Using Feed Forward Network to Increase the Accuracy in Face Emotion Recognition
Main Article Content
Abstract
One of best and easiest methods for emotion recognition is facial expressions. Facial expression gives important information about
emotion of a person. Face emotion recognition is one of main applications machine vision that widely attended in recent years. It can be used in
areas of security, entertainment and human machine interface (HMI). Emotion recognition usually uses of science image processing, speech
processing, gesture signal processing and physiological signal processing. In this paper a new algorithm using feed forward neural network
based on a set of images to face emotion recognition has been proposed. We recommend use of eyes and lip as biometric elements for face
emotion recognition. Face emotion recognition process involves three stages pre-processing, feature extraction and classification. One of biggest
problems in classification emotions is overlap in range of values. To increase accuracy in face emotion recognition we recommend use of feed
forward neural network. The obtained results show that success rate and running speed in PSO algorithm has improved with feed forward neural
network.
Â
Keywords: Face Emotion Recognition, Projection Profile, Particle Swarm Optimization (PSO), Feed Forward Neural Network.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.