The European Union funded aceMedia venture has developed a system to automatically tag or keyword video and image content. They do this by using computer algorithms to analyse the composition of individual frames. Partners in the aceMedia consortium include Motorola, Philips, the University of London and France Telecom.

The current focus of the project is to help consumers categorise their holiday videos and photos. But in our view, the system will soon join other search methods, which together will make the implementation of efficient, accurate contextual advertising for video and images a reality in the near future.

The aceMedia system uses advances in knowledge, semantics and multimedia processing technologies to support self-analysing, self-annotating and self-adapting content. It relies on content preprocessing, image recognition and knowledge analysis tools to supply metadata annotations on static and moving images, and on specific parts of those images. A photo of a crowded beach, for example, could be automatically annotated with references to the beach, sea, sky and bathers.

The team behind the aceMedia initiative are showcasing the results of their work so far at IST 2006 in Helsinki, where visitors can see demonstrations.

aceMedia project manager Adrian Matellanes of Motorola tells us:

“We will demonstrate how our system can automatically and intelligently organise photos from a digital camera on a PC, and how they can then be retrieved and displayed seamlessly on a television using a set-top box. It will be an opportunity to highlight the real ability of aceMedia to solve some of the biggest challenges in how we interact with multimedia content.”

For videos, different sections of the video could be annotated depending on what was being shown, and individual segments could easily be extracted and viewed.

As Paola Hobson, aceMedia project coordinator, says:

“You can’t make money out of content if people can’t find it, and the cost of annotating content manually is enormous. Automatic annotation will help people find what they want, and they would consume more of it.”