇 gennaro claudio
4 篇 ma songde
4 篇 falchi fabrizio
4 篇 stan sclaroff
4 篇 cheng h.d.
4 篇 cosimo distante
3 篇 zohreh doborjeh
3 篇 wendling laurent
3 篇 frontoni emanuel...
3 篇 guimaraes silvio...
3 篇 battiato sebasti...
3 篇 m. tanveer
3 篇 mufti mahmud
3 篇 giovanni m. fari...
3 篇 anon
3 篇 santosh k.c.
3 篇 hegadi ravindra ...
3 篇 andrew chi sing ...

语言

1,324 篇 英文
205 篇 其他
61 篇 中文
2 篇 土耳其文

检索条件"任意字段=1st International Conference on Image Processing Machine Learning and Pattern Recognition"

共 1536 条记录，以下是1141-1150 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：

Using Candidate Exploration and Ranking for Abbreviation Resolution in Clinical Documents

Using Candidate Exploration and Ranking for Abbreviation Res...

引用

1st IEEE international conference on Healthcare Informatics (ICHI)

作者： Kim, Jong-Beom Oh, Heung-Seon Nam, Sang-Soo Myaeng, Sung-Hyon LG Elect Inc Mobile Commun Co Seoul South Korea Korea Inst Sci & Technol Dept Comp Sci Taejon South Korea

ISBN: (纸本)9780769550893

In biomedical texts, abbreviations are frequently used due to their inclusion of many technical expressions of some length. Accordingly, appropriate recognition of abbreviations and their full form pairs is an essential task in automatic text processing of biomedical documents. However, unlike the biomedical literature, clinical notes have many abbreviations without their full forms available in the text or without standard definitions in dictionaries due to the nature of the documents. This causes difficulties in adapting traditional approaches for abbreviation disambiguation such as classification among fixed candidates or pattern-based definition extraction. Because of this reason, we consider the task as search problem and propose an approach with two steps: a) exploring possible full form candidates from various resources and b) choosing most acceptable one among retrieved candidates by ranking. To discover full form candidates and their features, we exploited external academic resources such as MEDLINE and UMLS as well as the clinical note corpus itself. To rank the candidates properly based on human criteria, we adopted RankBoost, one of the learning-to-rank models developed from information retrieval and machine learning communities. Experimental results show the suggested two-step approach is promising for this kind of task.

关键词： Abbreviation Resolution learning to Rank Medical Text processing

来源：评论

学校读者我要写书评

暂无评论

Speeding Up Local Patch Dissimilarity

Speeding Up Local Patch Dissimilarity

引用

17th international conference on image Analysis and processing (ICIAP)

作者： Ionescu, Radu Tudor Popescu, Marius Univ Bucharest Fac Math & Comp Sci Bucharest Romania

ISBN: (纸本)9783642411816;9783642411809

There are many patch-based techniques used in image processing, but most of them are heavy to compute with current machines. A dissimilarity measure for images based on patches, inspired from rank distance, called Local Patch Dissimilarity (LPD), was recently introduced. It has very promising results in optical character recognition, but, as other patch-based methods, it is computationally heavy. This work aims at showing that LPD can be improved in terms of efficiency. Several ways of optimizing the LPD algorithm are presented, such as using a hash table to store precomputed patch distances or skipping the comparison of overlapping patches. Another way to avoid the problem of the higher computational time on large sets of images is to turn to local learning methods. Several experiments are conducted on two datasets using both standard machine learning methods and local learning methods. All methods are based on LPD. The obtained results come to support the fact that LPD is a very good dissimilarity measure for images. In this paper, LPD is also used with success for classifying images other than handwritten digits.

关键词： image dissimilarity image classification handwritten digit recognition patches patch-based technique

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Visual Changepoint Detection Using Maximum Mean Discrepancy

Unsupervised Visual Changepoint Detection Using Maximum Mean...

引用

10th international conference on image Analysis and recognition (ICIAR)

作者： Diu, Michael Gangeh, Mehrdad Kamel, Mohamed S. Univ Waterloo Dept Elect & Comp Engn Ctr Pattern Anal & Machine Intelligence Waterloo ON N2L 3G1 Canada

ISBN: (纸本)9783642390944;9783642390937

The need to quantify similarity between two groups of objects is prevalent throughout the signal processing world. Traditionally, measures such as the Kullback-Leibler divergence are employed, but these may require expensive computations of covariance or integrals. Maximum mean discrepancy is a modern distance measure that is computationally simpler - involving the inner product between the difference in means of two groups' feature distributions - yet statistically powerful, because these distributions are mapped into a high-dimensional, nonlinear feature space using kernels, whereupon the means are estimated via the Parzen estimator. We apply this metric and leverage several powerful data representations from the supervised image classification world, such as bag-of-visual-words and sparse combinations of SIFT descriptors, to locate scene change points in videos with promising results.

