Could Micro-Expressions be Quantified? Electromyography Gives Affirmative Evidence

Abstract

Micro-expressions (MEs) are brief, subtle facial expressions that reveal concealed emotions, offering key behavioral cues for social interaction. Characterized by short duration, low intensity, and spontaneity, MEs have been mostly studied through subjective coding, lacking objective, quantitative indicators. This paper explores ME characteristics using facial electromyography (EMG), analyzing data from 147 macro-expressions (MaEs) and 233 MEs collected from 35 participants. First, regarding external characteristics, we demonstrate that MEs are short in duration and low in intensity. Precisely, we proposed an EMG-based indicator, the percentage of maximum voluntary contraction (MVC\%), to measure ME intensity. Moreover, we provided precise interval estimations of ME intensity and duration, with MVC\% ranging from 7\% to 9.2\% and the duration ranging from 307 ms to 327 ms. This research facilitates fine-grained ME quantification. Second, regarding the internal characteristics, we confirm that MEs are less controllable and consciously recognized compared to MaEs, as shown by participants responses and self-reports. This study provides a theoretical basis for research on ME mechanisms and real-life applications. Third, building on our previous work, we present CASMEMG, the first public ME database including EMG signals, providing a robust foundation for studying micro-expression mechanisms and movement dynamics through physiological signals.

Figures (15)

• Figure 1: Overview of EMG-based ME characteristic quantification. Our research process is divided into three main parts: Video and EMG collection, Expression temporal annotation and ME characteristic analysis. During this process, a ME database containing EMG and video, named CASMEMG, was naturally developed.
• Figure 2: Equipment layout based on data collection and transmission
• Figure 3: Data acquisition setup. Participants were recorded on video while watching emotional stimuli. Simultaneously, EMG signals were captured through electrodes attached to the participant's face and EMG module. Furthermore, the digital tube displays helped the coder synchronize the frames in the recorded video with the EMG signals. This example image is selected from recorded videos with the participant's consent.
• Figure 4: Electrode position distribution for facial EMG signal acquisition based on seven facial muscles
• Figure 5: Four steps of EMG signal pre-processing: removing DC offset, denoise, full-wave rectification, and linear envelope. (a) Raw EMG data; (b) EMG with DC Offset Removed; (c) EMG with Noise Removed; (d) EMG with Full-Wave Rectification; (e) Linear Envelope of EMG.