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

20 篇 会议

馆藏范围

20 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7 篇 工学
- 4 篇 计算机科学与技术...
- 4 篇 软件工程
- 2 篇 机械工程
- 1 篇 信息与通信工程
2 篇 理学
- 2 篇 数学
2 篇 管理学
- 1 篇 管理科学与工程(可...
- 1 篇 图书情报与档案管...

主题

9 篇 pattern recognit...
7 篇 image segmentati...
7 篇 artificial intel...
6 篇 optical characte...
6 篇 image analysis
5 篇 pattern analysis
4 篇 books
3 篇 algorithm design...
3 篇 feature extracti...
3 篇 text analysis
3 篇 image recognitio...
3 篇 robustness
3 篇 large-scale syst...
3 篇 character recogn...
2 篇 support vector m...
2 篇 traffic control
2 篇 computer crime
2 篇 databases
2 篇 machine learning
2 篇 testing

机构

7 篇 image understand...
4 篇 image understand...
3 篇 german research ...
3 篇 image understand...
3 篇 department of co...
2 篇 research group i...
2 篇 technical univer...
2 篇 image understand...
2 篇 image understand...
1 篇 key laboratory o...
1 篇 research group i...
1 篇 computer vision ...
1 篇 south china univ...
1 篇 research institu...
1 篇 technische unive...
1 篇 graduate institu...
1 篇 servicenow unite...
1 篇 german research ...
1 篇 computer vision ...
1 篇 state key labora...

作者

10 篇 thomas m. breuel
8 篇 faisal shafait
5 篇 joost van beusek...
3 篇 daniel keysers
3 篇 d. keysers
3 篇 f. shafait
3 篇 thomas breuel
2 篇 markus goldstein
2 篇 breuel thomas m.
2 篇 matthias reif
2 篇 j. van beusekom
2 篇 armin stahl
2 篇 t.m. breuel
2 篇 syed saqib bukha...
1 篇 phutke shruti s.
1 篇 ryu han-cheol
1 篇 seizinger tim
1 篇 huang junshi
1 篇 yang xingyi
1 篇 shafait faisal

语言

20 篇 英文

检索条件"机构=Image Understanding and Pattern Recognition Group"

共 20 条记录，以下是1-10 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：

Gated boosting: Efficient classifier boosting and combining

Gated boosting: Efficient classifier boosting and combining

引用

35th Annual German Conference on Artificial Intelligence, KI 2012

作者： Yousefi, Mohammad Reza Breuel, Thomas M. Image Understanding and Pattern Recognition Group Department of Computer Science TU Kaiserslautern Germany

ISBN: (纸本)9783642333460

We study boosting by using a gating mechanism, Gated Boosting, to perform resampling instead of the weighting mechanism used in Adaboost. In our method, gating networks determine the distribution of the samples for training a consecutive base classifier, considering the predictions of the prior base classifiers. Using gating networks prevents the training instances from being repeatedly included in different subsets used for training base classifiers, being a key goal in achieving diversity. Furthermore, these are the gating networks that determine which classifiers' output to be pooled for producing the final output. The performance of the proposed method is demonstrated and compared to Adaboost on four benchmarks from the UCI repository, and MNIST dataset. © 2012 Springer-Verlag.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Improvements to uncalibrated feature-based stereo matching for document images by using text-line segmentation

Improvements to uncalibrated feature-based stereo matching f...

