What are the main datasets for age-invariant face recognition?

From Antispoofing Wiki

Four datasets are used for training age-invariant face recognition.

Four primary facial aging datasets explore age-induced effects on the human face. The biggest example is the MORPH database that provides 400,000+ images featuring 70,000 volunteers. While being licensable, it periodically updates its sample collection and specifies each person’s age, height, gender, weight, and other metadata that can be used in biometric identification.

FG-NET is a free database with 1,002 images of average quality featuring 82 volunteers. LEO_LS comprises 31,852 samples of 5;636 people (the largest time-lapse is 8 years.) PCSO_S has 147,784 mugshots of repeat criminal offenders.


Return to FAQ