Automatic child-face age-progression based on heritability factors of familial faces

Abstract

This paper presents a novel age progression method specifically developed for children that incorporates genetic facial features of siblings and parents to synthetically predict the child's facial appearance up to adult years. The proposed approach is the first age-progression technique that directly incorporates familial data with Active Appearance Models (AAM). This work introduces a novel data set that contains longitudinal face images of children and siblings.