检索结果-内蒙古大学图书馆

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

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

User-oriented affective video content analysis

User-oriented affective video content analysis

引用

IEEE Workshop on Content-Based Access of image and video Libraries (CBAIVL)

作者： A. Hanjalic Li-Qun Xu Department of Mediamatics Delft University of Technnology Delft Netherlands BTexact Technologies Research Ipswich UK

ISBN: (纸本)0769513549

The article looks into a new direction in multimedia content analysis: the extraction and modeling of the affective content of an arbitrary video. The affective content is viewed as the amount of feeling/emotion contained in and mediated by a video toward a viewer. The ability to automatically extract video content of this nature will lead to a high level of personalization in broadcast delivery to private users, as well as considerably broadening the possibilities of efficiently handling and presenting large amounts of audio-visual data stored in emerging video databases. The technique we have developed uses the so-called "dimensional approach to affect" concept underlined by psychophysiology studies. Our computational method sets to represent the affective content as feature points in the so-called 2D emotion space. We manage to obtain time curves that represent the two affect dimensions (arousal and valence) for a video, considered respectively, from low-level video characteristics. Combining the two time curves results in the so-called affect curve that is regarded as a reliable representation of transitions from one feeling to another along a video, as perceived by a viewer. We illustrate the success of our technique on excerpts taken from an action movie and a typical soccer game, respectively.

关键词： Buffer storage Data mining Broadcasting Spatial databases Audio databases Psychology Motion pictures Games Information retrieval Signal analysis

来源：评论

学校读者我要写书评

暂无评论

On the security of the SARI image authentication system

On the security of the SARI image authentication system

引用

IEEE International Conference on image Processing

作者： R. Radhakrishnan N. Memon Polytechnic University Brooklyn USA

We investigate the image authentication system, SARI, proposed by C.Y. Lin and S.F. Chang (see SPIE storage and retrieval of image/video databases, 1998), that distinguishes JPEG compression from malicious manipulations. In particular, we look at the image digest component of this system. We show that if multiple images have been authenticated with the same secret key and the digests of these images are known to an attacker, Oscar, then he can cause arbitrary images to be authenticated with this same but unknown key. We show that the number of such images needed by Oscar to launch a successful attack is quite small, making the attack very practical. We then suggest possible solutions to enhance the security of this authentication system.

关键词： Authentication image coding Discrete cosine transforms Transform coding Public key cryptography Digital signatures Public key Security image converters Fingerprint recognition

来源：评论

学校读者我要写书评

暂无评论

VORTEX: video retrieval and tracking from compressed multimedia databases - Multiple object tracking from MPEG-2 bit stream

引用

JOURNAL OF VISUAL COMMUNICATION AND image REPRESENTATION 2000年第2期11卷 154-182页

作者： Schonfeld, D Lelescu, D Univ Illinois Dept EECS Signal & Image Res Lab Chicago IL 60607 USA

Multimedia data are generally stored in compressed form in order to efficiently utilize the available storage facilities. Access to multimedia archives is thus dependent on our ability to browse compressed information. In this paper, a novel approach to multiple object tracking from compressed multimedia databases is presented. This approach is intended to operate in a distributed environment, where users initiate video searches and retrieve relevant video information simultaneously From multiple compressed video archives. The system operates on the compressed video to find and track objects of interest and determine their positions in the image. This enables more complex query formulations in terms of the relative positions of the target objects in the image. The filtering and analysis of motion information (motion vectors) is used to track objects in the video bit stream. Once the search has terminated. the system may decompress and display the query-relevant video sequences upon request. (C) 2000 Academic Press.

关键词：

来源：评论

学校读者我要写书评

暂无评论

image and video databases: Restoration, Watermarking and retrieval 1st Edition

引用

丛书名： Advances in image Communication Volume 8

2000年

作者： Hanjalic, A. Langelaar, G. C. Roosmalen, P. M. B. van

ISBN: (数字)9780080508474

ISBN: (纸本)9780444505026

This book provides an in-depth treatment of the three important topics related to image and video databases: restoration, watermarking and retrieval . It is the result of the participation of the Delft University of Technology in the European Union ACTS program, a pre-competitive R&D program on Advanced Communications Technologies and Services (1994-1998). In particular the book has benefited from participation in the AURORA and SMASH projects respectively automated film and video restoration and storage for multimedia systems (watermarking & retrieval).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compact color descriptor for fast image and video segment retrieval

Compact color descriptor for fast image and video segment re...

