检索结果-内蒙古大学图书馆

作者： Lee, Won-Jong Srini, Vason P. Park, Woo-Chan Muraki, Shigeru Han, Tack-Don Department of Computer Science Yonsei University Seoul Korea Republic of Department of Computer Science and Engineering Information and Communications University Deajeon Korea Republic of Department of Internet Engineering Sejong University Seoul Korea Republic of Collaborative Research Team of Volume Graphics National Institute of Advanced Industrial Science and Technology Tokyo 135-0064 Japan

We present an adaptive dynamic load balancing scheme for 3D texture based sort-last parallel volume rendering on a PC cluster equipped with GPUs. Our scheme exploits not only task parallelism but also data parallelism during rendering by combining the hierarchical data structures (octree and parallel BSP tree) in order to skip empty regions and distribute proper workloads to rendering nodes. Our scheme can also conduct a valid parallel rendering and image compositing in visibility order by employing a 3D clustering algorithm. To alleviate the imbalance when the transfer function is changed, a load rebalancing is inexpensively supported by exchanging only needed data. A detailed performance analysis is provided and scaling characteristics of our scheme are discussed. These show that our scheme can achieve significant performance gains by increasing parallelism and decreasing synchronizing costs compared to the traditional static distribution schemes. Copyright © 2008 The Institute of Electronics, information and Communication Engineers.

关键词： Volume rendering

来源：评论

学校读者我要写书评

暂无评论

Multilevel metadata exploration using Meta-Previewer and Cascading-View widgets

Multilevel metadata exploration using Meta-Previewer and Cas...

引用

IEEE International Conference on Research, Innovation and Vision for the Future

作者： Dinh-Quyen Nguyen Henry Sonnet Faculty of Computer Science University of Information and Technology Ho Chi Minh Vietnam Department of Simulation and Graphics Otto-von-Guericke University of Magdeburg Magdeburg Germany

ISBN: (纸本)9781424423798

This paper introduces techniques for the exploration of images augmented with additional information. We present the so-called meta-previewer and propose the cascading-views which are widgets that can assist the end-user in interactively exploring metadata embedded in augmented images. In this regard, the term Interactive Images (Sonnet et al., 2008) will refer to those augmented images which allow the end-user to request further information which is in relation to the entire image or parts of it. Using our tools, data exploration process is accomplished following three steps: (i) getting an overview of the image regions that contain additional information, (ii) requesting and displaying the additional information which is of interest, and (iii) diving into that additional information to get even more information linked with it.

关键词： Multilevel metadata Data exploration and presentation Annotation Augmented images User interface design

来源：评论

学校读者我要写书评

暂无评论

An Exploratory Study on Malay Processing Tool for Acquisition of Taxonomy Using FCA

An Exploratory Study on Malay Processing Tool for Acquisitio...

引用

International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Mohd Zakree Ahmad Nazri Siti Mariyam Shamsudin Azuraliza Abu Bakar Centre of Artificial Intelligence Technology Faculty of Information Science & Technology Universiti Kebangsaan Malaysia Bangi Selangor Darul Ehsan Malaysia Department of Computer Graphics and Multimedia Faculty of Computer Science and. Information System Universiti Teknologi Malaysia Skudai Johor Malaysia

In an effort to develop a tool for automatic ontology building from Malay text based on formal concept analysis, an effective natural language processing (NLP) tool as the pre-processing components is needed. The goal of the study is to investigate whether existing Malay NLP tools can be a viable component to be part of the ontology learning tool. This paper discusses the outcome of the study on three NLP applications. The annotated corpus approach was adopted in this study as deemed suitable for exploratory research. Using the metrics relative subject recall and precision, the results obtained show that statistical modeling technique outperformed pola grammar technique.

关键词： Taxonomy Ontologies Artificial intelligence Natural language processing Machine learning Data mining Natural languages information science Buildings Performance analysis

来源：评论

学校读者我要写书评

暂无评论

Search in speech, language identification and speaker recognition in Speec@FIT

Search in speech, language identification and speaker recogn...

引用

2007 17th International Conference Radioelektronika

作者： Černocký, Jan Burget, Lukáš Schwarz, Petr Matějka, Pavel Karafiát, Martin Glembek, Ondřej Kopecký, Jiří Szöke, Igor Fapšo, Michal Grézl, František Hubeika, Valiantsina Oparin, Ilya Department of Computer Graphics and Multimedia Faculty of Information Technology Brno University of Technology

ISBN: (纸本)1424408229

This paper describes "search in speech " techniques developed in the Speech@FIT research group at FIT BUT in the last couple of years. It concentrates on spoken term detection (STD) and presents our system for NIST STD 2006 evaluations in detail. It also briefly mentions our systems for speaker and language recognition. © 2007 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Delaunay-based vector segmentation of volumetric medical images

Delaunay-based vector segmentation of volumetric medical ima...

