Now a day’s character Identification from films is a very challenging task due to the huge variation in the appearance of each & every character. It will lead significant research interests and may have many interesting applications in today’s life. In this paper, we investigate the problem of identifying characters & annotating them with respective name using graph matching algorithm to get the most accurate identification result. The contribution of our work include: 1) the character-character relationship representation including a noise insensitive 2) Use an edit operation based error correcting graph matching algorithm.3) Graph partitioning and graph matching for more complex character changes to handle simultaneously. 4) The existing character identification approaches, also we are going to perform an in-depth sensitivity analysis which will introduce two types of simulated noises.

ABSTRACT: Automatic face identification of characters in movies has drawn significant research interests and led to many interesting the applications. And it is the challenging problem due to the huge variation in the appearance of each character. Although these existing methods are demonstrate promising results in this the clean environment that the performances are limited in the complex movie scenes due to the noises can be generated during the face tracking and face clustering process. In this paper we can present two schemes of global face-name matching and based on the framework for robust character identification. In this the contributions of this work can be include: 1) A noise insensitive character and the relationship representation is incorporated. 2) We can introduce an edit operation based on the graph matching algorithm. 3) Complex character changes are can be handled by simultaneously graph partition and graph matching. 4) Beyond the existing character identification can be approaches; we can further perform an in-depth sensitivity analysis by introducing two types of simulated noises. There are the proposed schemes demonstrate state-of-the-art performance on this the movie character identification in various genres of movies. Keywords—face name matching, graph matching, character identification.

ABSTARCT: Rapidly face identification of eccentric in picture has drawn significant research interests and led to various applications. We investigate the problem of rapidly labelling appearances of eccentric in TV or picture material with their names. The contribution of this paper is two-fold: (1) we propose a generative model, named eccentric picture, to depict the temporal character correspondence between picture and script, from which face-name relationship can be automatically learned as a model parameter, and meanwhile, video scene structure can be effectively inferred as a hidden state sequence; (2) we find fast algorithms to accelerate both model parameter learning and state inference, resulting in an efficient and global optimal alignment. We first segment scenes in the movie by analysis and alignment of script and movie. Then we conduct sub story discovery and content attention analysis based on the scene analysis and character interaction features. Different from the existing methods that are categorized as static captioning, dynamic captioning puts scripts at suitable positions to help hearing impaired audience better recognize the speaking characters.