关键词： visual changepoint detection unsupervised learning maximum mean discrepancy scene boundary detection video indexing

来源：评论

学校读者我要写书评

暂无评论

stereo Where-What Networks: Unsupervised Binocular Feature learning

Stereo Where-What Networks: Unsupervised Binocular Feature L...

引用

international Joint conference on Neural Networks (IJCNN)

作者： Solgi, Mojtaba Weng, Juyang Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA

ISBN: (纸本)9781467361293;9781467361286

Unsupervised feature learning has been shown promising in the field of machine learning. However, the learning algorithms used in these methods, e.g., Deep Belief Networks based on Restricted Boltzman machines, are typically restricted in different ways, e. g., hard to train and calculate the partition function [1]. In this article, we present a cortexinspired learning network, Where-What Networks (WWN), for the problem of unsupervised learning of binocular local features. The results show that the learned features autonomously developed selectivity for disparity, profile and location of the input patterns. We present a novel algorithm, Dynamic Synapse Lobe Component Analysis (DSLCA), which not only resembles the pattern of neural connections in the visual cortex, but also results in the autonomous development of "domain disparity". To our knowledge, this work is the first to introduce unsupervised learning of both domain and weight disparities between left and right local receptive fields. Moreover, given the theoretical optimality of WWNs [2] and their empirically proven strength in supervised learning, the presented work is the first step towards creating a semi-supervised learning network for simultaneous type, location (including distance) and 3D shape perception.

关键词： Boltzmann machines belief networks shape recognition stereo image processing unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Compare effective fuzzy associative memories for grey-scale image recognition

Compare effective fuzzy associative memories for grey-scale ...

引用

1st international conference on Context-Aware Systems and Applications, ICCASA 2012

作者： Binh, Pham Viet Hoa, Nong Thi Thainguyen University of Information Technology and Communication Viet Nam

ISBN: (纸本)9783642366413

pattern recognition (PR) is the most important field of image processing that is widely developed by many scientists. Reason is that PR provides complete information of objects from noisy inputs. Several types of approach have been proposed to solve this problem, such as recognition base on key features, recognition base on the distribution of histogram. In studies about recognition using key features, Fuzzy Associative Memory (FAM) is an artificial neural network that solve effectively for PR. Advantages of FAM consist of compressing data and recalling from noisy inputs (noise tolerance). Therefore, FAM stores many patterns and retrieves stored patterns. In this paper, we present designs of effective FAM models and experiments to compare the ability of recall with nine types of noise. From results of experiments, we propose useful comments to choose an effective FAM model for pattern recognition applications. © 2013 ICst Institute for Computer Science, Social Informatics and Telecommunications Engineering.

关键词： Associative processing

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-Scale Orientation Estimation: Spatial domain Vs Fourier domain

Robust Multi-Scale Orientation Estimation: Spatial domain Vs...

引用

1st international conference on Communications, Signal processing, and their Applications (ICCSPA)

作者： Khan, Mohammad A. U. Alhalabi, Wadee Effat Univ Elect & Comp Engn Dept POB 34689 Jeddah 21478 Saudi Arabia Effat Univ Dept Comp Sci Jeddah 21478 Saudi Arabia

ISBN: (纸本)9781467328210;9781467328203

Orientation estimation is considered as an important and vital step towards many pattern recognition and image enhancement tasks. In a noisy environment, the gradient-based estimations provide poor results. A pre-smoothing Gaussian function with an appropriate scale is conventionally used to get better gradients. Later on, fixed-scale approach was extended to include multi-scale gradient estimates. More specifically, multi-scale orientation estimation, based on scale-space axioms, in spatial domain can be formulated. To further boost the performance of multi-scale orientation estimates, a Fourier domain foundation in the form of Directional Filter bank (DFB) is incorporated with multi scale spatial domain approach. This paper presents an approach for estimation of local orientations using multi-scale approach both in spatial and fourier domain. In fourier-domain approach, two linear combinations are deployed, one across the directional image, and the other across scales. This is opposed to only one linear combination across the scales, used in normal spatial domain technique. Simulations are conducted over noisy test images as well as real data. Our objective results indicate that multi-scale fourier domain approach always yields better estimates at variable level of noise as compared to stand alone multi-scale spatial domain. The improvements made by fourier domain estimate can largely be attributed to the use of double linear combination both across directional bands and across scales.

