Format

Send to

Choose Destination
Sensors (Basel). 2018 Nov 16;18(11). pii: E3993. doi: 10.3390/s18113993.

Computational Assessment of Facial Expression Production in ASD Children.

Author information

1
Institute of Applied Sciences and Intelligent Systems, National Research Council of Italy, via Monteroni, 73100 Lecce, Italy. marco.leo@cnr.it.
2
Institute of Applied Sciences and Intelligent Systems, National Research Council of Italy, via Monteroni, 73100 Lecce, Italy. pierluigi.carcagni@cnr.it.
3
Institute of Applied Sciences and Intelligent Systems, National Research Council of Italy, via Monteroni, 73100 Lecce, Italy. cosimo.distante@cnr.it.
4
Institute of Applied Sciences and Intelligent Systems, National Research Council of Italy, via Monteroni, 73100 Lecce, Italy. paolo.spagnolo@cnr.it.
5
Institute of Applied Sciences and Intelligent Systems, National Research Council of Italy, via Monteroni, 73100 Lecce, Italy. pierluigi.mazzeo@cnr.it.
6
Amici di Nico Onlus, Via Campania, 6, 73046 Lecce, Italy. annachiara.rosato@libero.it.
7
USI, Institute of Communication and Health, Via Buffi 6, 6900 Lugano, Switzerland. serena.petrocchi@usi.ch.
8
L' Adelfia Onlus, via S. Sangiovanni, 115-73031 Lecce, Italy. chiara.pellegrino@yahoo.it.
9
Dipartimento di Storia, University of Salento, Società e Studi Sull' Uomo, Studium 2000-Edificio 5-Via di Valesio, 73100 Lecce, Italy. annalisa.levante@unisalento.it.
10
Dipartimento di Storia, University of Salento, Società e Studi Sull' Uomo, Studium 2000-Edificio 5-Via di Valesio, 73100 Lecce, Italy. filomena.delume@unisalento.it.
11
Dipartimento di Storia, University of Salento, Società e Studi Sull' Uomo, Studium 2000-Edificio 5-Via di Valesio, 73100 Lecce, Italy. flavia.lecciso@unisalento.it.

Abstract

In this paper, a computational approach is proposed and put into practice to assess the capability of children having had diagnosed Autism Spectrum Disorders (ASD) to produce facial expressions. The proposed approach is based on computer vision components working on sequence of images acquired by an off-the-shelf camera in unconstrained conditions. Action unit intensities are estimated by analyzing local appearance and then both temporal and geometrical relationships, learned by Convolutional Neural Networks, are exploited to regularize gathered estimates. To cope with stereotyped movements and to highlight even subtle voluntary movements of facial muscles, a personalized and contextual statistical modeling of non-emotional face is formulated and used as a reference. Experimental results demonstrate how the proposed pipeline can improve the analysis of facial expressions produced by ASD children. A comparison of system's outputs with the evaluations performed by psychologists, on the same group of ASD children, makes evident how the performed quantitative analysis of children's abilities helps to go beyond the traditional qualitative ASD assessment/diagnosis protocols, whose outcomes are affected by human limitations in observing and understanding multi-cues behaviors such as facial expressions.

KEYWORDS:

ASD diagnosis and assessment; geometrical and temporal regularization of facial action units; quantitative facial expression analysis

PMID:
30453518
PMCID:
PMC6263710
DOI:
10.3390/s18113993
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center