List of facial expression databases: Difference between revisions

Revision as of 04:26, 8 August 2020

Latest revision as of 18:47, 26 August 2025

(25 intermediate revisions by 13 users not shown)

Line 1:

{{short description|none}}

A '''facial expression database''' is a collection of images or video clips with [[facial expression]]s of a range of [[emotions]].

Well-annotated ([[emotion]]-tagged) media content of facial behavior is essential for training, testing, and validation of [[algorithm]]s for the development of [[Emotion recognition|expression recognition systems]]. The emotion annotation can be done in [[discrete emotion theory|discrete emotion]] labels or on a continuous scale. Most of the databases are usually based on the [[basic emotions]] theory (by [[Paul Ekman]]) which assumes the existence of six discrete basic emotions (anger, fear, disgust, surprise, joy, sadness). However, some databases include the emotion tagging in continuous arousal-valence scale.

Line 4 ⟶ 5:

In posed expression databases, the participants are asked to display different basic emotional expressions, while in spontaneous expression database, the expressions are natural. Spontaneous expressions differ from posed ones remarkably in terms of intensity, configuration, and duration. Apart from this, synthesis of some AUs are barely achievable without undergoing the associated emotional state. Therefore, in most cases, the posed expressions are exaggerated, while the spontaneous ones are subtle and differ in appearance.

Many publicly available databases are categorized here.<ref>{{Cite web|url=http://emotion-research.net/wiki/Databases|title=collection of emotional databases|archive-url=https://web.archive.org/web/20180325205102/http://emotion-research.net/wiki/Databases|archive-date=2018-03-25|url-status=dead}}</ref><ref>{{Cite web|url=https://www.ecse.rpi.edu/~cvrl/database/other_facial_expression.htm|title=facial expression databases|last=|first=|date=|website=|access-date=}}</ref> Here are some details of the [[facial expression]] databases.

{| class="wikitable"

!Database

Line 14 ⟶ 15:

!Ground truth

!Type

!Remarks

|-

|FERG-3D-DB (Facial Expression Research Group 3D Database) for stylized characters <ref>Aneja, Deepali, et al. "Learning to generate 3D stylized character expressions from humans." 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2018.</ref>

Line 24:

|Emotion labels

|Frontal pose

|

|-

|Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) <ref>Livingstone & Russo (2018). The Ryerson Audio-Visual Database of

Emotional Speech and Song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. {{doi|10.1371/journal.pone.0196391

|doi-access=free}}</ref>

|Speech: Calm, happy, sad, angry, fearful, surprise, disgust, and neutral.

Song: Calm, happy, sad, angry, fearful, and neutral.

Line 39 ⟶ 38:

Ratings provided by 319 human raters

|Posed

|

|-

|Extended Cohn-Kanade Dataset (CK+)<ref>P. Lucey, J. F. Cohn, T. Kanade, J. Saragih, Z. Ambadar and I. Matthews, "The Extended Cohn-Kanade Dataset (CK+): A complete facial expression dataset for action unit and emotion-specified expression," in ''3rd IEEE Workshop on CVPR for Human Communicative Behavior Analysis'', 2010</ref>

Line 49 ⟶ 47:

|Facial expression labels and FACS (AU label for final frame in each image sequence)

|Posed; spontaneous smiles

|can be downloaded from CK website

|-

|Japanese Female Facial Expressions (JAFFE)<ref>{{Cite book | doi=10.5281/zenodo.3451524| year=1998| last1=Lyons| first1=Michael| title=The Japanese Female Facial Expression (JAFFE) Database| last2=Kamachi| first2=Miyuki| last3=Gyoba| first3=Jiro}}</ref>

|neutral, sadness, surprise, happiness, fear, anger, and disgust

|10

Line 59 ⟶ 56:

|Facial expression label

|Posed

|

|-

|MMI Database<ref>M. Valstar and M. Pantic, "Induced disgust, happiness and surprise: an addition to the MMI facial expression database," in ''Proc. Int. Conf. Language Resources and Evaluation'', 2010</ref>

Line 69 ⟶ 65:

|AU label for the image frame with apex facial expression in each image sequence

|Posed and Spontaneous

|

|-

| rowspan="3" |Belfast Database<ref>I. Sneddon, M. McRorie, G. McKeown and J. Hanratty, "The Belfast induced natural emotion database," ''IEEE Trans. Affective Computing,'' vol. 3, no. 1, pp. 32-41, 2012</ref>

Line 79 ⟶ 74:

|

| rowspan="3" |Natural Emotion

|

|-

|Set 2 (disgust, fear, amusement, frustration, surprise, anger, sadness)

