For micro-expression recognition: Database and suggestions

The impact of briefly observing faces in opaque facial masks on emotion recognition and empathic concern

Since the outbreak of SARS-CoV-2 in 2019, there have been global public health initiatives that have advocated for the community use of face masks to reduce spread of the virus. Although the community use of facial coverings has been deemed essential for public health, there have been calls for enquiries to ascertain how face masks may impact non-verbal methods of communication. This study aimed to ascertain how the brief observations of faces in opaque facial coverings could impact facial emotion recognition. It was also an aim to ascertain if there was an association between the levels of empathic concern and facial emotion recognition when viewing masked faces. An opportunity sample of 199 participants, who resided in the United Kingdom, were randomly assigned to briefly observe either masked (n = 102) or unmasked (n = 97) faces. Participants in both conditions were required to view a series of facial expressions, from the Radboud Faces Database, with models conveying the emotional states of anger, disgust, fear, happiness, sadness, and surprised. Each face was presented to participants for a period of 250 ms in the masked and unmasked conditions. A 6 (emotion type) x 2 (masked/unmasked condition) mixed ANOVA revealed that viewing masked faces significantly reduced facial emotion recognition of disgust, fear, happiness, sadness, and surprised. However, there were no differences in the success rate of recognising the emotional state of anger between the masked and unmasked conditions. Furthermore, higher levels of empathic concern were associated with greater success in facially recognising the emotional state of disgust. The results of this study suggest that significant reductions in emotion recognition, when viewing faces in opaque masks, can still be observed when people are exposed to facial stimuli for a brief period of time.

Micro-Expression Recognition Based on Optical Flow and PCANet+

Micro-expressions are rapid and subtle facial movements. Different from ordinary facial expressions in our daily life, micro-expressions are very difficult to detect and recognize. In recent years, due to a wide range of potential applications in many domains, micro-expression recognition has aroused extensive attention from computer vision. Because available micro-expression datasets are very small, deep neural network models with a huge number of parameters are prone to over-fitting. In this article, we propose an OF-PCANet+ method for micro-expression recognition, in which we design a spatiotemporal feature learning strategy based on shallow PCANet+ model, and we incorporate optical flow sequence stacking with the PCANet+ network to learn discriminative spatiotemporal features. We conduct comprehensive experiments on publicly available SMIC and CASME2 datasets. The results show that our lightweight model obviously outperforms popular hand-crafted methods and also achieves comparable performances with deep learning based methods, such as 3D-FCNN and ELRCN.

A False Trail to Follow: Differential Effects of the Facial Feedback Signals From the Upper and Lower Face on the Recognition of Micro-Expressions

Micro-expressions, as fleeting facial expressions, are very important for judging people’s true emotions, thus can provide an essential behavioral clue for lie and dangerous demeanor detection. From embodied accounts of cognition, we derived a novel hypothesis that facial feedback from upper and lower facial regions has differential effects on micro-expression recognition. This hypothesis was tested and supported across three studies. Specifically, the results of Study 1 showed that people became better judges of intense micro-expressions with a duration of 450 ms when the facial feedback from upper face was enhanced via a restricting gel. Additional results of Study 2 showed that the recognition accuracy of subtle micro-expressions was significantly impaired under all duration conditions (50, 150, 333, and 450 ms) when facial feedback from lower face was enhanced. In addition, the results of Study 3 also revealed that blocking the facial feedback of lower face, significantly boosted the recognition accuracy of subtle and intense micro-expressions under all duration conditions (150 and 450 ms). Together, these results highlight the role of facial feedback in judging the subtle movements of micro-expressions.

Objective Classes for Micro-Facial Expression Recognition

Micro-expressions are brief spontaneous facial expressions that appear on a face when a person conceals an emotion, making them different to normal facial expressions in subtlety and duration. Currently, emotion classes within the CASME II dataset (Chinese Academy of Sciences Micro-expression II) are based on Action Units and self-reports, creating conflicts during machine learning training. We will show that classifying expressions using Action Units, instead of predicted emotion, removes the potential bias of human reporting. The proposed classes are tested using LBP-TOP (Local Binary Patterns from Three Orthogonal Planes), HOOF (Histograms of Oriented Optical Flow) and HOG 3D (3D Histogram of Oriented Gradient) feature descriptors. The experiments are evaluated on two benchmark FACS (Facial Action Coding System) coded datasets: CASME II and SAMM (A Spontaneous Micro-Facial Movement). The best result achieves 86.35% accuracy when classifying the proposed 5 classes on CASME II using HOG 3D, outperforming the result of the state-of-the-art 5-class emotional-based classification in CASME II. Results indicate that classification based on Action Units provides an objective method to improve micro-expression recognition.

New Talent Signals: Shiny New Objects or a Brave New World?

Almost 20 years after McKinsey introduced the idea of a war for talent, technology is disrupting the talent identification industry. From smartphone profiling apps to workplace big data, the digital revolution has produced a wide range of new tools for making quick and cheap inferences about human potential and predicting future work performance. However, academic industrial–organizational (I-O) psychologists appear to be mostly spectators. Indeed, there is little scientific research on innovative assessment methods, leaving human resources (HR) practitioners with no credible evidence to evaluate the utility of such tools. To this end, this article provides an overview of new talent identification tools, using traditional workplace assessment methods as the organizing framework for classifying and evaluating new tools, which are largely technologically enhanced versions of traditional methods. We highlight some opportunities and challenges for I-O psychology practitioners interested in exploring and improving these innovations.