Emotion Recognition System for Autism Children using Non-verbal Communication
R. Santhoshkumar1, M. Kalaiselvi Geetha2

1R. Santhosh Kumar, (Research Scholar), Department of CSE, Annamalai University, (Chidambaram), Tamil Nadu, India.
2M. Kalaiselvi Geetha, (Research Scholar), Department of CSE, Annamalai University, (Chidambaram), Tamil Nadu, India.
Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 159-165 | Volume-8 Issue-8, June 2019 | Retrieval Number: G6234058719/19©BEIESP
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: Human beings can express their emotions through various ways, such as facial expression, bodily expressions, prosody, or language. Autism Spectrum Disorder (ASD) is a lifelong neuro developmental disorder, characterized by varying levels of deficit in social and communications skills. This paper aims to predict basic emotions from children with autism spectrum disorder (ASD) using body movements. The facial expression is difficult for ASD children to recognize emotion. The author proposed the body movement patterns to detect the type of emotions of ASD children. In this paper 12 dimensional body movement features (angle, distance, velocity and acceleration) from head, Lhand, R-hand are proposed for predict the emotion from children body movements. The dataset for this experiment is autism children’s recorded videos (5-11 years, n=10). The extracted features are given to the Support Vector Machine (SVM) and the Random Forest (RF) classifier to predict the children emotions. The performance measure can be calculated using quantitative analysis. Our finding shows that children have gradual ease in recognizing the following emotions: angry, fear, happy, sad and neutral.
Keyword: Autism Spectrum Disorder, Emotion recognition, non-verbal communication, Body movements, Body expressive feature, Support Vector Machine (SVM) and the Random Forest (RF) classifier.
Scope of the Article: Multimedia Communications