A patent application lodged by Google in July 2007 but recently made public seeks to patent a method where by robots (computers) can read and understand text in images and video.
The extension of the application would be that images and video indexed by Google would be searchable by the text located within the image or video itself, a big step forward in indexing that has not previously been available.This Invention might be an answer to the a series of Infringement cases including the much publicized Viacom dispute which google is faced with.
Google has been working on this filtering tool for quite a long time this might be an answer to curb copyright violation on websites like Youtube where majority of the content posted is in violation of copyright.
Though the DMCA provides for take down policy through notification to the Intermediary this method has not been quite effective, considering the amount of users in YBoutube it is very difficult to monitor the content as 1000 's of video are being uploaded on Youtube every minute this filitering tool might be an answer to this problem and will come a long way in protecting copyright owners.
Copyright owners could include in their video that the video is copyrighted then this application could detect such a word in the video and could prevent uploading of such videos.
A full copy of the patent application “Recognizing Text In Images” can be viewed here