检索结果-内蒙古大学图书馆

Proceedings of the 1999 7th conference of the storage and retrieval for image and video databases vII

作者： Ganapathy, S.Kicha Lei, Zhibin Safranek, Robert J. Bell Lab Murray Hill NJ United States

Multimedia Information Systems are experiencing a tremendous growth as a direct consequence of the popularity and pervasive use of world wide web. As a consequence, it is becoming increasingly important to provide efficient and flexible solutions for accessing and retrieving multimedia data. images and video are emerging as significant data types in multimedia systems. And yet, most commercial systems are still text and key-word based and do not fully exploit the image content of these systems. We believe that there is an opportunity to build a novel interactive multimedia system for some specific applications in electronic commerce. In this paper we present an overview of our approach, the rationale behind it and the problems that are inherent in building such a system. We address some of the technical issues in representing and analysing image primitive features. These are the building blocks of any such systems. They can be generalized into a much broader range of applications as well.

关键词： Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

Techniques for designing a classifier for multimedia indexing

Techniques for designing a classifier for multimedia indexin...

引用

conference on storage and retrieval for Media databases 2001

作者： Mittal, A Cheong, LF Natl Univ Singapore Dept Elect & Comp Engn Vis & Image Proc Lab Singapore 117576 Singapore

ISBN: (纸本)0819439932

This paper addresses the issues involved in designing a classifier for multimedia indexing, a representative of domain of tasks involving high dimensionality of feature space and large dissimilarity between features in range and variation, and requiring a strong inference mechanism. We consider decision trees, bayesian network, neural network and support vector approaches The Modified Bayesian Network (MBN), as designed by us offers significant advantages over other approaches. The application of bayesian network has generally been restricted to domains having discrete variable values (such as binary), or to the domain with continuous variable values which approximate to Gaussian distribution. However, MBN can form sound representation of non-Gaussian Multimodal continuous distribution, as is the case with feature space in multimedia indexing. This can be accomplished by intelligent partitioning and data clique association. The structure of MBN and its functionality on real video is also presented in the paper. MBN can perform optimal classification even with partially specified queries given by the user. The strategy automatically gives more weightage to the relevant features amongst hundreds of features present in multimedia indexing system. The inference mechanism is based on iteratively comparing the posterior probability of one class with all other classes. In the comparison of one class with another class, each feature takes different importance measure corresponding to the discerning capacity of the feature. A label is assigned to the multimedia data corresponding to the winning class. The comparison with other classification tools shows that MBN classification performance is consistently better than that of the other tools.

关键词： high dimensionality feature space modified Bayesian network decision trees neural networks support vector machines partitioning meaningful feature evaluation

来源：评论

学校读者我要写书评

暂无评论

Special section on storage, processing, and retrieval of digital media

引用

JOURNAL OF ELECTRONIC IMAGING 2001年第4期10卷 833-834页

作者： Yeung, MM Li, CS Lienhart, R Yeo, BL Intel Corp Microprocessor Res Labs Santa Clara CA 95052 USA IBM Thomas J Watson Res Ctr Hawthorne NY 10532 USA Teracent Corp Cupertino CA 95014 USA

Recent advances in computing and communications are leading to the creation of large-scale databases of visual and multimedia information. Such databases are finding ready applications in a wide range of fields such as advertising and marketing, education and training, entertainment, medicine, and remote sensing. Because of the very nature of visual and multimedia data, new and innovative methods are called for in modeling, processing, organizing and indexing of this data for efficient storage, management, access, and delivery of the content. The goal of this special section is to highlight the new research areas and explore technology frontiers, by soliciting and selecting quality papers addressing issues from various aspects of storage, search, retrieval, and processing of digital media data (video/image/audio) and across a wide range of research disciplines. For this special section, we have solicited papers in relevant areas, ranging from content capture and processing, database management, new results on similarity measures and semantic features, and query methods to multimedia systems embracing leading-edge technology, and special applications of media management, retrieval, and processing across multiple fields, from consumer media systems, digital libraries, and media imaging to remote sensing. We encouraged the authors of some very promising papers in the SPIE/IS&T Electronic Imaging Symposium (San Jose) 2001 conference on storage and retrieval of Media databases to submit a full journal-quality version of their conference manuscript to this special section. We also received submissions from outside of the conference, in response to our general call for papers. All submitted papers have undergone multiple peer-reviews, and we accepted 12 papers after two rounds of revisions and follow-up reviews. We have classified the 12 papers into four major categories: (A) Content-based image retrieval (the first two papers), (B) Content-based video retrieval (the next

关键词： Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

Data Processing and Presentation for a Personalised, image-driven Medical Graphical Avatar

Data Processing and Presentation for a Personalised, Image-d...

