2020
DOI: 10.3390/s20041199
|View full text |Cite
|
Sign up to set email alerts
|

Differences in Facial Expressions between Spontaneous and Posed Smiles: Automated Method by Action Units and Three-Dimensional Facial Landmarks

Abstract: Research on emotion recognition from facial expressions has found evidence of different muscle movements between genuine and posed smiles. To further confirm discrete movement intensities of each facial segment, we explored differences in facial expressions between spontaneous and posed smiles with three-dimensional facial landmarks. Advanced machine analysis was adopted to measure changes in the dynamics of 68 segmented facial regions. A total of 57 normal adults (19 men, 38 women) who displayed adequate pose… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
19
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
9
1

Relationship

1
9

Authors

Journals

citations
Cited by 24 publications
(19 citation statements)
references
References 45 publications
0
19
0
Order By: Relevance
“…The visual analysis revealed that the distribution of the activation value of the proposed model appears around the eyes and lips, including the eyebrows, whereas in the case of the common method using a posed smile as the anchor, the activation value only appears in a portion of the face and not in the eyebrows. In particular, the visualizations obtained using the two models showed significant differences in the eyebrows and around the eyes, which is very important because the spatiotemporal features around the eyes have been used as the main features in related works [ 14 , 19 , 20 , 21 , 22 , 23 , 43 ]. This observation demonstrates that a more meaningful metric feature of the L1-norm distance layer can be extracted when using a neutral expression as an anchor than when using a genuine and imposter pair.…”
Section: Discussionmentioning
confidence: 99%
“…The visual analysis revealed that the distribution of the activation value of the proposed model appears around the eyes and lips, including the eyebrows, whereas in the case of the common method using a posed smile as the anchor, the activation value only appears in a portion of the face and not in the eyebrows. In particular, the visualizations obtained using the two models showed significant differences in the eyebrows and around the eyes, which is very important because the spatiotemporal features around the eyes have been used as the main features in related works [ 14 , 19 , 20 , 21 , 22 , 23 , 43 ]. This observation demonstrates that a more meaningful metric feature of the L1-norm distance layer can be extracted when using a neutral expression as an anchor than when using a genuine and imposter pair.…”
Section: Discussionmentioning
confidence: 99%
“…Movements of the orolabial region can be voluntary or spontaneous, contributing in different ways to our verbal and non-verbal expressions [7][8][9]. In the middle and lower parts of the face, lips opening may result from different neural pathways [10].…”
Section: Introductionmentioning
confidence: 99%
“…Few studies have utilized face stimuli of humans expressing genuine, spontaneous expressions of emotion, whether static or dynamic (Cassidy et al, 2014). This distinction is important because research has shown that the human brain, and artificial intelligence (AI) systems, process posed facial expressions differently compared to how spontaneous expressions of emotion are processed (Hess et al, 1989;Schmidt et al, 2006;Wang et al, 2015;Park et al, 2020).…”
Section: Introductionmentioning
confidence: 99%