Telop-on-demand: video structuring and retrieval based on text recognition

The paper presents a telop-on-demand system that anatomically recognizes texts in video frames to create the indices needed for content based video browsing and retrieval. Superimposed texts are important as they provide semantic information about scene contents. Their attributes such as fonts, size, and position in a frame are important as they are carefully designed by the video editor and so reflect the intent of captioning. In news programs, for instance, the headline text is displayed in larger fonts than the subtitles. Our system takes into account not only the texts themselves but also their attributes for structuring videos. We describe: (i) novel methods for detecting and extracting texts that are robust against the presence of complex backgrounds and intensity degradation of the character patterns, and (ii) a method for structuring a video based on the text attributes