: Subjects are photographed wearing different accessories, including various pairs of glasses and different types of caps.
: The dataset provides metadata such as eye positions, face pose angles, and expression labels to help refine detection systems.
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 .
: Contains images of 1,040 individuals (595 males and 445 females).
Researchers use this data to benchmark various algorithms, including Principal Component Analysis (PCA) and Local Binary Patterns (LBP) , ensuring they can handle the diverse conditions found in practical applications.
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
The database systematically varies images across these categories:
Enhanced Local Texture Feature Sets for Face Recognition ... - HAL
