Scheduled System Maintenance on May 29th, 2015:
IEEE Xplore will be upgraded between 11:00 AM and 10:00 PM EDT. During this time there may be intermittent impact on performance. We apologize for any inconvenience.
By Topic

An enhanced independent component-based human facial expression recognition from video

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Uddin, M.Z. ; Dept. of Biomed. Eng., Kyung Hee Univ., Yongin, South Korea ; Lee, J.J. ; Kim, T.-S.

Facial expression recognition (FER) from video is an essential research area in the field of human computer interfaces (HCI). In this work, we present a new method to recognize several facial expressions from time sequential facial expression images. To produce robust facial expression features, enhanced independent component analysis (EICA) is utilized to extract locally independent component (IC) features which are further classified by Fisher linear discriminant analysis (FLDA). Using these features, discrete hidden Markov models (HMMs) are utilized to model different facial expressions such as joy, anger, and sad. Performance of our proposed FER system is compared against four other conventional feature extraction approaches (i.e., PCA, PCA-FLDA, ICA, and EICA) in conjunction with the same HMM scheme. The experimental results using the Cohn-Kanade database of facial expression videos show that our proposed system yields much improved recognition rate reaching the mean recognition rate of 93.23% whereas the conventional methods yield 82.92% at best.

Published in:

Consumer Electronics, IEEE Transactions on  (Volume:55 ,  Issue: 4 )