Indexing for Topics in Videos Using Foils

A long-standing goal of distance learning has been to provide a quality of learning comparable to the face-toface envir onmentof a traditional classr oomfor teaching or training. One of the fundamental problems in achieving this goal is providing e e ctiveways of highlevel semantic querying such as for the retrieval of relevant learning material relating to a topic of discussion. In this paper we present a method of identifying video segments relating to a topic of discussion by indexing vide os using the image and text content of foils. Specifically, we present a novel method of locating and recognizing foil images in vide o using the color and spatial layout geometry of their regions. We then search the audio asso ciate dwith vide o based on the text content of the foil to identify relate d vide o segments in which concepts represente don a foil are heard. Finally, we combine the results of foil image and text search of vide o exploiting their time co-occurrenc e. The resulting identi cation of topics is evaluated in the domain of classr oom le ctur es and talks.