Scientific publications
Read about the research that supports the FaceReader Ecosystem
Over the past 20+ years, our facial coding platform and its embedded technologies have been the subject as well as the preferred instrument for numerous accredited scientific studies. Below we present a comprehensive overview of the literature that has emerged from these studies, highlighting and validating the cutting-edge technology of FaceReader Online.
2021
2 citations
Linking teachers’ facial microexpressions with student-based evaluation of teaching effectiveness: A pilot study using FaceReader™
R. Schlag, M. Sailer
This study seeks to investigate the potential influence of facial microexpressions on student-based evaluations and explore future possibilities using automated technologies in higher education. We applied a non-experimental correlational design if number of videotaped university lecturers’ recognized by FaceReader™ serves as predictor for positive results student evaluation teaching effectiveness. Therefore, we analyzed five lectures with automatic recognition software. Additionally, each video was rated between 8-16 students, rating instrument based Murray’s (1983) factor analysis. The software could detect more than 5.000 microexpressions. Although emotions bear ‘overall performance’ rating, ‘emotions’ is not predicting b=.05, t(37)=.35, p > .05. demonstrates that ratings are affected variables just showed sympathy well estimated age lecturer predicted ratings.
2021
8 citations
Face the music: Children’s facial affect in musical imitation and improvisation tasks
J. A. Bugos, D. DeMarie, M. R. Torres, N. Fuller
The purpose of this study was to examine facial affect in young children who completed a singing task that included imitation and improvisation. Eighty-nine children (4–6 years: 45 male, 44 female participants) completed three conditions from the standard test battery (i.e., Advancing Interdisciplinary Research in Singing-Test Battery Singing Skills [AIRS-TBSS]). These conditions included singing their favorite song, imitating a song, and improvising a song ending. Facial affect was analyzed with Noldus FaceReader software, and subjective responses also were collected. Results revealed children exhibited happy emotion most prominently during the improvisation compared to the imitation condition. However, a higher percentage of surprised emotions were found frequency analysis significantly different in the range of the final note for the condition imitation. Children’s self-reported ratings of happiness were related to their displayed happiness (p < .05). Qualitative data emerging themes included familiarity, object association, and preference. Children were more positive when singing or improvising. Based on the type of vocal performance task, it is necessary to consider how children respond to tasks.
2021
26 citations
Efficiency in real-time webcam gaze tracking
A. Gudi, X Li and J. van Gemert
Efficiency and ease of use are essential for practical applications of camera-based eye/gaze-tracking. Gaze tracking involves estimating where a person is looking on a screen based on face images from a computer-facing camera. In this paper, we investigate two complementary forms of efficiency in gaze tracking: 1. The computational efficiency of the system, which is dominated by the inference speed of a CNN predicting gaze-vectors; 2. The usability efficiency, which is determined by the tediousness of the mandatory calibration of the gaze-vector to a computer screen. To do so, we evaluate the computational speed/accuracy trade-off for the CNN and the calibration effort/accuracy trade-off for screen calibration. For the CNN, we evaluate the full face, two-eyes, and single eye input. For screen calibration, we measure the number of calibration points needed and evaluate three types of calibration: 1. pure geometry, 2. pure machine learning, and 3. hybrid geometric regression. Results suggest that a single eye input and geometric regression calibration achieve the best trade-off.
2021
44 citations
Assessing Automated Facial Action Unit Detection Systems for Analyzing Cross-Domain Facial Expression Databases
S. Namba, W. Sato, M. Osumi, K. Shimokawa
In the field of affective computing, achieving accurate automatic detection of facial movements is an important issue, and great progress has already been made. However, a systematic evaluation of systems that now have access to dynamic database remains an unmet need. This study compared the performance of three systems (FaceReader, OpenFace, and AFARtoolbox) that detect each facial movement corresponding to an action unit (AU) derived from the Facial Action Coding System. All machines could detect the presence of AUs at a level above chance. Moreover, OpenFace provided higher area under receiver operating characteristic curve values than FaceReader. In addition, several confusion biases and components (e.g., AU12 and AU14) were observed to be related to the automated AU system. The static mode was superior for analyzing the posed database. These findings demonstrate that prediction patterns provide guidance for research on facial expressions.
2021
31 citations
Sensory Features, Liking and Emotions of Consumers towards Classical, Molecular and Note by Note Foods
A. Głuchowski, E. Czarniecka‐Skubina, E. Kostyra, G. Wasiak‐Zys, K. Bylinka
Modern cuisine served at top-end restaurants attempts to attract customers, who increasingly demand new flavor, pleasure, and fun. The materials were six dishes prepared using lemon or tomatoes made in the traditional (classical), molecular and Note by Note (NbN) versions. The study explores sensory characteristics, consumer liking, of key attributes, their declared sensations, emotions, as well as consumers’ facial expressions responding to dishes. These objectives were investigated using descriptive quantitative analysis tests. Tests included a 9-point hedonic scale for degree of dish, Check-All-That-Apply (CATA) and FaceReader expressions. Influence of factors associated with attitudes toward food and willingness to try in the future also determined. It was stated that product profiles represent different characteristics due to technology and production ingredients used. Neophobia and innovativeness had significant (p ≤ 0.05) effect on liking. Odor-, flavor-, texture- and overall-liking of NbN were lower than versions, but did not vary from scores of samples. Consumers experienced liking for NbN, but expected higher experienced-liking. Traditional and modern products differed in CATA terms. Classical perceived by consumers as more tasty, typical, while modern as surprising, intriguing, innovative and trendy. Mimic assessment showed similar trends for some emotions in both classical and separate temporal patterns of products.
2020
19 citations
Significance of Intensity of Swedish Massage Course in Improvement of Health Status
U. Veseta, A. Gulbe, O. Onžeevs
In this research, FaceReader software is used to explore significance of intensity of swedish massage course in improvement of health status, providing objective data on emotional responses and facial muscle activities.