Title :
Characterizing smiles in the context of video phone data compression
Author :
Tang, Li-an ; Huan, Thomas S.
Author_Institution :
Beckman Inst. for Adv. Sci. & Technol., Illinois Univ., Urbana, IL, USA
Abstract :
We propose an approach to characterizing human smiles based on the principal component analysis of the facial motion parameters. Motion vectors of a set of feature points are derived from neutral and smiling face images and a feature space is built based on those motion vectors. The principal component analysis technique is used for dimension reduction and some preliminary results of smile characterization are obtained
Keywords :
data compression; feature extraction; motion estimation; video coding; videotelephony; dimension reduction; facial motion parameters; feature points; feature space; human smiles; motion vectors; neutral face image; principal component analysis; smile characterization; smiling face image; video phone data compression; Cognitive science; Data compression; Face recognition; Humans; Motion analysis; Mouth; Principal component analysis; Speech; User interfaces; Video compression;
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-8186-7282-X
DOI :
10.1109/ICPR.1996.547028