引用

10th IAPR International Workshop on Document Analysis Systems, DAS 2012

作者： Afzal, Muhammad Zeshan Krämer, Martin Bukhari, Syed Saqib Shafait, Faisal Breuel, Thomas M. Image Understanding and Pattern Recognition Group Technical University of Kaiserslautern Kaiserslautern Germany Kaiserslautern Germany

ISBN: (纸本)9780769546612

Document images prove to be a difficult case for standard stereo correspondence approaches. One of the major problem is that document images are highly self-similar. Most algorithms try to tackle this problem by incorporating a global optimization scheme, which tends to be computationally expensive. In this paper, we show that incorporation of layout information into the matching paradigm, as a grouping entity for features, leads to better results in terms of robustness, efficiency, and ultimately in a better 3D model of the captured document, that can be used in various document restoration systems. This can be seen as a divide and conquer approach that partitions the search space into portions given by each grouping entity and then solves each of them independently. As a grouping entity text-lines are preferred over individual character blobs because it is easier to establish correspondences. Text-line extraction works reasonably well on stereo image pairs in the presence of perspective distortions. The proposed approach is highly efficient and matches obtained are more reliable. The claims are backed up by showing their practical applicability through experimental evaluations. © 2012 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

引用

21st National Conference on Artificial Intelligence and the 18th Innovative Applications of Artificial Intelligence Conference, AAAI-06/IAAI-06

作者： Stahl, Armin Gabel, Thomas German Research Center Image Understanding and Pattern Recognition Group Technical University of Kaiserslautern Department of Mathematics and Computer Science Institute of Cognitive Science University of Osnabrück

ISBN: (纸本)1577352815

The definition of accurate similarity measures is a key issue of every Case-Based Reasoning application. Although some approaches to optimize similarity measures automatically have already been applied, these approaches are not suited for all CBR application domains. On the one hand, they are restricted to classification tasks. On the other hand, they only allow optimization of feature weights. We propose a novel learning approach which addresses both problems, i.e. it is suited for most CBR application domains beyond simple classification and it enables learning of more sophisticated similarity measures. Copyright © 2006, American Association for Artificial Intelligence (***). All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Visual cortex inspired features for object detection in X-ray images

Visual cortex inspired features for object detection in X-ra...

引用

International Conference on pattern recognition

作者： Ludwig Schmidt-Hackenberg Mohammad Reza Yousefi Thomas M. Breuel Image Understanding and Pattern Recognition Group Department of Computer Science University of Kaiserslautern Germany

ISBN: (纸本)9781467322164

Visual cortex inspired features mimic what we know of the brain's visual cortex, which is still the best existing object detection system regarding speed and accuracy. For this paper we benchmarked two prominent implementations of these features, Mutch and Lowe's SLF-HMAX and Pinto et al.'s V1-like, against the popular local invariant features SIFT and PHOW in combination with the bag of visual words approach. The benchmark task was the detection of illicit objects in X-ray images of luggage. X-ray inspection is one of the main means of preventing the transport of illicit objects into sensitive areas. The visual cortex inspired features performed superior to the conventional features, probably owing to the textureless nature of X-ray images and the encoding of geometric information.

关键词： Visualization Feature extraction X-ray imaging Support vector machines Brain modeling Object recognition Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Automated OCR Ground Truth Generation

Automated OCR Ground Truth Generation

引用

IAPR International Workshop on Document Analysis Systems, DAS

作者： Joost van Beusekom Faisal Shafait Thomas M. Breuel Image Understanding and Pattern Recognition (IUPR) Research Group German Research Center for Artificial Intelligence (DFKI) Kaiserslautern Germany Image Understanding and Pattern Recognition (IUPR) Research Group Technical University of Kaiserslautern Germany

Most optical character recognition (OCR) systems need to be trained and tested on the symbols that are to be recognized. Therefore, ground truth data is needed. This data consists of character images together with their ASCII code. Among the approaches for generating ground truth of real world data, one promising technique is to use electronic version of the scanned documents. Using an alignment method, the character bounding boxes extracted from the electronic document are matched to the scanned image. Current alignment methods are not robust to different similarity transforms. They also need calibration to deal with non-linear local distortions introduced by the printing/scanning process. In this paper we present a significant improvement over existing methods, allowing to skip the calibration step and having a more accurate alignment, under all similarity transforms. Our method finds a robust and pixel accurate scanner independent alignment of the scanned image with the electronic document, allowing the extraction of accurate ground truth character information. The accuracy of the alignment is demonstrated using documents from the UW3 dataset. The results show that the mean distance between the estimated and the ground truth character bounding box position is less than one pixel.

