What are the main age-invariant face recognition methods?

From Antispoofing Wiki

There’s a group of methods to recognize aging faces.

A set of techniques for aging face recognition is proposed — age-invariant methods. They are separated into Generative and Non-generative groups.

The first group implies analysis of discriminative and aging models. The former pays attention to the facial features that stay permanent over the time, like facial contour. The latter learns the parametric aging model, synthesizes images and then removes aging from them.

Non-generative methods include facial mark analysis, which explores unique traits that stay more or less unchanged: freckles, birthmarks, and others. This method may fail or be spoofed with a surgery.


Return to FAQ