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 dataset provides metadata such as eye positions, face pose angles, and expression labels to help refine detection systems. Cas Peal
: Includes various facial expressions such as neutral, smile, surprise, frown, and closed eyes. Researchers use this data to benchmark various algorithms,
: Images are captured from multiple angles using a horizontal semicircular camera array to simulate different head rotations. : Images are captured from multiple angles using
: Subjects are photographed wearing different accessories, including various pairs of glasses and different types of caps.
: The full database includes 99,594 images, while a publicly available subset called CAS-PEAL-R1 contains 30,900 images.
: Features images taken under 15 different lighting directions to test an algorithm's robustness to shadows and illumination changes. Database Specifications