引用

35th Annual International conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： de Ridder, Michael Bi, Lei Constantinescu, Liviu Kim, Jinman Feng, David Dagan Univ Sydney Sch Informat Technol Sydney NSW 2006 Australia

ISBN: (纸本)9781457702167

With the continuing digital revolution in the healthcare industry, patients are being confronted with the difficult task of managing their digital medical data. Current personal health record (PHR) systems are able to store and consolidate this data, but they are limited in providing tools to facilitate patients' understanding and management of the data. One reason for this stems from the limited use of contextual information, especially in presenting spatial details such as in volumetric images and videos, as well as time-based temporal data. Further, lack of meaningful visualisation techniques exist to represent the data stored in PHRs. In this paper we propose a medical graphical avatar (MGA) constructed from whole-body patient images, and a navigable timeline of the patient's medical records. A data mapping framework is presented that extracts information from medical multimedia data such as images, video and text, to populate our PHR timeline, while also embedding spatial and textual annotations such as regions of interest (ROIs) that are automatically derived from image processing algorithms. We developed a prototype to process the various forms of PHR data and present the data in a graphical avatar. We analysed the usefulness of our system under various scenarios of patient data use and present preliminary results that indicate that our system performs well on standard consumer hardware.

关键词： data handling data structures data visualisation health care information retrieval information storage medical information systems multimedia databases visual databases

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic dynamic video object marker creation

Semi-automatic dynamic video object marker creation

引用

Proceedings of the 1999 7th conference of the storage and retrieval for image and video databases vII

作者： Toklu, Candemir Liou, Shih-Ping Siemens Corporate Research Inc Princeton NJ United States

In this paper we propose a method for tracking a video object in an ordered sequence of two-dimensional images, where the outcome is the trajectory of the video object throughout the time sequence of images. This method is designed to run in real-time in a synchronous video collaboration environment, and used for producing dynamic object annotations for enhanced video content understanding. A dynamic object is an object whose location or size in the video frame constantly changes due to the camera motion, the motion of its own, or both. We suggest a novel method for finding the trajectory of the object in the intermediate frames given the locations and shapes of the object in two end frames. In addition to the shape and location information of the object, its texture information in the end frames is used to predict the location and search space of it in the intermediate frames.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Binary data storage, retrieval and feature calculation on Netezza PureData system for Analytics 5

Binary data storage, retrieval and feature calculation on Ne...

引用

5th International conference on Information Technology and Nanotechnology, ITNT 2019

作者： Donon, Y. Paringer, R. Kupriyanov, A. Samara National Research University Moskovskoe Shosse 34A Samara443086 Russia Image Processing Systems Institute of RAS Branch of the FSRC Crystallography and Photonics RAS Molodogvardejskaya street 151 Samara443001 Russia

The storage of images in databases has long been a delicate matter but comes now more and more in use. This kind of data is in most DBMS limited in storage size to 64kb, making necessary to divide large objects into fragments;moreover, programming languages also present limitations in data retrieval. In this paper, we experimented the retrieval, reconstitution, feature calculation of pictures using different fragment size and determined the optimal one. In this work, the server used was a Netezza model from the N2001 line. In this work, we present the architecture of the database, our research and bring recommendation about the optimal fragmentation size to store images into a database. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Gesture for video content navigation

Gesture for video content navigation

引用

Proceedings of the 1999 7th conference of the storage and retrieval for image and video databases vII

作者： Bradski, Gary Yeo, Boon-Lock Yeung, Minerva M. Intel Corp Santa Clara CA United States

