Performance Optimization Algorithms in Classification Face Emotion Recognition
Main Article Content
Abstract
The work areas for emotion recognition are facial expressions, vocal, gesture and physiology signal. Facial expressions are one of
most functional areas for face emotion recognition. For best results we should similar eye and lip as regular and irregular ellipse. The main
purpose of this paper is introducing an Imperialist Competitive Algorithm (ICA) to optimize eye and lip ellipse characteristics. Then
performance of three optimization methods including Imperialist Competitive Algorithm (ICA), Particle Swarm Optimization (PSO) and Genetic
Algorithm (GA) for this issue will be discussed. This process involves three stages pre-processing, feature extraction and classification. Firstly a
series of pre-processing tasks such as adjusting contrast, filtering, skin color segmentation and edge detection are done. One of important tasks at
this stage after pre-processing is feature extraction. Projection profile method to reason has high speed and high precision used in feature
extraction. Secondly ICA, GA and PSO are used to optimize eye and lip ellipse characteristics. Finally in the third stage with using features
obtained on optimal ellipse eye and lip, emotion a person according to experimental results have been classified. The obtained results show that
success rate and running speed in ICA is better than PSO and these two parameters for PSO are better than GA.
Keywords: Face emotion recognition, Projection profile, Imperialist Competitive Algorithm (ICA), Particle Swarm Optimization (PSO)
algorithm and Genetic algorithm (GA).
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.