引用

12th International Conference on computer Analysis of Images and Patterns, CAIP 2007

作者： Španěl, Michal Kršek, Přemysl Švub, Miroslav Štancl, Vít Šiler, Ondřej Department of Computer Graphics and Multimedia Faculty of Information Technology Brno University of Technology Czech Republic

ISBN: (纸本)9783540742715

The image segmentation plays an important role in medical image processing. Many segmentation algorithms exist. Most of them produce raster data which is not suitable for 3D geometrical modeling of human tissues. In this paper, a vector segmentation algorithm based on a 3D Delaunay triangulation is proposed. Tetrahedral mesh is used to divide a volumetric CT/MR data into non-overlapping regions whose characteristics are similar. Novel methods for improving quality of the mesh and its adaptation to the image structure are also presented. © Springer-Verlag Berlin Heidelberg 2007.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Video summarization at Brno university of technology

Proceedings of the ACM International Multimedia Conference a...

引用

Proceedings of the ACM International Multimedia Conference and Exhibition 2007年 16-19页

作者： Beran, Vitězslav Hradiš, Michal Herout, Adam Sumec, Stanislav Potúček, Igor Zemčik, Pavel Mlích, Josef Láník, Aleš Chmelař, Petr Brno University of Technology Faculty of Information Technology Department of Computer Graphics and Multimedia Božetěchova 2 612 66 Brno Czech Republic

ISBN: (纸本)9781595937803

This paper describes the video summarization system built for the TRECVID 2007 evaluation by the Brno team. Motivations for the system design and its overall structure are described followed by more detailed description of the critical parts of the system, which are feature extraction and clustering of frames (shots, sub-shots) in time domain. Many ideas were not included in the system because of the time constraints. Those considered promising are stated and are briefly described as possible future work. The result of video summarization presented in this paper is promising and will benefit further investigation. This is specifically true as not all the features that can be considered and processing methods were implemented in the evaluated system. Copyright 2007 ACM.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Video summarization at Brno University of technology

Video summarization at Brno University of Technology

引用

1st TRECVID Video Summarization Workshop, TVS'07, Co-located with the ACM Multimedia 2007, MM'07

作者： Beran, Vítězslav Hradiš, Michal Herout, Adam Sumec, Stanislav Potúček, Igor Zemčík, Pavel Mlích, Josef Láník, Aleš Chmelař, Petr Brno University of Technology Faculty of Information Technology Department of Computer Graphics and Multimedia Božetěchova 2 612 66 Brno Czech Republic

ISBN: (纸本)9781595937803

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Search in speech, language identification and speaker recognition in Speech@FIT

Search in speech, language identification and speaker recogn...

引用

International Conference on Radioelektronika

作者： Jan Cernocky Lukas Burget Petr Schwarz Pavel Matejka Martin Karafiat Ondrej Glembek Jiri Kopecky Igor Szoke Michal Fapso Frantisek Grezl Valiantsina Hubeika Ilya Oparin Speech@FIT Department of Computer Graphics and Multimedia Faculty of Information Technology Brno University of Technology Czech Republic

ISBN: (纸本)1424408210

This paper describes "search in speech" techniques developed in the Speech@FIT research group at FIT BUT in the last couple of years. It concentrates on spoken term detection (STD) and presents our system for NIST STD 2006 evaluations in detail. It also briefly mentions our systems for speaker and language recognition.

关键词： Natural languages Speaker recognition Speech processing Speech recognition Humans Mobile communication Telephony Personnel Security Vocabulary

来源：评论

学校读者我要写书评

暂无评论

Guest editorial

引用

The Visual computer 2007年第7期23卷 451-452页

作者： Gutierrez, Diego Shamsuddin, Siti Mariyam CPS (Edificio Ada Byron) Universidad de Zaragoza Zaragoza Spain Department of Graphics and Multimedia Faculty of Computer Science and Information System University Technology of Malaysia Skudai Malaysia

来源：评论

学校读者我要写书评

暂无评论

A fast coarse-to-fine vehicle logo detection and recognition method

A fast coarse-to-fine vehicle logo detection and recognition...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Yunqiong Wang Zhifang Liu Fei Xiao Faculty of Computer Science and Information Technology Yunnan Normal Universitye Kunming 650092 China Institute of Image and Graphics Computer Science Department of Sichuan University Chengdu 610064 China

This paper presents algorithms for vision-based classification of vehicles based on vehicle logo in monocular image of traffic scenes recorded by a stationary camera. The intended application is automatic recognition of vehicle type for secure access and traffic monitoring applications, a problem not hitherto considered at such a level of accuracy. In recognition of vehicle type, differing with other researchers who attend to the recognition of shape, size of vehicle, we pay attention to the location and recognition of vehicle logo. The vehicle logo is unique mark of vehicle type (both make and model). We demonstrate that a relatively simple vehicle logo recognition method from front images can be used to obtain high performance verification and recognition of vehicle type. Firstly, the vehicle logo can be rough detected by prior knowledge, such as license, and then logo can be exactly detected by edge feature. Finally, the logo can be recognized using template matching and edge orientation histograms. Experimental results show the effectiveness of the proposed method.

关键词： Vehicle detection Vehicles Image edge detection Image recognition Classification algorithms Layout Cameras computerized monitoring Shape Licenses

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：