Content-based Indexing of Captioned Video on the ViewStation
Submitted to ACM Multimedia 95, San Francisco, CA, October 1995.
Authors
D. R. Bacher and
C. J. Lindblad
Abstract
We have designed and constructed a mechanism for using caption text from
broadcast television programs to analyze their content. In this paper, we
describe the method by which captions are captured and translated from the raw
video signal into text on the ViewStation. We also describe our Caption
Parser, which analyzes the text and extracts information about the content of
broadcast television programs. A specialized version of the parser is used by
our Joke Markup program to index captioned monologues of late-night talk
shows. The output of the markup program can be viewed through our Joke
Browser, enabling selection and replay of jokes based on their content.
Text
(.ps,
.ps.Z)
