Identification of Aging Faces using A-stack Classification Model

The problem of time validity of biometric models has received only a marginal attention from researchers. In this paper, we investigate the aging influence on the classifier scores of genuine client. Our studies show that as age progresses the classifier scores of genuine user hold a decreasing tendency, which leads to the degrading identification performance. Actual and up-to-date at the time of their creation, extracted features and models relevant to a person's face may eventually become outdated, leading to a failure in the face identification task. If physical characteristics of the individual change over time, their classification model has to be updated. Alternatively in this paper we propose an A-stack scheme, which is based on the concept of classifier stacking and makes use of age information and baseline classifier scores, in order to improve the identification performance during age progression. Our experiments on the YouTube and MORPH data show that the use of the proposed technique allows for improving the identification accuracy as opposed to the baseline classifier