Line 85 ⟶ 79:

|650 video clips

|Color

|

|

|

Line 94 ⟶ 87:

|Color

|1920*1080

|

|

|-

|Indian Semi-Acted Facial Expression Database (iSAFE)<ref>{{Cite journalbook|lastlast1=Singh|firstfirst1=Shivendra|last2=Benedict|first2=Shajulin|title=Advances in Signal Processing and Intelligent Recognition Systems |chapter=Indian Semi-Acted Facial Expression (ISAFE) Dataset for Human Emotions Recognition |date=2020|editor-last=Thampi|editor-first=Sabu M.|editor2-last=Hegde|editor2-first=Rajesh M.|editor3-last=Krishnan|editor3-first=Sri|editor4-last=Mukhopadhyay|editor4-first=Jayanta|editor5-last=Chaudhary|editor5-first=Vipin|editor6-last=Marques|editor6-first=Oge|editor7-last=Piramuthu|editor7-first=Selwyn|editor8-last=Corchado|editor8-first=Juan M.|title=Indian Semichapter-Acted Facial Expression (iSAFE) Dataset for Human Emotions Recognition|url=https://link.springer.com/chapter/10.1007/978-981-15-4828-4_13|journal=Advances in Signal Processing and Intelligent Recognition Systems|series=Communications in Computer and Information Science|volume=1209 |language=en|___location=Singapore|publisher=Springer|pages=150–162|doi=10.1007/978-981-15-4828-4_13|isbn=978-981-15-4828-4}}</ref>

|Happy, Sad, Fear, Surprise, Angry, Neutral, Disgust

|44

Line 106 ⟶ 98:

|Emotion labels

|Spontaneous

|Can be downloaded from GitHub (username: shivendra2015iiit)

|-

|DISFA<ref>S. M. Mavadati, M. H. Mahoor, K. Bartlett, P. Trinh and J. Cohn., "DISFA: A Spontaneous Facial Action Intensity Database," ''IEEE Trans. Affective Computing,'' vol. 4, no. 2, pp. 151–160, 2013</ref>

Line 116 ⟶ 107:

|AU intensity for each video frame (12 AUs)

|Spontaneous

|

|-

|Multimedia Understanding Group (MUG)<ref>N. Aifanti, C. Papachristou and A. Delopoulos, The MUG Facial Expression Database, in Proc. 11th Int. Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS), Desenzano, Italy, April 12–14, 2010.</ref>

Line 126 ⟶ 116:

|Emotion labels

|Posed

|

|-

|Indian Spontaneous Expression Database (ISED)<ref>S L Happy, P. Patnaik, A. Routray, and R. Guha,&nbsp;"The Indian Spontaneous Expression Database for&nbsp;Emotion Recognition," in IEEE Transactions on Affective Computing,&nbsp;2016, {{doi|10.1109/TAFFC.2015.2498174}}.</ref>

“The Indian Spontaneous Expression Database for&nbsp;

Emotion Recognition,” in IEEE Transactions on Affective Computing,&nbsp;

2016, {{doi|10.1109/TAFFC.2015.2498174}}.

</ref>

|sadness, surprise,&nbsp;happiness, and disgust

|50

Line 143 ⟶ 125:

|Emotion labels

|Spontaneous

|Can be downloaded from ISED website

|-

|Radboud Faces Database (RaFD)<ref>Langner, O., Dotsch, R., Bijlstra, G., Wigboldus, D.H.J., Hawk, S.T., & van Knippenberg, A. (2010). Presentation and validation of the Radboud Faces Database. Cognition & Emotion, 24(8), 1377—1388. {{doi|10.1080/02699930903485076}}</ref>

|neutral, sadness,&nbsp;contempt, surprise,&nbsp;happiness, fear, anger, and disgust

|67

Line 153 ⟶ 134:

|Emotion labels

|Posed

|

|-

|Oulu-CASIA NIR-VIS database

Line 163 ⟶ 143:

|

|Posed

|

|-

|FERG (Facial Expression Research Group Database)-DB<ref>{{Cite web|url=http://grail.cs.washington.edu/projects/deepexpr/ferg-db.html|title=Facial Expression Research Group Database (FERG-DB)|website=grail.cs.washington.edu|access-date=2016-12-06}}</ref> for stylized characters

Line 173 ⟶ 152:

|Emotion labels

|Frontal pose

|

|-

|AffectNet<ref>{{Cite journal|lastlast1=Mollahosseini|firstfirst1=A.|last2=Hasani|first2=B.|last3=Mahoor|first3=M. H.|date=2017|title=AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild|journal=IEEE Transactions on Affective Computing|volume=PP|issue=99|pages=18–31|doi=10.1109/TAFFC.2017.2740923|issn=1949-3045|arxiv=1708.03985|s2cid=37515850}}</ref>

|neutral, happy, sad, surprise, fear, disgust, anger, contempt

|

Line 184 ⟶ 162:

|Emotion labels, valence, arousal

|Wild setting

|can be downloaded from affectnet website

|-

|IMPA-FACE3D<ref>{{Cite web|url=http://app.visgraf.impa.br/database/faces/documents/|title=IMPA-FACE3D Technical Reports|website=visgraf.impa.br|access-date=2018-03-08}}</ref>

