Robust face name graph matching for movie character identification
Automatic face identification of characters inmovies become a challenging problem due to thehuge variation of each characters. In this paper, wepresent two schemes of global face name matchingbased frame work for robust character identification.A noise insensitive character relationshiprepresentation is incorporated. We introduce an editoperation based graph matching algorithm.
The objective is to identify the faces of the characters in thevideo and label them with the corresponding names in thecast.The textual clues like cast list, scripts, subtitles and closedcaptions are usually exploited.This occurrences provides lots of movie structure andcontent.Automatic character identification is essential for semanticmovie index and retrieval, scene segmentation and otherapplications.
During face tracking and face clustering process, the noises has been generated. The performance are limited at the time of noise generation.DISADVANTAGES The time taken for detecting the face is too long. The detected face cannot be more accurate.
By using clustering mechanism, the face of the movie character is detected more accurately.ADVANTAGES In the proposed system, the face detection is performed in a minute process. The faces are identified easily in low resolution, complex background also.
Two schemes considered in robust face name graph matching algorithm First, External script resources are utilized in both schemes belong to the global matching based category. Second, The original graph is employed for face name graph representation.
In ECGM, the difference between the two graph is measured by edit distance which is a sequence of graph edit operation. The optimal match is achieved with the least edit distance.