Video matching using binary signature

Automated video matching and recognition has emerged in many applications in recent years. Computer recognition of TV commercials is one of interesting areas. One of critical challenges in automatic recognition of TV commercials is to generate a unique, robust and compact signature. As amount of video data is stored in large quantities, it is necessary to propose an efficient technique for video seeking and matching. In this paper, we present a binary signature based method BOC for TV matching. Experimental results on a real large commercial video database show that our novel approach delivers a significantly better performance comparing to the existing methods.