People in videos from people in pictures

We propose an appearance based model for face recognition in news videos using an enormously large databank of still images. This is a step towards building an elaborate face-query system using multimodal audio-visual data. We use the fact that faces of the same person appear similar than of different people. We preprocess the videos, apply feature extraction, feature matching and a unique parallel line matching algorithm to develop a simple yet a powerful face recognition system. We tested our approach on real world data and the results show good performance both for high resolution still images and low resolution news videos without involving any training or tasks like face rectification, warping etc. It can be incorporated as part of a larger multimodal news video analysis system with problems of time alignment between text and faces. Our results show that this simple approach also works well where video modality is the only source of information.

[1]  Andrew Zisserman,et al.  Automatic face recognition for film character retrieval in feature-length films , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

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

[3]  Yee Whye Teh,et al.  Faces and names in the news , 2004, CVPR 2004.

[4]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[5]  Jun Yang,et al.  Finding Person X: Correlating Names with Visual Appearances , 2004, CIVR.

[6]  Diane Gershon,et al.  In the picture , 1990, Nature.

[7]  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.

[8]  Pinar Duygulu Sahin,et al.  A Graph Based Approach for Naming Faces in News Photos , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).