Analysis of emotion recognition from facial expressions using spatial and transform domain methods
by P. Suja; Shikha Tripathi
International Journal of Advanced Intelligence Paradigms (IJAIP), Vol. 7, No. 1, 2015

Abstract: Facial expressions are non-verbal signs that play an important role in interpersonal communications. There are six basic universally accepted emotions viz., happiness, surprise, anger, sadness, fear and disgust. An emotion recognition system is used for recognising different expressions from the facial images/videos and classifying them into one of the six basic emotions. Spatial domain methods are more popularly used in literature in comparison to transform domain methods. In this paper, two approaches viz., cropped face and whole face methods for feature extraction are implemented separately on the images taken from Cohn-Kanade (CK) and JAFFE databases. Classification is performed using K-nearest neighbour and neural network. The results are compared and analysed. The results suggest that transform domain techniques yield better accuracy than spatial domain techniques and cropped face approach outperforms whole face approach for both the databases for few feature extraction methods. Such systems find application in human computer interaction, entertainment industry and could be used for clinical diagnosis.

Online publication date: Thu, 02-Jul-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Advanced Intelligence Paradigms (IJAIP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com