Face And Name Matching In A Movie By Grapical Methods In Dynamic Way

Abstract With the flourishing development of the movie industry a huge amount of movie data is being generated every day. It becomes very important for a media creator or distributor to provide better media content description indexing and organization so that users can easily browsing skimming and retrieving the content of interest. Our goal is to automatically determine the cast of a feature-length film and match it with the character name. This is challenging because the cast size is not known with appearance changes of faces caused by extrinsic imaging factors like illumination pose and expression often greater than due to differing identities. Although in the existing system the performances are limited due to the noises generated during the face tracking and face clustering process. The contributions of this work include A noise insensitive character relationship. An error correcting graph matching algorithm is introduced. Complex character changes are handled simultaneously by graph partition and graph matching.