Emotion Recognition from Facial Expressions using Images with Pose, Illumination and Age Variation for Human-Computer/Robot Interaction
Publication Type:Journal Article
Source:Journal of ICT Research and Applications, ITB Publisher, Indonesia, Volume 12, Issue 1, p.14-34 (2018)
Keywords:Dept. of Electronics and communication Engineering.
<p>A technique for emotion recognition from facial expressions in images with simultaneously varying pose, illumination and age at real time is proposed in this paper. The basic emotions that are considered are anger, disgust, happy, surprise and neutral. Feature vector formed from images of CMU-MultiPIE database for pose and illumination is used for training the classifier. For real time implementation, Raspberry Pi II is used which can be placed on a robot to recognize emotions in interactive real time applications. The proposed method includes face detection using Viola Jones Haar cascade, Active Shape Model (ASM) for feature extraction and Adaboost classifier for classification at real time. Performance of the proposed method is validated at real time by testing with subjects from different age groups expressing basic emotions with varying pose and illumination. 96% accuracy with an average time of 120ms for recognition has been obtained. The results are encouraging as the proposed method gives better accuracy with higher speed compared to methods existing in literature. The major contribution and strength of the proposed method lies in marking of suitable feature points on face, speed and invariance to pose, illumination and age at real time.</p>