Cas Peal -
: 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.
: Images are captured from multiple angles using a horizontal semicircular camera array to simulate different head rotations. Cas Peal
: Features images taken under 15 different lighting directions to test an algorithm's robustness to shadows and illumination changes. Database Specifications
The database systematically varies images across these categories: : Contains images of 1,040 individuals (595 males
: The full database includes 99,594 images, while a publicly available subset called CAS-PEAL-R1 contains 30,900 images.
: The dataset provides metadata such as eye positions, face pose angles, and expression labels to help refine detection systems. : Features images taken under 15 different lighting
Enhanced Local Texture Feature Sets for Face Recognition ... - HAL