Cas Peal May 2026

is a large-scale Chinese face database created to evaluate face recognition algorithms, specifically focusing on four key types of variations known as PEAL : P ose, E xpression, A ccessories, and L ighting .

The database systematically varies images across these categories: Cas Peal

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 is a large-scale Chinese face database created to

: Contains images of 1,040 individuals (595 males and 445 females). Core "PEAL" Features : Contains images of 1,040

: The dataset provides metadata such as eye positions, face pose angles, and expression labels to help refine detection systems.

: Includes various facial expressions such as neutral, smile, surprise, frown, and closed eyes.

: Features images taken under 15 different lighting directions to test an algorithm's robustness to shadows and illumination changes. Database Specifications