The Community for Technology Leaders
Green Image
Issue No. 05 - September/October (1999 vol. 14)
ISSN: 1541-1672
pp: 45-50
This article describes Named Faces, a fully functional and automated system that builds a large database of name-face association pairs from broadcast news. Named Faces detects and recognizes superimposed text in the video. It then verifies or repairs the text with a dynamic programming match to a large list of automatically generated names found in news stories. Faces found in the video where superimposed names were recognized are tracked, extracted, and associated with the superimposed text. The system gathers news stories and images from the Web to improve its performance.

R. Houghton, "Named Faces: Putting Names to Faces," in IEEE Intelligent Systems, vol. 14, no. , pp. 45-50, 1999.
94 ms
(Ver 3.3 (11022016))