Abstract
We investigate how pressure-sensitive smart textiles, in the form of a headband, can detect changes in facial expressions that are indicative of emotions and cognitive activities. Specifically, we present the Expressure system that performs surface pressure mechanomyography on the forehead using an array of textile pressure sensors that is not dependent on specific placement or attachment to the skin. Our approach is evaluated in systematic psychological experiments. First, through a mimicking expression experiment with 20 participants, we demonstrate the system’s ability to detect well-defined facial expressions. We achieved accuracies of 0.824 to classify among three eyebrow movements (0.333 chance-level) and 0.381 among seven full-face expressions (0.143 chance-level). A second experiment was conducted with 20 participants to induce cognitive loads with N-back tasks. Statistical analysis has shown significant correlations between the Expressure features on a fine time granularity and the cognitive activity. The results have also shown significant correlations between the Expressure features and the N-back score. From the 10 most facially expressive participants, our approach can predict whether the N-back score is above or below the average with 0.767 accuracy.
Highlights
Over the last decade, physiological wearable monitoring has made tremendous advances, and more and more robust systems suitable for long-term everyday use are becoming available.Psychological monitoring, on the other hand, has been slower to make real-world impacts, mostly due to the fact that it requires more complex, often more subtle, sensing that is more difficult to implement in an unobtrusive, robust wearable form factor
We present Expressure (EXpression detected by PRESSURE), a novel approach to using wearable textile MMG in the form of an unobtrusive wearable device to monitor cognitive and emotional states on the basis of facial expressions
The accuracy of inferring emotional states from facial expressions of derived/complex emotions is lower compared to that of universal emotions. Current standards such as Facial Action Coding System (FACS) classifies facial expression based on the facial muscle movements from 44 action units (AU) [32]
Summary
Physiological wearable monitoring has made tremendous advances, and more and more robust systems suitable for long-term everyday use are becoming available. While video-based face expression analysis methods have produced excellent results, they are unsuitable for wearable applications as they require a camera with a good view of the user’s face. We propose to use textile pressure mapping (TPM) arrays unobtrusively integrated into a headband to sense the mechanical deformation and muscle motions directly It requires no electrical contact with the skin and, because of the array nature of the sensor, has no strict requirements on sensor placement (other than being placed roughly on the forehead). The approach, known as surface pressure mechanomyography (MMG), can be used both as an alternative sensing method to EMG or together with EMG to reduce errors and motion artifacts While it has been well studied (see related work) on legs, arms and upper body muscles; there is very little work on using MMG for facial expression recognition. This is a significant advantage compared to systems based on individual force sensitive resistors (FSR) sensors (such as [24] and our abandoned early prototype)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