Line 194 ⟶ 171:

|Emotion labels

|Posed

|

|-

|FEI Face Database

Line 204 ⟶ 180:

|Emotion labels

|Posed

|

|-

|Aff-Wild<ref>{{Cite journalbook|lastlast1=Zafeiriou|firstfirst1=S.|last2=Kollias|first2=D.|last3=Nicolaou|first3=M.A.|last4=Papaioannou|first4=A.|last5=Zhao|first5=G.|last6=Kotsia|first6=I.|datetitle=2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) |titlechapter=Aff-Wild: Valence and Arousal in'In-the-wildWild' Challenge |date=2017|chapter-url=httphttps://openaccesseprints.thecvfmdx.comac.uk/content_cvpr_2017_workshops22045/w331/papers/Zafeiriou_Aff-Wild_Valence_and_CVPR_2017_paperaff_wild_kotsia.pdf|journalpages=Computer Vision and Pattern Recognition Workshops (1980–1987|doi=10.1109/CVPRW), .2017.248|isbn=978-1-5386-0733-6|s2cid=3107614|url=http://urn.fi/urn:nbn:fi-fe201902276466 }}</ref> <ref>{{Cite journal|lastlast1=Kollias|firstfirst1=D.|last2=Tzirakis|first2=P.|last3=Nicolaou|first3=M.A.|last4=Papaioannou|first4=A.|last5=Zhao|first5=G.|last6=Schuller|first6=B.|last7=Kotsia|first7=I.|last8=Zafeiriou|first8=S.|date=2019|title=Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond|url=https://rdcu.be/bmGm2|journal=International Journal of Computer Vision (IJCV), 2019|volume=127|issue=6–7|pages=907–929|doi=10.1007/s11263-019-01158-4|s2cid=13679040|doi-access=free|arxiv=1804.10938}}</ref>

|valence and arousal

|200

Line 214 ⟶ 189:

|Valence, Arousal

|In-the-Wild setting

|

|-

|Aff-Wild2<ref>{{Cite journal|lastlast1=Kollias|firstfirst1=D.|last2=Zafeiriou|first2=S.|date=2019|title=Expression, affect, action unit recognition: Aff-wild2, multi-task learning and arcface|url=https://bmvc2019.org/wp-content/uploads/papers/0399-paper.pdf|journal=British Machine Vision Conference (BMVC), 2019|arxiv=1910.04855}}</ref> <ref>{{Cite journalbook|lastlast1=Kollias|firstfirst1=D.|last2=Schulc|first2=A.|last3=Hajiyev|first3=E.|last4=Zafeiriou|first4=S.|datetitle=2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020) |titlechapter=Analysing affectiveAffective behaviorBehavior in the firstFirst abawABAW 2020 competitionCompetition |date=2020|chapter-url=https://www.computer.org/csdl/proceedings-article/fg/2020/307900a794/1kecIYu9wL6|journalpages=IEEE International Conference on Automatic Face and Gesture Recognition (FG), 637–643|doi=10.1109/FG47880.2020.00126|arxiv=2001.11409|isbn=978-1-7281-3079-8|s2cid=210966051}}</ref>

|neutral, happiness, sadness, surprise, fear, disgust, anger + valence-arousal + action units 1,2,4,6,12,15,20,25

|458

Line 224 ⟶ 198:

|Valence, Arousal, 7 basic expressions, action units for each video frame

|In-the-Wild setting

|-

|Real-world Affective Faces Database (RAF-DB)<ref>{{Cite web|last=Li.|first=S.|title=RAF-DB|url=http://www.whdeng.cn/RAF/model1.html|website=Real-world Affective Faces Database}}</ref><ref>{{Cite book|last1=Li|first1=S.|last2=Deng|first2=W.|last3=Du|first3=J.|title=2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |chapter=Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild |date=2017|pages=2584–2593|doi=10.1109/CVPR.2017.277|isbn=978-1-5386-0457-1|s2cid=11413183}}</ref>

|6 classes of '''basic emotions''' (Surprised, Fear, Disgust, Happy, Sad, Angry) plus Neutral and 12 classes of '''compound emotions''' (Fearfully Surprised, Fearfully Disgusted, Sadly Angry, Sadly Fearful, Angrily Disgusted, Angrily Surprised, Sadly Disgusted, Disgustedly Surprised, Happily Surprised, Sadly Surprised, Fearfully Angry, Happily Disgusted)

|

|29672 annotated examples

|Color

|Various for original dataset and 100x100 for aligned dataset

|Emotion labels

|Posed and Spontaneous

|-

|}

Line 234 ⟶ 214:

{{reflist}}

{{Nonverbal communication}}

[[Category:Database-related lists|Facial expression]]

[[Category:Facial expressions]]