Boosted Features for Face Authentication
Marsyita Binti Hanafi, Wan Azizun Wan Adnan · Applied Mechanics and Materials · 2014
Boosted features developed using face signatures in combination with Gentle Adaboost algorithm offer alternative features for face authentication and face recognition. Face signatures are face representations extracted from Trace transform and Gentle Adaboost is used to enhance the performance of the features extracted from the face signatures. In this paper, we demonstrate the usefulness of the constructed features with experiments on BANCA database.