Extended LBP based Facial Expression Recognition System for Adaptive AI Agent Behaviour

Kamlesh Mistry, Jyoti Jasekar, Biju Issac, Li Zhang

Research output: Contribution to conferencePaperResearchpeer-review

24 Downloads (Pure)

Abstract

Automatic facial expression recognition is widely
used for various applications such as health care, surveillance
and human-robot interaction. In this paper, we present a novel
system which employs automatic facial emotion recognition
technique for adaptive AI agent behaviour. The proposed
system is equipped with kirsch operator based local binary
patterns for feature extraction and diverse classifiers for
emotion recognition. First, we nominate a novel variant of the
local binary pattern (LBP) for feature extraction to deal with
illumination changes, scaling and rotation variations. The
features extracted are then used as input to the classifier for
recognizing seven emotions. The detected emotion is then used
to enhance the behaviour selection of the artificial intelligence
(AI) agents in a shooter game. The proposed system is
evaluated with multiple facial expression datasets and
outperformed other state-of-the-art models by a significant
margin.
Original languageEnglish
Publication statusAccepted/In press - 15 Mar 2018
EventInternational Joint Conference on Neural Networks (IJCNN) under IEEE World Congress on Computational Intelligence (WCCI 2018) - Rio de Janerio, Brazil
Duration: 8 Jul 201813 Jul 2018
http://www.ecomp.poli.br/~wcci2018/

Conference

ConferenceInternational Joint Conference on Neural Networks (IJCNN) under IEEE World Congress on Computational Intelligence (WCCI 2018)
Abbreviated titleIJCNN-WCCI-2018
CountryBrazil
CityRio de Janerio
Period8/07/1813/07/18
Internet address

Fingerprint

Artificial intelligence
Feature extraction
Classifiers
Human robot interaction
Health care

Bibliographical note

This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Cite this

Mistry, K., Jasekar, J., Issac, B., & Zhang, L. (Accepted/In press). Extended LBP based Facial Expression Recognition System for Adaptive AI Agent Behaviour. Paper presented at International Joint Conference on Neural Networks (IJCNN) under IEEE World Congress on Computational Intelligence (WCCI 2018), Rio de Janerio, Brazil.
Mistry, Kamlesh ; Jasekar, Jyoti ; Issac, Biju ; Zhang, Li. / Extended LBP based Facial Expression Recognition System for Adaptive AI Agent Behaviour. Paper presented at International Joint Conference on Neural Networks (IJCNN) under IEEE World Congress on Computational Intelligence (WCCI 2018), Rio de Janerio, Brazil.
@conference{4ec2c6752b4a402bbdcc0a2406fe8c9f,
title = "Extended LBP based Facial Expression Recognition System for Adaptive AI Agent Behaviour",
abstract = "Automatic facial expression recognition is widelyused for various applications such as health care, surveillanceand human-robot interaction. In this paper, we present a novelsystem which employs automatic facial emotion recognitiontechnique for adaptive AI agent behaviour. The proposedsystem is equipped with kirsch operator based local binarypatterns for feature extraction and diverse classifiers foremotion recognition. First, we nominate a novel variant of thelocal binary pattern (LBP) for feature extraction to deal withillumination changes, scaling and rotation variations. Thefeatures extracted are then used as input to the classifier forrecognizing seven emotions. The detected emotion is then usedto enhance the behaviour selection of the artificial intelligence(AI) agents in a shooter game. The proposed system isevaluated with multiple facial expression datasets andoutperformed other state-of-the-art models by a significantmargin.",
author = "Kamlesh Mistry and Jyoti Jasekar and Biju Issac and Li Zhang",
note = "This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible; International Joint Conference on Neural Networks (IJCNN) under IEEE World Congress on Computational Intelligence (WCCI 2018), IJCNN-WCCI-2018 ; Conference date: 08-07-2018 Through 13-07-2018",
year = "2018",
month = "3",
day = "15",
language = "English",
url = "http://www.ecomp.poli.br/~wcci2018/",

}

Mistry, K, Jasekar, J, Issac, B & Zhang, L 2018, 'Extended LBP based Facial Expression Recognition System for Adaptive AI Agent Behaviour' Paper presented at International Joint Conference on Neural Networks (IJCNN) under IEEE World Congress on Computational Intelligence (WCCI 2018), Rio de Janerio, Brazil, 8/07/18 - 13/07/18, .

Extended LBP based Facial Expression Recognition System for Adaptive AI Agent Behaviour. / Mistry, Kamlesh; Jasekar, Jyoti ; Issac, Biju; Zhang, Li.

2018. Paper presented at International Joint Conference on Neural Networks (IJCNN) under IEEE World Congress on Computational Intelligence (WCCI 2018), Rio de Janerio, Brazil.

Research output: Contribution to conferencePaperResearchpeer-review

TY - CONF

T1 - Extended LBP based Facial Expression Recognition System for Adaptive AI Agent Behaviour

AU - Mistry, Kamlesh

AU - Jasekar, Jyoti

AU - Issac, Biju

AU - Zhang, Li

N1 - This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

PY - 2018/3/15

Y1 - 2018/3/15

N2 - Automatic facial expression recognition is widelyused for various applications such as health care, surveillanceand human-robot interaction. In this paper, we present a novelsystem which employs automatic facial emotion recognitiontechnique for adaptive AI agent behaviour. The proposedsystem is equipped with kirsch operator based local binarypatterns for feature extraction and diverse classifiers foremotion recognition. First, we nominate a novel variant of thelocal binary pattern (LBP) for feature extraction to deal withillumination changes, scaling and rotation variations. Thefeatures extracted are then used as input to the classifier forrecognizing seven emotions. The detected emotion is then usedto enhance the behaviour selection of the artificial intelligence(AI) agents in a shooter game. The proposed system isevaluated with multiple facial expression datasets andoutperformed other state-of-the-art models by a significantmargin.

AB - Automatic facial expression recognition is widelyused for various applications such as health care, surveillanceand human-robot interaction. In this paper, we present a novelsystem which employs automatic facial emotion recognitiontechnique for adaptive AI agent behaviour. The proposedsystem is equipped with kirsch operator based local binarypatterns for feature extraction and diverse classifiers foremotion recognition. First, we nominate a novel variant of thelocal binary pattern (LBP) for feature extraction to deal withillumination changes, scaling and rotation variations. Thefeatures extracted are then used as input to the classifier forrecognizing seven emotions. The detected emotion is then usedto enhance the behaviour selection of the artificial intelligence(AI) agents in a shooter game. The proposed system isevaluated with multiple facial expression datasets andoutperformed other state-of-the-art models by a significantmargin.

M3 - Paper

ER -

Mistry K, Jasekar J, Issac B, Zhang L. Extended LBP based Facial Expression Recognition System for Adaptive AI Agent Behaviour. 2018. Paper presented at International Joint Conference on Neural Networks (IJCNN) under IEEE World Congress on Computational Intelligence (WCCI 2018), Rio de Janerio, Brazil.