Description: Frontal views of all subjects are videotaped under
constant illumination using fixed light sources, and none
of the subjects wear eyeglasses. These constraints are
imposed to minimize optical flow degradation. Previously
untrained subjects are video recorded performing a series
of expressions, and the image sequences are coded by
certified FACS coders. Facial expressions are analyzed in
digitized image sequences of arbitrary length (expression
sequences neutral to peak vary 9 to 44 frames).
60 subjects, both male and female, the larger
database were used in this study. The study includes more
than 260 image sequences and 5000 images. Subjects
ranged in age (18-35) and ethnicity (Caucasian, African-
American, and Asian/Indian).
To Search:
File list (Check if you may need any files):
multisvm.m
Download