9.9 MPEG-7: Multimedia Content Description Interface

As more and more audio-visual information becomes available in digital form, there is increasing pressure to make use of it. Before one can use any information, however, it has to be located first. Unfortunately the increasing availability of interesting material makes this search extremely difficult.

For textual information, currently many text-based search engines are available on the World Wide Web (www), and they are among the most visited sites. This is an indication of real demand for searching information on the public domain. However, identifying information for audiovisual content is not so trivial, and no generally recognised description of these material exists. In the mean time, there is no efficient way of searching the www for, say, a picture of a "lady with a red hat waiting for a taxi". However, in specific cases, solutions do exist. Multimedia databases on the market today allow searching for pictures using characteristics like colour, texture and information about the shape of objects in the picture. One could envisage a similar example for audio, in which a melody could be whistled to find a song.

The question of finding contents is not restricted to database retrieval applications. For example, in television news studios, there is an increasing demand to locate a video clip of a certain event. Another example is the selection of the program of interest from a vast number of available satellite television channels.

In October 1996, MPEG started a new program to provide a...