Infant AFAR: Automated facial action recognition in infants

Automated facial expression measurement in a longitudinal sample of 4- and 8-month-olds: Baby FaceReader 9 and manual coding of affective expressions

Facial expressions are among the earliest behaviors infants use to express emotional states, and are crucial to preverbal social interaction. Manual coding of infant facial expressions, however, is laborious and poses limitations to replicability. Recent developments in computer vision have advanced automated facial expression analyses in adults, providing reproducible results at lower time investment. Baby FaceReader 9 is commercially available software for automated measurement of infant facial expressions, but has received little validation. We compared Baby FaceReader 9 output to manual micro-coding of positive, negative, or neutral facial expressions in a longitudinal dataset of 58 infants at 4 and 8 months of age during naturalistic face-to-face interactions with the mother, father, and an unfamiliar adult. Baby FaceReader 9's global emotional valence formula yielded reasonable classification accuracy (AUC = .81) for discriminating manually coded positive from negative/neutral facial expressions; however, the discrimination of negative from neutral facial expressions was not reliable (AUC = .58). Automatically detected a priori action unit (AU) configurations for distinguishing positive from negative facial expressions based on existing literature were also not reliable. A parsimonious approach using only automatically detected smiling (AU12) yielded good performance for discriminating positive from negative/neutral facial expressions (AUC = .86). Likewise, automatically detected brow lowering (AU3+AU4) reliably distinguished neutral from negative facial expressions (AUC = .79). These results provide initial support for the use of selected automatically detected individual facial actions to index positive and negative affect in young infants, but shed doubt on the accuracy of complex a priori formulas.

Human and machine recognition of dynamic and static facial expressions: prototypicality, ambiguity, and complexity

A growing body of research suggests that movement aids facial expression recognition. However, less is known about the conditions under which the dynamic advantage occurs. The aim of this research was to test emotion recognition in static and dynamic facial expressions, thereby exploring the role of three featural parameters (prototypicality, ambiguity, and complexity) in human and machine analysis. In two studies, facial expression videos and corresponding images depicting the peak of the target and non-target emotion were presented to human observers and the machine classifier (FACET). Results revealed higher recognition rates for dynamic stimuli compared to non-target images. Such benefit disappeared in the context of target-emotion images which were similarly well (or even better) recognised than videos, and more prototypical, less ambiguous, and more complex in appearance than non-target images. While prototypicality and ambiguity exerted more predictive power in machine performance, complexity was more indicative of human emotion recognition. Interestingly, recognition performance by the machine was found to be superior to humans for both target and non-target images. Together, the findings point towards a compensatory role of dynamic information, particularly when static-based stimuli lack relevant features of the target emotion. Implications for research using automatic facial expression analysis (AFEA) are discussed.

An Ensemble Multi-Stream Classifier for Infant needs Detection

In this paper, we propose a novel multi-stream video classifier for infant needs detection. The proposed system is an ensemble-based system that combines several machine learning to improve the overall result of the state-of-the-art algorithms. It is a multi-stream in the sense that it combines the output predictions of both audio and images of infants from every single classifier employed in the system for a unified result. This produces better performance and results compared to the previous other research techniques, which relied on only one of these modalities. For training and testing the proposed system, from the Dunstan Baby Language video collection, we built three separate datasets for videos, images, and sounds encompassing the five primary infant needs that require predicting. These are: hunger, have wind, uncomfortable (require diaper change), wants to burp or tired, with a total of 3348 samples. We used four different ensemble algorithms for the best reachable performance. The proposed algorithm improves the overall accuracies of each single classifier from a low of 51% to a high of 99%. The proposed method also improves the accuracy of the classification process by about 9% compared to the state-of-the-art approaches, which was 90%.

Reconstructing 3D Face of Infants in Social Interactions Using Morphable Models of Non-Infants

3D morphable models (3DMMs) simultaneously reconstruct facial morphology, expression and pose from 2D images, and thus could be an invaluable tool for capturing and characterizing the face and facial behavior in early childhood. However, 3DMM fitting on infants is a largely unexplored problem. All publicly available 3DMMs are developed for adults, and it is unclear if and to what extent they can be used on videos of infants. In this paper, we compare five state-of-the-art 3DMM fitting methods on data from naturalistic infant-caregiver interactions. Results suggest that it is possible to produce consistent and subject-specific reconstructions of 3D shape identity from multiple frames, but not from a single frame. Qualitative evaluation highlights that facial regions with high texture variation, such as eyes, brows and mouth, are captured with higher accuracy compared to the rest of the face. Thus, even though a 3DMM developed for adults has significant limitations when reconstructing the morphology of the entire facial region of infants, applications that involve analysis of facial behavior can be feasible. Our encouraging results, combined with the unique ability of 3DMMs to disentangle two major sources of noise for expression analysis (i.e., identity bias and pose variations), motivate future research on using 3DMMs to measure the facial behavior of infants.