Facial Expression Recognition using Robust Algorithm based on Modern Machine Learning Technique
Shashank M Gowda1, H N Suresh2

1Prof. Shashank M Gowda*, Assistant Professor, Department of Electronics and Communication Engineering, Yenepoya Institute of Technology, Moodbidri (Karnataka), India
2Dr. H. N. Suresh, Professor and Head, Department of Electronics & Instrumentation Engineering, Bangalore Institute of Technology, Bangalore (Karnataka), India.
Manuscript received on 20 April 2022. | Revised Manuscript received on 25 April 2022. | Manuscript published on 30 June 2022. | PP: 30-40 | Volume-11 Issue-5, June 2022. | Retrieval Number: 100.1/ijeat.E35350611522 | DOI: 10.35940/ijeat.E3535.0611522
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Recently facial expression recognition has turned out to be an interesting field in research because of more demand for security and the advancement of mobile devices. Due to many serious incidents like terrorists’ attack, there arises more concern to develop the security systems mainly in certain places like airports and border crossings where identification and verification are mandatory. On the other hand, these surveillance systems aid to identify the missing person, even though it is based on robust facial expression recognition algorithms and on the developed database for facial expression recognition. However, the human faces are complex and multidimensional which make the facial gesture extraction to be very challenging. Obviously, in high secured applications facial expression recognition (FER) systems are mandatory to avoid incidents. In this paper, the automatic facial expression recognition system is developed based on the machine learning algorithms for classification. This research reveals the identification of FER for the ease of communication. Hybridization of Adaptive Kernel function based Extreme Learning Machine with Chicken Swarm Optimization (HAKELM-CSO) algorithm is introduced for identifying the accurate facial expression among the large database. In this work, an approach is developed by applying the machine learning techniques for the automated classification on the image region. The major purpose of this research work is to overcome the flaws of traditional algorithms and to improve the process of facial expression recognition which could be used in various applications. 
Keywords: Facial, Machine Learning, HAKELM-CSO, Pre-processing, Weiner Filter.
Scope of the Article: Machine Learning