: The full database includes 99,594 images, while a publicly available subset called CAS-PEAL-R1 contains 30,900 images.
The database was developed by the Joint Research & Development Laboratory (JDL) of the Chinese Academy of Sciences (CAS). Its primary purpose is to provide researchers with a robust dataset for training and testing algorithms against real-world visual challenges. Core "PEAL" Features
: Images are captured from multiple angles using a horizontal semicircular camera array to simulate different head rotations.