Facial Age Estimation.

Abstract

In the last few years, human age estimation from face images attracted the attention of many researchers in computer vision and machine learning fields. This is due to its numerous applications. In this thesis, we propose a two new architectures for age estimation based on facial images.The first one is mainly based on a cascade of classification trees ensembles, which are known recently as a Deep Random Forest (DRF). This first proposed architecture is composed of two types of DRF. The first type extends and enhances the feature representation of a given facial descriptor. The second type operates on the fused form of all enhanced representations in order to provide a prediction for the age while taking into account the fuzziness property of the human age. While the proposed methodology is able to work with all kinds of image features, the face descriptors adopted in this work used off-the-shelf deep features allowing to retain both the rich deep features and the powerful enhancement and decision provided by the proposed architecture. Experiments conducted on six public databases prove the superiority of the proposed architecture over other state-of-the-art methods. Next we propose a method which extends and improves the previous work. This new second scheme composed of Deep Random Forests (DRF) and tensor based subspace learning before applying the DRFs. The training set of the face features are showed as a 3D tensor. Multi-linear Principal Component (MWPCA) and Tensor Exponential Discriminant (TEDA) are used. After that, features passed through DRFs to estimate the age. Tests conducted on five open confront databases appear that the strategy can compete with numerous state-of-the craftsmanship strategies.