Automated Analysis of Children Emotion Expression Levels

Despite the advancement in the field of facial emotion expression analysis, less attention has been given for facial emotion expression and emotion level analysis in children. This paper presents three novel findings in the area of child emotion expression. Identifying and validating the AU stimulation of children, automating the child emotion and level of emotion prediction and age wise analysis of child emotion expression. Emotion predictions were compared resulting through deep learning methods such as 3DCNN and machine learning approaches using EFA.AU stimulation results generated through EFA are consistent with the FACS. Through AU analysis, the paper shows that a child video or image can be predicted for the expressed emotion and its level with 91.04% accuracy through KNN classifier. While the 3DCNN approach resulted in 82.64% accuracy, the age wise emotion prediction through CNN resulted in the range of 60% to 86.6%. Though all approaches evidenced comparable results in emotion prediction, the emotion level prediction through EFA and AU outperformed 3DCNN and CNN approaches in all cases. Happy emotion prediction in age wise emotion analysis resulted in a higher accuracy over sad and disgust emotions. As emotion level prediction in age wise analysis display mixed results, a further research on age wise AU stimulation is encouraged.

I. Introduction

Identification of universal facial expressions [1] is a wide area of research at present. Facial action coding system (FACS) [2] is a comprehensive, anatomy based system for describing all visually discernible facial movements. It breaks down facial expressions into individual components of muscle movement, called Action Units (AUs) which provide different clues about facial expressions and act as indicators to identify abnormalities. Many attempts have been taken in improvising the ability to detect AU in facial features. Research [3] addresses the difficulties faced by the existing AU detection mechanisms in learning the facial features and provides a comprehensive study on the AUs controlling head and face rotation of adults. Research [4] focuses on the affect of differing domains such as gender diversity, participant diversity and video resolution in detecting the AU behaviors where they provide the considerations to be taken when applying the AU classifiers from one domain to another. Even though many have focused on the detection of AUs in facial features, less work have been carried out in identifying the mapping of AUs in relation to the emotional stimulation.