This article describes the use of gesture recognition techniques in computer vision as a natural interface for video content navigation, and the design of a navigation and browsing system that caters to these natural means of computer-human interaction. For consumer applications, video content navigation presents two challenges: (1) how to parse and summarize multiple video streams in an intuitive and efficient manner, and (2) what type of interface will enhance the ease of use for video browsing and navigation in a living room setting or an interactive environment. In this paper, we address the issues and propose the techniques that combine video content navigation with gestures, seamlessly and intuitively, in an integrated system. The current framework can incorporate speech recognition technology. We present a new type of browser for browsing and navigating video content, as well as a gesture recognition interface for this browser.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Processing of partial video data for detection of wipes

Processing of partial video data for detection of wipes

引用

Proceedings of the 1999 7th conference of the storage and retrieval for image and video databases vII

作者： Kim, Hyeokman Park, Sung-Jun Lee, Jinho Kim, Woonkyung M. Song, S.Moon-Ho Korea Telecom Seoul Korea Republic of

With the currently existing shot change detection algorithms, abrupt changes are detected fairly well. It is thus more challenging to detect gradual changes including fades, dissolves, and wipes as these are often missed or falsely detected. In this paper, we focus on the detection of wipes. The proposed algorithm begins by processing the visual rhythm, a portion of the DC image sequence. It is a single image, a sub-sampled version of a full video in which the sampling is performed in a pre-determined and in a systematic fashion. The visual rhythm contains distinctive patterns or visual features for many different types of video effects. The different video effects manifest themselves differently on the visual rhythm. In particular, wipes appear as curves that run from the top to the bottom of the visual rhythm. Thus, using the visual rhythm, it becomes possible to automatically detect wipes simply by determining various lines and curves on the visual rhythm.

关键词： video signal processing

来源：评论

学校读者我要写书评

暂无评论

Ontology-based information integration in virtual learning environment 05

Ontology-based information integration in virtual learning e...

引用

IEEE/WIC/ACM International conference on Web Intelligence

作者： Dong, AJ Li, HL N Dakota State Univ Dept Comp Sci Fargo ND 58105 USA

ISBN: (纸本)076952415X

A good virtual learning environment should deliver relevant learning materials to learners at the most appropriate time and locations to facilitate learners' acquisition of knowledge and skills. In this paper, we propose ontology-based information integration in virtual learning environment using ontology and web services. Relevant concepts extracted from domain ontology provide ontology-based browsing space that allows users to browse and select relevant terms of interest and increases the degree of relevancy. By using web services to integrate learning materials from heterogeneous public domain data sources, applications do not need to know the internal structure and working of public domain data sources, and reuse existing applications and recourses. We use Gene Ontology, PubMed eUtils and Google Web APIs to demonstrate our idea. The implementation involves techniques in image and video processing, database management, programming, and multimedia learning materials presentation.

关键词： Ontologies Information retrieval Web services Data mining Multimedia databases Computational modeling Material storage Computer science Neodymium videoconference

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT video SEARCH USING image QUERIES

EFFICIENT VIDEO SEARCH USING IMAGE QUERIES

引用

IEEE International conference on image Processing

作者： A. Araujo M. Makar v. Chandrasekhar D. Chen S. Tsai H. Chen R. Angst B. Girod Stanford University Qualcomm Inc. Institute for Infocomm Research

ISBN: (纸本)9781479957521

We study the challenges of image-based retrieval when the database consists of videos. This variation of visual search is important for a broad range of applications that require indexing video databases based on their visual contents. We present new solutions to reduce storage requirements, while at the same time improving video search quality. The video database is preprocessed to find different appearances of the same visual elements, and build robust descriptors. Compression algorithms are developed to reduce system's storage requirements. We introduce a dataset of CNN broadcasts and queries that include photos taken with mobile phones and images of objects. Our experiments include pairwise matching and retrieval scenarios. We demonstrate one order of magnitude storage reduction and search quality improvements of up to 12% in mean average precision, compared to a baseline system that does not make use of our techniques.

关键词： Efficient video search image-based retrieval

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：