TY - GEN
T1 - Analysis of human attractiveness using manifold kernel regression
AU - Davis, B. C.
AU - Lazebnik, S.
PY - 2008
Y1 - 2008
N2 - This paper uses a recently introduced manifold kernel regression technique to explore the relationship between facial shape and attractiveness on a heterogeneous dataset of over three thousand images gathered from the Web. Using the concept of the Fréchet mean of images under a diffeomorphic transformation model, we evolve the average face as a function of attractiveness ratings. Examining these averages and associated deformation maps enables us to discern aggregate shape change trends for male and female faces.
AB - This paper uses a recently introduced manifold kernel regression technique to explore the relationship between facial shape and attractiveness on a heterogeneous dataset of over three thousand images gathered from the Web. Using the concept of the Fréchet mean of images under a diffeomorphic transformation model, we evolve the average face as a function of attractiveness ratings. Examining these averages and associated deformation maps enables us to discern aggregate shape change trends for male and female faces.
KW - Diffeomorphic registration
KW - Fréchet mean
KW - Human attractiveness
KW - Manifold kernel regression
UR - http://www.scopus.com/inward/record.url?scp=69949125679&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=69949125679&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2008.4711703
DO - 10.1109/ICIP.2008.4711703
M3 - Conference contribution
AN - SCOPUS:69949125679
SN - 1424417643
SN - 9781424417643
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 109
EP - 112
BT - 2008 IEEE International Conference on Image Processing, ICIP 2008 Proceedings
T2 - 2008 IEEE International Conference on Image Processing, ICIP 2008
Y2 - 12 October 2008 through 15 October 2008
ER -