Answers are grounded in this paper and cite their sources.
Facial expressions are usually linked to emotional states of a person, and are among the most salient cues for automatic emotion recognition. They are an indispensable social communication tool, and therefore, they can also be fabricated to face complex situations in social interaction. Despite efforts to either deliberately or unconsciously conceal an emotion, micro-expressions are usually leaked. Because of their revealing nature, potential applications can arise from automatically detecting them, both at a personal and inter-personal levels. Therefore, we explored micro-expression detection using a wearable device that detects distal facial EMG signals unobtrusively, as an alternative to Computer Vision-based detection. EMG recognition is advantageous over commonly used video recognition techniques because of its robustness against occlusion and light changes, good temporal resolution, and independence of movement. We evaluated the performance of the wearable device on micro-smile recognition. The results show the potential of EMG to detect such fast and subtle spontaneous expressions. Finally, we evaluated the device as a tool to provide affective annotations of Advertisement Videos, and social interaction in a face-to-face context while watching these stimuli.
No takes yet. Share an insight, caveat, or question.
Perusquía-Hernández et al. (2017) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: