Abstract
In this paper, an Eigenvector based system has been presented to recognize facial expressions from digital facial images. In the approach, firstly the images were acquired and cropping of five significant portions from the image was performed to extract and store the Eigenvectors specific to the expressions. The Eigenvectors for the test images were also computed, and finally the input facial image was recognized when similarity was obtained by calculating the minimum Euclidean distance between the test image and the different expressions.
Highlights
A human face carries a lot of important information while interacting to one another
As per the study of Mehrabian [1], amongst the human communication, facial expressions comprises 55% of the message transmitted in comparison to the 7% of the communication information conveyed by linguistic language and 38% by paralanguage
Aleksic and Katsaggelos [9] developed a www.ijacsa.thesai.org (IJACSA) International Journal of Advanced Computer Science and Applications, Vol 4, No 2, 2013 facial expression recognition system utilizing these facial action parameters basically describing the eyebrow and the outer lip features, and classifying up to 93.66% of the test expressions by calculating the maximum likelihoods generated by the multistream hidden markov model (MS-HMM)
Summary
A human face carries a lot of important information while interacting to one another. As per the study of Mehrabian [1], amongst the human communication, facial expressions comprises 55% of the message transmitted in comparison to the 7% of the communication information conveyed by linguistic language and 38% by paralanguage. This shows that the facial expression forms the major mode of interaction between the man and machine. A set of 10 images for each basic expression is processed and Eigenvectors specific to the expressions are stored.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: International Journal of Advanced Computer Science and Applications
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.