关键词： Fourier analysis channel bank filters gradient methods image enhancement

来源：评论

学校读者我要写书评

暂无评论

Classification of Pollen Apertures Using Bag of Words

Classification of Pollen Apertures Using Bag of Words

引用

17th international conference on image Analysis and processing (ICIAP)

作者： Lozano-Vega, Gildardo Benezeth, Yannick Marzani, Franck Boochs, Frank Fachhochsch Mainz i3mainz Lucy Hillebrand Str 2 D-55128 Mainz Germany Univ Bourgogne Le2i F-21078 Dijon France

ISBN: (纸本)9783642411816;9783642411809

The taxonomical recognition of microscopic biological particles such as pollen and spores is relevant for medical and aerobiological applications. Focusing on an accurate and automatic vision-based pollen recognition system, we propose a method for classification of pollen apertures based on bag-of-words strategy, with the ability of learning new types from different taxa without the need of new algorithms. Results demonstrate suitable performance and ability to add new taxa.

关键词： pattern recognition classification local jets bag of words apertures palynology

来源：评论

学校读者我要写书评

暂无评论

The third ACM international workshop on interactive multimedia on mobile and portable devices (IMMPD'13) 13

The third ACM international workshop on interactive multimed...

引用

21st ACM international conference on Multimedia, MM 2013

作者： Luo, Jiebo Shan, Caifeng Etoh, Minoru Shao, Ling University of Rochester Rochester NY 14627 United States Philips Researchm High Tech Campus 36 Eindhoven 5656 AE Netherlands NTT DoCoMo Yokosuka Japan University of Sheffield Mappin Street Sheffield S1 3JD United Kingdom

ISBN: (纸本)9781450324045

With the mobile and portable devices become ubiquitous for people's daily life, how to design user interfaces of these products that enable natural, intuitive and fun interaction is one of the main challenges the multimedia community is facing. Following previous successful events, the third ACM international workshop on Interactive Multimedia on Mobile and Portable Devices (IMMPD'13) aims to bring together researchers from both academia and industry in domains including computer vision, audio and speech processing, machine learning, pattern recognition, communications, human-computer interaction, and media technology to share and discuss recent advances in interactive multimedia. Copyright © 2013 ACM.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

recognition of limited vocabulary Kannada words through structural pattern matching: An experimentation on low resolution images 1

引用

1st international conference on Multimedia processing, Communication and Computing Applications, ICMCCA 2012

作者： Angadi, S.A. Kodabagi, M.M. Department of Computer Science and Engineering Basaveshwar Engineering College Bagalkot Karnataka 587102 India

ISBN: (数字)9788132211433

ISBN: (纸本)9788132211426

Text recognition at character/word level is one of the very important steps for development of automated systems for understanding low resolution display board images which facilitate several new applications such as blind assistants, tour guide systems, location aware systems and many more. In this paper, a new approach for recognition of Kannada words in low resolution natural scene images from a limited vocabulary is presented. The proposed method uses structural patterns of vertical and horizontal cuts as features, which are tolerant to font variability, uncertainty, noise and other degradations. These structural representations characterize the shape of the word image. The method works in two phases;In the training phase, several patterns of vertical and horizontal cut features that can occur generally even in the presence of uncertainty are determined from training word images and templates are constructed, one for each word under study. Further, these templates are organized into knowledge bases, one for each set of word images of equal size in terms of number of characters. During testing, a test word image is processed to obtain vertical and horizontal cut features and a newly defined pattern matching procedure that measures the maximum similarity between test sample and pre-constructed templates of word images in the knowledge base is used to recognize the word. The proposed methodology is evaluated for 1,200 Kannada word images and an overall recognition accuracy of 97.67 % is achieved. The proposed method is found to be robust and insensitive to the variations in size and style of font, thickness and spacing between characters, noise, and other degradations. © 2013 Springer.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Brain imaging classification based On learning Vector Quantization

Brain imaging classification based On Learning Vector Quanti...

引用

international conference on Communications, Signal processing, and their Applications (ICCSPA)

作者： Baher H. Nayef Shahnorbanun Sahran Rizuana Iqbal Hussain Siti Norul Huda Sheikh Abdullah Pattern Recognition Research Group Center for Artificial Intelligence Technology FTSM Universiti Kebangsaan Malaysia Bangi Selangor Malaysia Department of Radiology UKM Medical Center Universiti Kebangsaan Malaysia Kuala Lumpur Malaysia

The performance accuracy of the Artificial Neural Network (ANN) is highly dependent on the class distribution. Data multi-randomization before classification is proposed in this paper in order to obtain a proper classification model, which guaranties well performance of the classifiers. Multi randomization aims to allocate the best class distribution by re-ordering the input dataset randomly. In this paper, learning Vector Quantization (LVQ) which is a supervised ANN, Multilayer perceptron (MLP), unsupervised Self organizing Map (SOM) and Radial Base Function (RBF) are used to classify multi randomized brain Magnetic Resonance Imaging (MRI) dataset. The proposed method showed significant improvement in the stability of the classifiers.

关键词： Magnetic resonance imaging Feature extraction image segmentation Accuracy Artificial neural networks Training Neurons

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154页 << < 111 112 113 114 115 116 117 118 119 120 > >>

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：