关键词： Optical character recognition software Character recognition Data mining Robustness Calibration Nonlinear optics Optical distortion System testing Nonlinear distortion Printing

来源：评论

学校读者我要写书评

暂无评论

Server-Side Prediction of Source IP Addresses Using Density Estimation

Server-Side Prediction of Source IP Addresses Using Density ...

引用

International Conference on Availability, Reliability and Security, ARES

作者： Markus Goldstein Matthias Reif Armin Stahl Thomas Breuel Research Group Image Understanding and Pattern Recognition (IUPR) German Research Center for Artificial Intelligence Kaiserslautern Germany Research Group Image Understanding and Pattern Recognition (IUPR) Technical University of Kaiserslautern Kaiserslautern Germany

Source IP addresses are often used as a major feature for user modeling in computer networks. Particularly in the field of distributed denial of service (DDoS) attack detection and mitigation traffic models make extensive use of source IP addresses for detecting anomalies. Typically the real IP address distribution is strongly undersampled due to a small amount of observations. Density estimation overcomes this shortage by taking advantage of IP neighborhood relations. In many cases simple models are implicitly used or chosen intuitively as a network based heuristic. In this paper we review and formalize existing models including a hierarchical clustering approach first. In addition, we present a modified k-means clustering algorithm for source IP density estimation as well as a statistical motivated smoothing approach using the Nadaraya-Watson kernel-weighted average. For performance evaluation we apply all methods on a 90 days real world dataset consisting of 1.3 million different source IP addresses and try to predict the users of the following next 10 days. ROC curves and an example DDoS mitigation scenario show that there is no uniformly better approach: k-means performs best when a high detection rate is needed whereas statistical smoothing works better for low false alarm rate requirements like the DDoS mitigation scenario.

关键词： Computer crime Traffic control Telecommunication traffic pattern recognition Predictive models Smoothing methods Machine learning Quality of service Routing Density functional theory

来源：评论

学校读者我要写书评

暂无评论

recognition Driven Page Orientation Detection

Recognition Driven Page Orientation Detection

引用

IEEE International Conference on image Processing

作者： Yves Rangoni Faisal Shafait Joost van Beusekom Thomas M. Breuel Image Understanding and Pattern Recognition (IUPR) Research Group German Research Center for Artificial Intelligence Kaiserslautern Germany Image Understanding and Pattern Recognition (IUPR) Research Group Technical University of Kaiserslautern Kaiserslautern Germany

In document image recognition, orientation detection of the scanned page is necessary for the following procedures to work correctly as they assume that the text is well oriented. Several methods have been proposed, but most of them rely on heuristics of the script such as the graphical asymmetry between ascenders and descenders for Roman script. The literature shows that as soon as this assumption is not fulfilled, e.g. plain capital text, noisy or degraded characters, etc. they fail. For a large-scale digitalization process, a low error and rejection rate are expected in order to reduce the amount of human intervention. We propose a recognition Driven Page Orientation Detection (RD-POD) which does not depend on external criteria or assumption on the shape of the script. It uses the OCR engine for estimating the right orientation with a few lines of the document image. The RD-POD is highly robust and accurate, and is able to detect multiple orientations. Experimental evaluation shows that our method outperforms the current state-of-the-art on UW-1 dataset with an accuracy of 99.7%. Further tests on other three large and public datasets (MARG, ICDAR07, Google 1000 books) show accuracies of above 99% on each of them.

