The recognition of human facial expressions has been expected to have appli
cations in various fields, such as psychology, engineering, and so forth, a
nd many techniques have been proposed to date. However, most of the techniq
ues are based on the motions of local feature-bearing blocks, such as the e
yes and mouth, which are supposed to be closely associated with facial expr
essions. It is thus required to segment these blocks from the face image an
d to track their motions in real-time applications, resulting in high compl
exity. Furthermore, not all information on the motions of the facial expres
sions has been utilized. In this paper, a new recognition technique is prop
osed, which uses the 2D DCT of the entire facial image and a neural network
.
The segmentation of local feature-bearing blocks is not needed. The differe
nces of the DCT coefficients in the lower frequency area between neutral an
d expression-bearing images are given to a neural network to realize a mapp
ing into the facial expression space. The new technique has been applied to
a database of normalized facial images of 60 persons, with images of 40 pe
rsons used for network training and the remaining images for testing. The r
ecognition rate is 100% for the training images. A maximum recognition rate
of 95% is achieved for the testing images. (C) 1999 Scripta Technica.