引用

Conference on storage and retrieval for Media databases 2000

作者： Krishnamachari, S Abdel-Mottaleb, M Philips Res Labs Briarcliff Manor NY 10562 USA

ISBN: (纸本)0819435902

Histograms are the most prevalently used representation for the color content of images and video. An elaborate representation of the histograms requires specifying the color centers of the histogram bins and the count of the number of image pixels with that color. Such an elaborate representation, though expressive, may not be necessary for some tasks in image search, filtering and retrieval. A qualitative representation of the histogram is sufficient for many applications. Such a representation will be compact and greatly simplify the storage and transmission of the image representation. It will also reduce the computational complexity of search and filtering algorithms without adversely affecting the quality. We present such a compact binary descriptor for color representation. This descriptor is the quantized Haar transform coefficients of the color histograms. We show the use of this descriptor for fast retrieval of similar images and search for similar video segments from a large database. We also show the use of this descriptor for browsing large image databases without the need for computationally expensive clustering algorithms. The compact nature of the descriptor and the associated simple similarity measure allows searching over a database of about four hours of video in less than 5-6 seconds without the use of any sophisticated indexing scheme.

关键词： compact descriptor binary histogram image retrieval video segment matching browsing

来源：评论

学校读者我要写书评

暂无评论

Adaptive synthesis in progressive retrieval of audio-visual data

Adaptive synthesis in progressive retrieval of audio-visual ...

引用

1st IEEE International Conference on Multimedia and Expo (ICME2000)

作者： Smith, JR Li, CS IBM Corp TJ Watson Res Ctr Hawthorne NY 10532 USA

ISBN: (纸本)0780365364

With the advent of pervasive computing, a growing diversity of client devices is gaining access to audio-visual content. The increased variability in client device processing power, storage, bandwidth, and server loading require adaptive solutions for image, video and audio retrieval. Progressive retrieval is one prominent mode of access in which views at different resolutions are incrementally retrieved and refined over time. In this paper, we present a new framework for adaptively partitioning the synthesis operations in progressive retrieval of audio-visual signals. The framework considers that the server and client cooperate in synthesizing the views in order to best utilize the available processing power and bandwidth. We provide experimental results that demonstrate a significant reduction in latency in the progressive retrieval of images under different conditions of the client, server and network.

关键词： image and video databases progressive retrieval pervasive computing wavelets

来源：评论

学校读者我要写书评

暂无评论

A novel approach to scene change detection using a cross entropy

A novel approach to scene change detection using a cross ent...

引用

IEEE International Conference on image Processing (ICIP 2000)

作者： Kim, SH Park, RH Sogang Univ Dept Elect Engn Seoul 100611 South Korea

ISBN: (纸本)0780362985

In huge video databases, the effective video indexing method is required. While manual indexing is the most effective approach to this goal, it is slow and expensive. Thus automatic indexing is desirable and recently various indexing tools for video databases have been developed. For efficient video indexing and retrieval, the similarity measure is an important factor. This paper presents new similarity measures between frames and proposes a new algorithm to detect scene changes using a cross entropy defined between two histograms. Experimental results show that the proposed algorithm is fast and effective compared with several conventional algorithms to detect abrupt scene changes and gradual transitions including fade in/out and flash light scenes.

关键词： video signal processing

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Introduction to the Special Issue on image and video Processing for Digital Libraries

引用

IEEE Transactions on image Processing 2000年第1期9卷 1-2页

作者： Manjunath, B.S. Huang, T. Tekalp, A.M. Zhang, H.J. University of California Santa Barbara CA 93106 United States University of Illinois at Urbana-Champaign Urbana IL 61801 United States University of Rochester Rochester NY 14627 United States Microsoft Research China Beijing China

来源：评论

学校读者我要写书评

暂无评论

Dimensionality reduction for image retrieval

Dimensionality reduction for image retrieval

引用

IEEE International Conference on image Processing (ICIP 2000)

作者： Wu, P Manjunath, BS Shin, HD Univ Calif Santa Barbara Dept Elect & Comp Engn Santa Barbara CA 93106 USA

ISBN: (纸本)0780362985

Dimensionality reduction methods are of interest in applications such as content based image and video retrieval. In large multimedia databases, it may not be practical to search through the entire database in order to retrieve the nearest neighbors of a query. Good data structures for similarity search and indexing are needed, and the existing data structures do not scale well for the high dimensional multimedia descriptor-a. We investigate the use of weighted multi-dimensional scaling (WMDS) for dimensionality reduction. The main objective of the WMDS is to preserve the local topology of the high dimensional space, i.e,, to map the nearest neighbors in the high dimensional space to nearest neighbors in the lower dimensional space. In addition to the well known retrieval accuracy as a measure of performance, we propose two additional measures that take into account the ordinal relationships among the nearest neighbors. Experimental results are given.

关键词： image 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：