Facial Action Coding System

1. In the present research, we test the assumption that emotional mimicry and contagion are moderated by group membership. We report two studies using facial electromyography (EMG; Study 1), Facial Action Coding System (FACS; Study 2), and self-reported emotions (Study 2) as dependent measures. As predicted, both studies show that ingroup anger and fear displays were mimicked to a greater extent than outgroup displays of these emotions. The self-report data in Study 2 further showed specific divergent reactions ...

The advance of computing technology has provided the means for building intelligent vehicle systems. Drowsy driver detection system is one of the potential applications of intelligent vehicle systems. Previous approaches to drowsiness detection primarily make pre-assumptions about the relevant behavior, focusing on blink rate, eye closure, and yawning. Here we employ machine learning to datamine actual human behavior during drowsiness episodes. Automatic classifiers for 30 facial actions from the Facial Action Coding system were developed using machine learning on a separate database of spontaneous expressions. These facial actions include blinking and yawn motions, as well as a number of other facial movements. In addition, head motion was collected through automatic eye tracking and an accelerometer. These measures were passed to learning-based classifiers such as Adaboost and multinomial ridge regression. The system was able to predict sleep and crash episodes during a driving computer game with 96% accuracy within subjects and above 90% accuracy across subjects. This is the highest prediction rate reported to date for detecting real drowsiness. Moreover, the analysis revealed new information about human behavior during drowsy driving.

Many approaches to facial expression recognition focus on assessing the six basic emotions (anger, disgust, happiness, fear, sadness, and surprise). Real-life situations proved to produce many more subtle facial expressions. A reliable way of analyzing the facial behavior is the Facial Action Coding System (FACS) developed by Ekman and Friesen, which decomposes the face into 46 action units (AU) and is usually performed by a human observer. Each AU is related to the contraction of one or more specific facial muscles. In this study we present an approach towards automatic AU recognition enabling recognition of an extensive palette of facial expressions. As distinctive features we used motion flow estimators between every two consecutive frames, calculated in special regions of interest (ROI). Even though a lot has been published on the facial expression recognition theme, it is still difficult to draw a conclusion regarding the best methodology as there is no common basis for compari...

Facial expression has been a focus of emotion research for over a hundred years (Darwin, 1872/1998). It is central to several leading theories of emotion (Ekman, 1992; Izard, 1977; Tomkins, 1962) and has been the focus of at times heated debate about issues in emotion science (Ekman, 1973, 1993; Fridlund, 1992; Russell, 1994). Facial expression figures prominently in research on almost every aspect of emotion, including psychophysiology (Levenson, Ekman, & Friesen, 1990), neural bases (Calder et al., 1996; Davidson, Ekman, ...

The facial action coding system (FACS) was used to examine recognition rates in 105 healthy young men and women who viewed 128 facial expressions of posed and evoked happy, sad, angry and fearful emotions in color photographs balanced for gender and ethnicity of poser. Categorical analyses determined the specificity of individual action units for each emotion. Relationships between recognition rates for different emotions and action units were evaluated using a logistic regression model. Each emotion could be identified by a group of action units, characteristic to the emotion and distinct from other emotions. Characteristic happy expressions comprised raised inner eyebrows, tightened lower eyelid, raised cheeks, upper lip raised and lip corners turned upward. Recognition of happy faces was associated with cheek raise, lid tightening and outer brow raise. Characteristic sad expressions comprised furrowed eyebrow, opened mouth with upper lip being raised, lip corners stretched and turned down, and chin pulled up. Only brow lower and chin raise were associated with sad recognition. Characteristic anger expressions comprised lowered eyebrows, eyes wide open with tightened lower lid, lips exposing teeth and stretched lip corners. Recognition of angry faces was associated with lowered eyebrows, upper lid raise and lower lip depression. Characteristic fear expressions comprised eyes wide open, furrowed and raised eyebrows and stretched mouth. Recognition of fearful faces was most highly associated with upper lip raise and nostril dilation, although both occurred infrequently, and with inner brow raise and widened eyes. Comparisons are made with previous studies that used different facial stimuli.

The facial action coding system (FAGS) is an objective method for quantifying facial movement in terms of component actions. This paper explores and compares techniques for automatically recognizing facial actions in sequences of images. These techniques include: analysis of facial motion through estimation of optical flow; holistic spatial analysis, such as principal component analysis, independent component analysis, local feature analysis, and linear discriminant analysis; and methods based on the outputs of local filters, such as Gabor wavelet representations and local principal components. Performance of these systems is compared to naive and expert human subjects. Best performances were obtained using the Gabor wavelet representation and the independent component representation, both of which achieved 96 percent accuracy for classifying 12 facial actions of the upper and lower face. The results provide converging evidence for the importance of using local filters, high spatial frequencies, and statistical independence for classifying facial actions

We present a systematic comparison of machine learning methods applied to the problem of fully automatic recognition of facial expressions. We explored recognition of facial actions from the Facial Action Coding System (FACS), as well as recognition of full facial expressions. Each videoframe is first scanned in real-time to detect approximately upright-frontal faces. The faces found are scaled into image patches of equal size, convolved with a bank of Gabor energy filters, and then passed to a recognition engine that codes facial expressions into 7 dimensions in real time: neutral, anger, disgust, fear, joy, sadness, surprise. We report results on a series of experiments comparing recognition engines, including AdaBoost, support vector machines, linear discriminant analysis, as well as feature selection techniques. Best results were obtained by selecting a subset of Gabor filters using AdaBoost and then training Support Vector Machines on the outputs of the filters selected by AdaB...

The advance of computing technology has provided the means for building intelligent vehicle systems. Drowsy driver detection system is one of the potential applications of intelligent vehicle systems. Previous approaches to drowsiness detection primarily make pre-assumptions about the relevant behavior, focusing on blink rate, eye closure, and yawning. Here we employ machine learning to datamine actual human behavior during drowsiness episodes. Automatic classifiers for 30 facial actions from the Facial Action Coding system were developed using machine learning on a separate database of spontaneous expressions. These facial actions include blinking and yawn motions, as well as a number of other facial movements. In addition, head motion was collected through automatic eye tracking and an accelerometer. These measures were passed to learning-based classifiers such as Adaboost and multinomial ridge regression. The system was able to predict sleep and crash episodes during a driving computer game with 96% accuracy within subjects and above 90% accuracy across subjects. This is the highest prediction rate reported to date for detecting real drowsiness. Moreover, the analysis revealed new information about human behavior during drowsy driving.

Independently, we created descriptive systems to characterize chimpanzee facial behavior, responding to a common need to have an objective, standardized coding system to ask questions about primate facial behaviors. Even with slightly different systems, we arrive at similar outcomes, with convergent conclusions about chimpanzee facial mobility. This convergence is a validation of the importance of the approach, and provides support for the future use of a facial action coding system for chimpanzees, ChimpFACS. Chimpanzees ...

We present ongoing work on a project for automatic recognition of spon- taneous facial actions. Spontaneous facial expressions differ substan- tially from posed expressions, similar to how continuous, spontaneous speech differs from isolated words produced on command. Previous methods for automatic facial expression recognition assumed images were collected in controlled environments in which the subjects delib- erately faced the camera.