关键词： image recognition Noise shaping Degradation Large-scale systems Humans Shape Optical character recognition software Search engines Robustness Testing

来源：评论

学校读者我要写书评

暂无评论

Structural Mixtures for Statistical Layout Analysis

Structural Mixtures for Statistical Layout Analysis

引用

IAPR International Workshop on Document Analysis Systems, DAS

作者： Faisal Shafait Joost van Beusekom Daniel Keysers Thomas M. Breuel Image Understanding and Pattern Recognition (IUPR) Research Group German Research Center for Artificial Intelligence (DFKI) Kaiserslautern Germany Technische Universitat Kaiserslautern Kaiserslautern Rheinland-Pfalz DE Image Understanding and Pattern Recognition (IUPR) Research Group Technical University of Kaiserslautern Germany

A key limitation of current layout analysis methods is that they rely on many hard-coded assumptions about document layouts and can not adapt to new layouts for which the underlying assumptions are not satisfied. Another major drawback of these approaches is that they do not return confidence scores for their outputs. These problems pose major challenges in large scale digitization efforts where a large number of different layouts need to be handled and manual inspection of the results on each individual page is not feasible. This paper presents a novel statistical approach to layout analysis that aims at solving the above mentioned problems for Manhattan layouts. The presented approach models known page layouts as a structural mixture model. A probabilistic matching algorithm is presented that gives multiple interpretations of input layout with associated probabilities. First experiments on documents from the publicly available MARG dataset achieved below 5%error rate for geometric layout analysis.

关键词： Books image segmentation image analysis pattern analysis Text analysis Large-scale systems pattern recognition Artificial intelligence Inspection Probability

来源：评论

学校读者我要写书评

暂无评论

Fast Discriminative Linear Models for Scalable Video Tagging

Fast Discriminative Linear Models for Scalable Video Tagging

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Roberto Paredes Adrian Ulges Thomas Breuel Instituto Tecnológico de Informática Universidad Politecnica de valencia Spain Image Understanding and Pattern Recognition Research Group German Research Center for Artificial Intelligence Kaiserslautern Germany Image Understanding and Pattern Recognition Research Group Technical University of Kaiserslautern Kaiserslautern Germany

While video tagging (or "concept detection") is a key building block of research prototypes for video retrieval, its practical use is hindered by the computational effort associated with learning and detecting thousands of concepts. Support vector machines (SVMs), which can be considered the standard approach, scale poorly since the number of support vectors is usually high. In this paper, we propose a novel alternative that offers the benefits of rapid training and detection. This linear-discriminative method is based on the maximization of the area under the ROC. In quantitative experiments on a publicly available dataset of Web videos, we demonstrate that this approach offers a significant speedup at a moderate performance loss compared to SVMs, and also outperforms another well-known linear-discriminative method based on a Passive-Aggressive Online Learning (PAMIR).

关键词： Tagging Machine learning Feature extraction Vocabulary pattern recognition Prototypes Support vector machines Detectors Videoconference Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Distance measures for layout-based document image retrieval

Distance measures for layout-based document image retrieval

引用

International Workshop on Document image Analysis for Libraries

作者： J. van Beusekom D. Keysers F. Shafait T.M. Breuel Image Understanding and Pattern Recognition (IUPR) Research Group German Research Center for Artificial Intelligence (DFKI) Technical University of Kaiserslautern Kaiserslautern Germany

Most methods for document image retrieval rely solely on text information to find similar documents. This paper describes a way to use layout information for document image retrieval instead. A new class of distance measures is introduced for documents with Manhattan layouts, based on a two-step procedure: First, the distances between the blocks of two layouts are calculated. Then, the blocks of one layout are assigned to the blocks of the other layout in a matching step. Different block distances and matching methods are compared and evaluated using the publicly available MARG database. On this dataset, the layout type can be determined successfully in 92.6% of the cases using the best distance measure in a nearest neighbor classifier. The experiments show that the best distance measure for this task is the overlapping area combined with the Manhattan distance of the corner points as block distance together with the minimum weight edge cover matching

关键词： image retrieval Databases Optical character recognition software Algorithm design and analysis Information retrieval pattern recognition Artificial intelligence Nearest neighbor searches Area measurement Current measurement

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2页 << < 1 2 > >>

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：