Publication of Little Lion Scientific R & D , Islamabad PAKISTAN CHARACTER IDENTIFICATION IN VIDEOS USING IRIS RECOGNITION

In Character based browsing which is predominant in films, the identification of speaking faces plays a vital role. After identifying the speaking face, cl ustering of those faces is a difficult task. The di fficulty is in extracting the exact speaking faces and clustering them. In the existing techniques, lip movement of a character is taken as Region Of Interest (ROI) for identifying the faces in the films. For clustering those faces, the k-means clustering technique is used. By using the above technique, retrieval of speaking f aces cannot produce an accurate result. So, in this pape r, li movement as ROI and IRIS recognition for clustering of speaking faces are used. This paper proposes a mechanism to generate precise results by comparing with the existing techniques.

[1]  Takeo Kanade,et al.  Name-It: association of face and name in video , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Cedric Nishan Canagarajah,et al.  A Unified Framework for Object Retrieval and Mining , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[3]  Changsheng Xu,et al.  Character Identification in Feature-Length Films Using Global Face-Name Matching , 2009, IEEE Transactions on Multimedia.

[4]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[5]  A. Umamakeswari,et al.  Object Based Video Analysis, Interpretation and Tracking , 2007 .

[6]  S. Natarajan An efficient Video Segmentation Algorithm with Real time Adaptive Threshold Technique , 2009 .

[7]  Rong Yan,et al.  Multiple instance learning for labeling faces in broadcasting news video , 2005, MULTIMEDIA '05.