Browsing System
نویسنده
چکیده
In this demo, we present a system we have developed for automatic broadcast-quality video indexing that successfully combines results from the fields of speaker verification, acoustic analysis, very large vocabulary caption character recognition, content based sampling of video, information retrieval, dialogue systems, and ASF media delivery over IP. The prototype system of this demo is available at http://nn.csie.nctu.edu.tw/Project11/intruduction.htm. I. THE EMERGENCY OF TV NEWS BROWSING SYSTEM THE fierce competition among TV news programs make the news contents become more and more fruitful. However, people become less patient to wait for their favored news stories. Therefore, news on-demand becomes an attracting feature. Since, TV news were generated around the clock, manually indexing news video can be very heavy load labor work. Therefore, how to index news stories automatically becomes a critical issue. Increasing computing power and matured multimedia technologies provide a powerful workspace that can automatically segment news video into semantically meaningful units such as stories and summaries, and derive a content hierarchy. II. SYSTEM REQUIREMENTS IN general, an automated hierarchical TV-news indexing system needs to provide the followings: Retrieve necessary news information, e.g., news video for web-browsing, web news texts for content analysis, etc. Segment news program into story based units. Generate keywords and titles from segmented stories. Search news stories by keywords, dates, etc. Associate relative news series. Provide user interface for searching and browsing news stories. III. SYSTEM DESIGN BASED on the requirements mentioned in Section II, we designed the proposed hierarchical news indexing system. This system consist three major modules: (1) data acquisition (2) data analysis, and (3) user interface. The major task of the data acquisition module is to record TV news programs in proper video format, and fetch relative news documents from Internet web. Data analysis module receives and segments the recorded news video, into story based units, and also generates keywords and news titles for each story. Providing a friendly searching and browsing environment for WAN Browser Web Browser Web Index
منابع مشابه
ارزیابی هدف دسترسی به مراقبتهای سرپایی در برنامۀ پزشک خانوادۀ روستایی با معیارهای تداوم مراقبتها و دسترسی بموقع به مراقبتها در شهرستان گرگان
Background and Objective: Increasing access to health care has been regarded as the main objective of the Iranian Health Care system and development of the rural healthcare network. The family physician plan within this network aimed at increasing access to health care by improvement in performance criteria of the Health Care system in villages and cities under 20,000 population since 2005. In ...
متن کاملAccelerating browsing by automatically inferring a user's search goal
This paper discusses a novel method called active browsing which increases the speed and accuracy with which a user may browse libraries for reusable software. Information inferred solely from the user’s normal actions is employed by the system to locate software items relevant to the user’s search goal. This paper describes our active browsing system and illustrates its operation with an examp...
متن کاملMotion Design of Behavior Components in Remote Book Browsing Robot System
In this research, we are developing a system for browsing books from remote places through the Internet by means of the teleoperation of a mobile robot. In the process of developing this system, we firstly designed and built a prototype of a mobile robot, specially equipped for the accomplishment of browsing determined books, which is mainly categorized by 3 basic goals: (1) picking up the book...
متن کاملA Flexible Architecture for Collaborative Browsing
Collaborative Browsing is a new and promising research area whose purpose is to provide new collaboration schemes among users browsing the Web. To become an efficient collaboration tool, Collaborative Browsing should go far beyond a simple mechanism for coordinating the browsing of Web pages (like Web tours) and should include, in a integrated framework, awareness and communication facilities. ...
متن کاملUsing formal concept analysis with an incremental knowledge acquisition system for web document management
It is necessary to provide a method to store Web information effectively so it can be utilised as a future knowledge resource. A commonly adopted approach is to classify the retrieved information based on its content. A technique that has been found to be suitable for this purpose is Multiple Classification Ripple-Down Rules (MCRDR). The MCRDR system constructs a classification knowledge base o...
متن کاملPersonalized Content Browsing Based on Notions
In this paper we propose a system that facilitates users to browse through related multimedia documents in an efficient manner. The system utilizes the notion of Electronic Roads to make content browsing more effective; that is, it provides them with intelligent personalized content retrieval services, using relevance feedback together with a novel document clustering algorithm. The above notio...
متن کامل