Automatic Generation of a Multimedia Encyclopedia from TV Programs by Using Closed Captions and Detecting Principal Video Objects

This paper proposes a method for automatically generating a multimedia encyclopedia from video clips using closed-caption text information. The goal is to automatically index each video segment of the television program by the principal video object. We focus on several features of the closed-caption text style in order to identify the principal video objects. Using Quinlan's C4.5 decision-tree learning algorithm and the predicted accuracies of production rule indicators, one object noun is extracted for each video shot. To show the effectiveness of the method, we conducted experiments on the extraction of video segments in which animals appear in twenty television programs on animals and nature. We obtained a precision rate of 74.6 percent and a recall rate of 51.4 percent on the extraction of video segments in which animals appear, and generated a multimedia encyclopedia comprising 322 video clips showing 82 kinds of animals