Combined IMage and WOrd Spotting - CIMWOS
 
  Home
  Project Summary
  Features
  Technology
  Partners
  Contact
  Publications
  System Demo
 

Password:

  Private
   
   
 
webmaster at xanthi.ilsp.gr

Last Updated:
2003-11-25

System Demo

CIMWOS is an integrated environment for accessing multimedia digital contents that provides advanced searching and browsing capabilities. The CIMWOS consortium is conducting research on emerging technologies for data storage, indexing and retrieval, and is embedding them in a video library system that covers sports, broadcast news and documentaries in English, French and Greek. The CIMWOS Digital Video Library uses intelligent, automatic mechanisms that provide full-content search and retrieval from a large (scaling to several hours) online digital video library. The tools we are developing during the project, can automatically populate the library and support access to it. The approach we follow uses combined speech, language and image understanding technology to automatically transcribe, segment and index the video. Retrieval is text-based, performed on the material resulting from image analysis, speech recognition and Natural Language Processing of the transcribed text. The information produced by the speech, image and text components is suitable for intelligent indexing and retrieval so that a user can find an item of interest within the digital library.

 

The Graphical User Interface of CIMWOS determines the way users control and interact with the system. The interaction between the user and the system can be roughly described in four steps: User Query (free text or guided through system metadata), Query Processing (stop list, Boolean operations formed from queries and Boolean operators etc.), Search Results (table of results with media information and key frame thumbnails), and Video Presentation (selection and display of a certain amount of time of video using the MediaPlayer). Searching through browsing is also supported.

 

CIMWOS is an innovative combination of speech, language and image understanding technology to automatically transcribe, segment and index the video. In the search demo page the user can enter a complex query and retrieve the corresponding video segments.

Enter password on the left to access the online system demo.