The project entitled “Video-Based Face Recognition” is used for automatic face identification of characters in movies. Recognition of face in videos has drawn significant research interests and lead to many interesting applications. Automatic face identification of characters in videos is a challenging problem due to the huge variation in the appearance of each character. Although existing methods demonstrate promising results in the clean environment, the performances are limited in complex movie scenes due to the noises generated during the face tracking and face clustering process. In this system, two schemes of a global face-name matching based framework are proposed for robust character identification.