Abstract
Hidden factor analysis ( HFA ) has been widely used in age invariant face recognition systems. It decomposes facial features into independent age factor and identity factor. Age invariant face recognition systems utilize identity factor for face recognition; however, the age factor remains unutilized . The age component of the hidden factor analysis model depends on the subject's age, hence it carries a significant age related information. In this paper, we propose the HFA model based discriminative manifold learning method for age estimation. Further, multiple regression methods are applied on low dimensional features learned from the aging subspace. Extensive experiments are performed on a large scale aging database MORPH II and the accuracy of our method is found superior to the current state-of-the-art methods.
Tied Factor Analysis for Face Recognition across Large Pose Differences