Moving images are still indexed manually, but the overwhelming amount of video fragments makes it necessary to look for automatic indexing techniques. Because many videos contain spoken texts, text recognition can be applied to extract text, which then can be indexed using methods designed for automatic text indexing. Keyframe indexing extracts the most meaningful images from video fragments. It can be compared with the automatic generation of a table of contents of a written text.
automatic video indexing
Librarians have experience with indexing films, videos and DVDs: they simply use the same methods they have for indexing ...