Age Estimation Guided Convolutional Neural Network for Age-Invariant Face Recognition

Authors:
  • TZTianyue Zheng
    Tianyue Zheng
  • WDWeihong Deng
    Weihong Deng
  • JHJiani Hu
    Jiani Hu

Abstract
While very promising results have been shown on face recognition related problems, age-invariant face recognition still remains a challenge. Facial appearance of a person changes over time, which results in significant intraclass variations. In order to address this problem, we propose a novel deep face recognition network called age estimation guided convolutional neural network (AE-CNN) to separate the variations caused by aging from the personspecific features which are stable. The carefully designed CNN model can learn age-invariant features for face recognition. To the best of our knowledge, this is the first attempt to use age estimation task for obtaining age-invariant features. Extensive results on two well-known public domain face aging datasets: MORPH Album 2 and CACD show the effectiveness of the proposed approach.

This publication has 20 references indexed in Scilit: