Cross-domain AU Detection: Domains, Learning Approaches, and Measures

Infant AFAR: Automated facial action recognition in infants

Automated detection of facial action units in infants is challenging. Infant faces have different proportions, less texture, fewer wrinkles and furrows, and unique facial actions relative to adults. For these and related reasons, action unit (AU) detectors that are trained on adult faces may generalize poorly to infant faces. To train and test AU detectors for infant faces, we trained convolutional neural networks (CNN) in adult video databases and fine-tuned these networks in two large, manually annotated, infant video databases that differ in context, head pose, illumination, video resolution, and infant age. AUs were those central to expression of positive and negative emotion. AU detectors trained in infants greatly outperformed ones trained previously in adults. Training AU detectors across infant databases afforded greater robustness to between-database differences than did training database specific AU detectors and outperformed previous state-of-the-art in infant AU detection. The resulting AU detection system, which we refer to as Infant AFAR (Automated Facial Action Recognition), is available to the research community for further testing and applications in infant emotion, social interaction, and related topics.

Novel Method for Three-Dimensional Facial Expression Recognition Using Self-Normalizing Neural Networks and Mobile Devices

Introduction To date, most ways to perform facial expression recognition rely on two-dimensional images, advanced approaches with three-dimensional data exist. These however demand stationary apparatuses and thus lack portability and possibilities to scale deployment. As human emotions, intent and even diseases may condense in distinct facial expressions or changes therein, the need for a portable yet capable solution is signified. Due to the superior informative value of three-dimensional data on facial morphology and because certain syndromes find expression in specific facial dysmorphisms, a solution should allow portable acquisition of true three-dimensional facial scans in real time. In this study we present a novel solution for the three-dimensional acquisition of facial geometry data and the recognition of facial expressions from it. The new technology presented here only requires the use of a smartphone or tablet with an integrated TrueDepth camera and enables real-time acquisition of the geometry and its categorization into distinct facial expressions. Material and Methods Our approach consisted of two parts: First, training data was acquired by asking a collective of 226 medical students to adopt defined facial expressions while their current facial morphology was captured by our specially developed app running on iPads, placed in front of the students. In total, the list of the facial expressions to be shown by the participants consisted of "disappointed", "stressed", "happy", "sad" and "surprised". Second, the data were used to train a self-normalizing neural network. A set of all factors describing the current facial expression at a time is referred to as "snapshot". Results In total, over half a million snapshots were recorded in the study. Ultimately, the network achieved an overall accuracy of 80.54% after 400 epochs of training. In test, an overall accuracy of 81.15% was determined. Recall values differed by the category of a snapshot and ranged from 74.79% for "stressed" to 87.61% for "happy". Precision showed similar results, whereas "sad" achieved the lowest value at 77.48% and "surprised" the highest at 86.87%. Conclusions With the present work it can be demonstrated that respectable results can be achieved even when using data sets with some challenges. Through various measures, already incorporated into an optimized version of our app, it is to be expected that the training results can be significantly improved and made more precise in the future. Currently a follow-up study with the new version of our app that encompasses the suggested alterations and adaptions, is being conducted. We aim to build a large and open database of facial scans not only for facial expression recognition but to perform disease recognition and to monitor diseases' treatment progresses.

Assessing Automated Facial Action Unit Detection Systems for Analyzing Cross-Domain Facial Expression Databases

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 the dynamic facial database remains an unmet need. This study compared the performance of three systems (FaceReader, OpenFace, 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 from the dynamic facial database at a level above chance. Moreover, OpenFace and AFAR provided higher area under the receiver operating characteristic curve values compared to FaceReader. In addition, several confusion biases of facial components (e.g., AU12 and AU14) were observed to be related to each automated AU detection system and the static mode was superior to dynamic mode for analyzing the posed facial database. These findings demonstrate the features of prediction patterns for each system and provide guidance for research on facial expressions.

Crossing Domains for AU Coding: Perspectives, Approaches, and Measures

Facial action unit (AU) detectors have performed well when trained and tested within the same domain. How well do AU detectors transfer to domains in which they have not been trained? We review literature on cross-domain transfer and conduct experiments to address limitations of prior research. We evaluate generalizability in four publicly available databases. EB+ (an expanded version of BP4D+), Sayette GFT, DISFA and UNBC Shoulder Pain (SP). The databases differ in observational scenarios, context, participant diversity, range of head pose, video resolution, and AU base rates. In most cases performance decreased with change in domain, often to below the threshold needed for behavioral research. However, exceptions were noted. Deep and shallow approaches generally performed similarly and average results were slightly better for deep model compared to shallow one. Occlusion sensitivity maps revealed that local specificity was greater for AU detection within than cross domains. The findings suggest that more varied domains and deep learning approaches may be better suited for generalizability and suggest the need for more attention to characteristics that vary between domains. Until further improvement is realized, caution is warranted when applying AU classifiers from one domain to another.

D-PAttNet: Dynamic Patch-Attentive Deep Network for Action Unit Detection

Facial action units (AUs) relate to specific local facial regions. Recent efforts in automated AU detection have focused on learning the facial patch representations to detect specific AUs. These efforts have encountered three hurdles. First, they implicitly assume that facial patches are robust to head rotation; yet non-frontal rotation is common. Second, mappings between AUs and patches are defined a priori, which ignores co-occurrences among AUs. And third, the dynamics of AUs are either ignored or modeled sequentially rather than simultaneously as in human perception. Inspired by recent advances in human perception, we propose a dynamic patch-attentive deep network, called D-PAttNet, for AU detection that (i) controls for 3D head and face rotation, (ii) learns mappings of patches to AUs, and (iii) models spatiotemporal dynamics. D-PAttNet approach significantly improves upon existing state of the art.