Face Recognition: The Face Database



We conduct experiments using a database of 960 bitmap images of 120 individuals (60 male, 60 female), extracted from the AR Face Database provided by Martinez and Benavente*.  We separate the database into two disjoint sets: i) The training set, containing 60 images of different people of various gender, race and age taken under natural lighting conditions with neutral expression; ii) the test set containing 900 images (15 images of 60 people of various gender, race and age).  Each of the 15 images were taken under the conditions described in the table below.  All images are scaled and rotated such that the centres of the eyes are aligned, using our eye detection algorithm (not described here).
 
Lighting
     
Expressions
Natural
From the left
From the right
From left & right
Neutral expression
Day 1, Day 2 
Day 1, Day 2 
Day 1, Day 2 
Day 1, Day 2 
Happy expression
Day 1, Day 2 
-
-
-
Angry expression
Day 1, Day 2 
-
-
-
Mouth covered
Day 1
Day 1
Day 1
-



The above images are examples indicating the image capture conditions represented in the
database, however none of these images are actually included in the database.


*[A.M. Martinez, R. Benavente. “The AR Face Database.” CVC Technical Report #24, 1998] - The AR Face Database.