Abstract

Modeling the face aging process is a challenging taskdue to large and non-linear variations present in differ-ent stages of face development. This paper presents adeep model approach for face age progression that can effi-ciently capture the non-linear aging process and automati-cally synthesize a series of age-progressed faces in variousage ranges. In this approach, we first decompose the long-term age progress into a sequence of short-term changesand model it as a face sequence. The Temporal Deep Re-stricted Boltzmann Machines based age progression modeltogether with the prototype faces are then constructed tolearn the aging transformation between faces in the se-quence. In addition, to enhance the wrinkles of faces in the later age ranges, the wrinkle models are further constructed using Restricted Boltzmann Machines to capture their variations in different facial regions. The geometry constraints are also taken into account in the last step for more consistent age-progressed results. The proposed approach isevaluated using various face aging databases, i.e. FGNET, Cross-Age Celebrity Dataset (CACD) and MORPH, and our collected large-scale aging database named AginG Faces in the Wild (AGFW). In addition, when ground-truth age is not available for input image, our proposed system is able to automatically estimate the age of the input face before aging process is employed.