Facial expression synthesis images using hybrid neural network with particle swarm optimisation techniques
by Deepti Chandra; Rajendra Hegadi; Sanjeev Karmakar
International Journal of Biomedical Engineering and Technology (IJBET), Vol. 31, No. 1, 2019

Abstract: In the advance life trend, the facial expression is the visual facial outer structure of the human affective state, intellectual action, and human interchanges and facial expression go about as the key role in the movement of communication. In this paper, the facial expression synthesis performance is done using different facial expressions such as angry, sad, smile, surprise and cry of various peoples. In the proposed method, two procedures are used namely hybrid neural network (HNN) and particle swarm optimisation (PSO) algorithm. By training particle swarm optimisation and hybrid neural network, we take the desired output. In the result section, various evaluation metrics namely peak signal to noise ratio (PSNR), mean square error (MSE) and a second-derivative-like measure of enhancement (SDME) value is calculated using diverse algorithms. In this evaluation performance, the particle swarm optimisation is given enhanced output while comparing it with other techniques and the existing methods of facial expression.

Online publication date: Tue, 23-Jul-2019

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 Biomedical Engineering and Technology (IJBET):
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