A Computational Study of Expressive Facial Dynamics in Children with Autism

Abstract

Several studies have established that facial expressions of children with autism are often perceived as atypical, awkward or less engaging by typical adult observers. Despite this clear deficit in the quality of facial expression production, very little is understood about its underlying mechanisms and characteristics. This paper takes a computational approach to studying details of facial expressions of children with high functioning autism (HFA). The objective is to uncover those characteristics of facial expressions, notably distinct from those in typically developing children, and which are otherwise difficult to detect by visual inspection. We use motion capture data obtained from subjects with HFA and typically developing subjects while they produced various facial expressions. This data is analyzed to investigate how the overall and local facial dynamics of children with HFA differ from their typically developing peers. Our major observations include reduced complexity in the dynamic facial behavior of the HFA group arising primarily from the eye region.

Children with autism spectrum disorder produce more ambiguous and less socially meaningful facial expressions: an experimental study using random forest classifiers

“…The groups of Grossman and Narayanan showed that children with ASD had less synchrony of motion between facial regions and a higher level of variability [27] and that they displayed less complex facial dynamics (assessed by multiple scale entropy), specifically in the eye region [28]. In their last study, they also showed that distance features were less predictive of the emotional valence for FEs in ASD than in typical participants [29].…”

Computational Analysis of Deep Visual Data for Quantifying Facial Expression Production

“…This is due to the fact that computational analysis of facial expressions in digital images is an emerging research topic: there are only a few attempts to quantify facial expression production [17] whereas most of the scientific productions aim at the easier task of evaluating the ability to recognize if either a facial expression is present or not [18]. Very recently, some pioneering studies introduced advanced approaches to get computational outcomes able to numerically prove only the differences in facial skills of ASD vs. TD children groups [19][20][21][22]. Other approaches focused instead on detecting early risk markers of ASD.…”

“…For each work the involved computer vision tasks are indicated and, in the last column, the validation process put in place is mentioned. In particular, from the last column, it is possible to derive that works in [19][20][21][22] did not consider any quantitative evaluation but just a qualitative analysis of the outcomes to highlight the differences in affective abilities of ASD vs. TD groups. [16] x x x expert clinician [15] x manual annotation [13] x x human rater [14] x ASD vs. TD [19] x ASD vs. TD [20] x ASD vs. TD [21] x ASD vs. TD [22] x ASD vs. TD [24] x diagnostic labels (ASD/non-ASD) [23] x x expert human raters (smiling/not smiling)) [8] x expert psychologists (only on ASD Group)…”

Proceedings of the Fifth Workshop on Computational Linguistics and Clinical Psychology: From Keyboard to Clinic

“…Building on existing knowledge about language production (Bone et al, 2013(Bone et al, , 2014Heeman et al, 2010;Tanaka et al, 2014;Goodkind et al, 2018;Parish-Morris et al, 2016b) and facial movements in ASD (Yirmiya et al, 1989;Borsos and Gyori, 2017;Guha et al, 2018;Owada et al, 2018), as well as the known interrelation between the two domains (Busso and Narayanan, 2007), this study investigates patterns of word production and mouth movements during natural conversation. Our goal is to test whether an underlying dimension of cognitive-motor restriction can be detected across multiple behavioral domains in ASD.…”

“…Individuals with ASD produce flattened facial expressions (Yirmiya et al, 1989) that are hard to read (Brewer et al, 2016), and overt facial expression mimicry is impaired (Yoshimura et al, 2015). Reduced complexity in facial behavior, particularly in the eye region, while participants produced various facial expressions has been reported (Guha et al, 2018). Limited research, however, has examined facial expressions and oral-motor movement in dynamic social contexts such as conversations.…”