What’s in a Smile? Initial Analyses of Dynamic Changes in Facial Shape and Appearance

Single-level principal component analysis (PCA) and multi-level PCA (mPCA) methods are applied here to a set of (2D frontal) facial images from a group of 80 Finnish subjects (34 male; 46 female) with two different facial expressions (smiling and neutral) per subject. Inspection of eigenvalues gives...

Full description

Bibliographic Details
Main Authors: Damian J.J. Farnell, Jennifer Galloway, Alexei I. Zhurov, Stephen Richmond, David Marshall, Paul L. Rosin, Khtam Al-Meyah, Pertti Pirttiniemi, Raija Lähdesmäki
Format: Article
Language:English
Published: MDPI AG 2018-12-01
Series:Journal of Imaging
Subjects:
Online Access:http://www.mdpi.com/2313-433X/5/1/2
_version_ 1828381612583157760
author Damian J.J. Farnell
Jennifer Galloway
Alexei I. Zhurov
Stephen Richmond
David Marshall
Paul L. Rosin
Khtam Al-Meyah
Pertti Pirttiniemi
Raija Lähdesmäki
author_facet Damian J.J. Farnell
Jennifer Galloway
Alexei I. Zhurov
Stephen Richmond
David Marshall
Paul L. Rosin
Khtam Al-Meyah
Pertti Pirttiniemi
Raija Lähdesmäki
author_sort Damian J.J. Farnell
collection DOAJ
description Single-level principal component analysis (PCA) and multi-level PCA (mPCA) methods are applied here to a set of (2D frontal) facial images from a group of 80 Finnish subjects (34 male; 46 female) with two different facial expressions (smiling and neutral) per subject. Inspection of eigenvalues gives insight into the importance of different factors affecting shapes, including: biological sex, facial expression (neutral versus smiling), and all other variations. Biological sex and facial expression are shown to be reflected in those components at appropriate levels of the mPCA model. Dynamic 3D shape data for all phases of a smile made up a second dataset sampled from 60 adult British subjects (31 male; 29 female). Modes of variation reflected the act of smiling at the correct level of the mPCA model. Seven phases of the dynamic smiles are identified: rest pre-smile, onset 1 (acceleration), onset 2 (deceleration), apex, offset 1 (acceleration), offset 2 (deceleration), and rest post-smile. A clear cycle is observed in standardized scores at an appropriate level for mPCA and in single-level PCA. mPCA can be used to study static shapes and images, as well as dynamic changes in shape. It gave us much insight into the question “what’s in a smile?”.
first_indexed 2024-12-10T04:18:00Z
format Article
id doaj.art-3e90e7781ffb421ebc1aaa00f4dd1f2c
institution Directory Open Access Journal
issn 2313-433X
language English
last_indexed 2024-12-10T04:18:00Z
publishDate 2018-12-01
publisher MDPI AG
record_format Article
series Journal of Imaging
spelling doaj.art-3e90e7781ffb421ebc1aaa00f4dd1f2c2022-12-22T02:02:32ZengMDPI AGJournal of Imaging2313-433X2018-12-0151210.3390/jimaging5010002jimaging5010002What’s in a Smile? Initial Analyses of Dynamic Changes in Facial Shape and AppearanceDamian J.J. Farnell0Jennifer Galloway1Alexei I. Zhurov2Stephen Richmond3David Marshall4Paul L. Rosin5Khtam Al-Meyah6Pertti Pirttiniemi7Raija Lähdesmäki8School of Dentistry, Cardiff University, Heath Park, Cardiff CF14 4XY, UKSchool of Dentistry, Cardiff University, Heath Park, Cardiff CF14 4XY, UKSchool of Dentistry, Cardiff University, Heath Park, Cardiff CF14 4XY, UKSchool of Dentistry, Cardiff University, Heath Park, Cardiff CF14 4XY, UKSchool of Computer Science and Informatics, Cardiff University, CF24 3AA Cardiff, UKSchool of Computer Science and Informatics, Cardiff University, CF24 3AA Cardiff, UKSchool of Computer Science and Informatics, Cardiff University, CF24 3AA Cardiff, UKResearch Unit of Oral Health Sciences, Faculty of Medicine, University of Oulu, FI-90014, Oulu, FinlandResearch Unit of Oral Health Sciences, Faculty of Medicine, University of Oulu, FI-90014, Oulu, FinlandSingle-level principal component analysis (PCA) and multi-level PCA (mPCA) methods are applied here to a set of (2D frontal) facial images from a group of 80 Finnish subjects (34 male; 46 female) with two different facial expressions (smiling and neutral) per subject. Inspection of eigenvalues gives insight into the importance of different factors affecting shapes, including: biological sex, facial expression (neutral versus smiling), and all other variations. Biological sex and facial expression are shown to be reflected in those components at appropriate levels of the mPCA model. Dynamic 3D shape data for all phases of a smile made up a second dataset sampled from 60 adult British subjects (31 male; 29 female). Modes of variation reflected the act of smiling at the correct level of the mPCA model. Seven phases of the dynamic smiles are identified: rest pre-smile, onset 1 (acceleration), onset 2 (deceleration), apex, offset 1 (acceleration), offset 2 (deceleration), and rest post-smile. A clear cycle is observed in standardized scores at an appropriate level for mPCA and in single-level PCA. mPCA can be used to study static shapes and images, as well as dynamic changes in shape. It gave us much insight into the question “what’s in a smile?”.http://www.mdpi.com/2313-433X/5/1/2multilevel principal components analysisshape and image texturefacial expression
spellingShingle Damian J.J. Farnell
Jennifer Galloway
Alexei I. Zhurov
Stephen Richmond
David Marshall
Paul L. Rosin
Khtam Al-Meyah
Pertti Pirttiniemi
Raija Lähdesmäki
What’s in a Smile? Initial Analyses of Dynamic Changes in Facial Shape and Appearance
Journal of Imaging
multilevel principal components analysis
shape and image texture
facial expression
title What’s in a Smile? Initial Analyses of Dynamic Changes in Facial Shape and Appearance
title_full What’s in a Smile? Initial Analyses of Dynamic Changes in Facial Shape and Appearance
title_fullStr What’s in a Smile? Initial Analyses of Dynamic Changes in Facial Shape and Appearance
title_full_unstemmed What’s in a Smile? Initial Analyses of Dynamic Changes in Facial Shape and Appearance
title_short What’s in a Smile? Initial Analyses of Dynamic Changes in Facial Shape and Appearance
title_sort what s in a smile initial analyses of dynamic changes in facial shape and appearance
topic multilevel principal components analysis
shape and image texture
facial expression
url http://www.mdpi.com/2313-433X/5/1/2
work_keys_str_mv AT damianjjfarnell whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance
AT jennifergalloway whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance
AT alexeiizhurov whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance
AT stephenrichmond whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance
AT davidmarshall whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance
AT paullrosin whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance
AT khtamalmeyah whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance
AT perttipirttiniemi whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance
AT raijalahdesmaki whatsinasmileinitialanalysesofdynamicchangesinfacialshapeandappearance