PROJECT TITLE :
Latent codebook regression for facial feature localisation
A new non-parametric inferring procedure of facial feature localisation that learns regression in latent variable space is introduced. The proposed method uses regression between latent feature and motion spaces spanned by a group of bases of nonlinear feature house and motion vector house that is trained from a massive sample set in codebook. Compared with the previous methodology of using codebook or eigen-codebook, the proposed methodology achieved both a important reduction in the memory consumption without loss of accuracy and a very low computational complexity enough to run in mobile devices.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here