Multimedia Database System for TV Newscasts and Newspapers
It is important to use pattern information (e.g. TV newscasts) and textual information (e.g. newspapers) together. For this purpose, we describe a method for aligning articles in TV newscasts and newspapers. Also, we describe a method for extracting a newspaper article and its follow-ups. In order to align articles, the alignment system uses words extracted from telops in TV newscasts. The recall and the precision of the alignment process are 97% and 89%, respectively. On the other hand, in order to obtain a newspaper and its follow-ups, the system uses typical expressions which give signs of subsequent articles. The recall and precision are 80% and 85%, respectively. Using the results of these processes, we develop a browsing and retrieval system for articles in TV newscasts and newspapers.
Unable to display preview. Download preview PDF.
- [Kurohashi97]Kurohashi, Nagao: JUMAN Manual version 3.4 (in Japanese), Nagao Lab., Kyoto University, (1997).Google Scholar
- [Mino96]Mino: Intelligent Retrieval for Video Media (in Japanese), Journal of Japan Society for Artificial Intelligence Vol.11 No.1, (1996).Google Scholar
- [Sakai93]Sakai: A History and Evolution of Document Information Processing, 2nd International Conference on Document Analysis and Recognition, (1993).Google Scholar
- [Sato98]Sato, Hughes, and Kanade: Video OCR for Digital News Archive, IEEE International Workshop on Content-based Access of Image and Video Databases, (1998).Google Scholar
- [Tsunoda96]Tsunoda, Ooishi, Watanabe, Nagao: Automatic Alignment between TV News and Newspaper Articles by Maximum Length String between Captions and Article Texts (in Japanese), IPSJ-WGNL 96-NL-115, (1996).Google Scholar
- [Watanabe96]Watanabe, Okada, Nagao: Semantic Analysis of Telops in TV Newscasts (in Japanese). IPSJ-WGNL 96-NL-116, (1996).Google Scholar