Google's Youtube To Begin Testing Video Fingerprinting Technology To Enforce Copyrights

Tuesday, June 12th 2007, 5:57 pm

By: News On 6

LOS ANGELES (AP) _ The popular user-generated video sharing site YouTube will begin testing video recognition technology in conjunction with partners Time Warner Inc. and The Walt Disney Co.

The test will begin next month with hopes that the software, designed to recognize copyright content in videos, will be ready to roll out later this year, the company said.

The site's owner, Google Inc., has previously pledged to adopt some kind of solution to identify copyright content on its site so it can remove pirated content or negotiate with owners for a license.

While much of YouTube's videos are homegrown, copyright content from such partners as CBS and NBC also attract viewers. Protecting those relationships is key for online video sites.

The importance of those relationships was highlighted in March when Viacom Inc. sued YouTube and Google for more than $1 billion in a federal complaint alleging YouTube hasn't done enough to prevent its users from posting thousands of copyright clips to the site.

YouTube said it had started using audio recognition technology from Audible Magic Corp. earlier this year to either block unauthorized content or pay royalties to the major record labels who have licensed their content to the site.

The company was searching for a similar video fingerprinting technology when it was bought by Google in October for $1.65 billion.

``What we found was that no one had anything we felt was accurate enough and scalable enough for our needs,'' YouTube Partner Development Director Chris Maxcy said Tuesday.

YouTube engineers discovered that Google had been developing such video technology.

``The technology is built for maximum flexibility,'' he said. ``It can be used to remove content once it is identified or used to license content where we pay a revenue share to our partners.''

Video recognition is more complicated than audio fingerprinting, Maxcy said. It involves extensive indexing of images from videos and collecting the images in a database. It also involves compiling the rules associated with each piece of content as set by the copyright holder.

For instance, a TV network could tell YouTube to pay a royalty whenever one clip is uploaded to its site but block another that is unauthorized.