Human face aging with guided prediction and detail synthesis

Abstract

In this paper, we present an example-based method to estimate the aging process of a human face. To tackle the difficulty of collecting considerable chronological photos of individuals, we utilize a two-layer strategy. Based on a sparse aging database, an EM-PCA-based algorithm with the personal guidance vector is first applied to conjecture the temporal variations of a target face. Since the subspace-based prediction may not preserve detailed creases, we propose synthesizing facial details with a separate texture dataset. Besides automatic simulation, the proposed framework can also include further guidance, e.g., parents\' impact vector or users\' indication of wrinkles. Our estimated results can improve feature point positions and user evaluation demonstrates that the two-layer approach provides more reasonable aging prediction.