A facial expression database is a collection of images or video clips with facial expressions of a range of emotions. Well-annotated (emotion-tagged) media content of facial behavior is essential for training, testing, and validation of algorithms for the development of expression recognition systems. The emotion annotation can be done in 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.

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.[1][2] Here are some details of the facial expression databases.

Database Facial expression Number of Subjects Number of images/videos Gray/Color Resolution, Frame rate Ground truth Type
FERG-3D-DB (Facial Expression Research Group 3D Database) for stylized characters [3] angry, disgust, fear, joy, neutral, sad, surprise 4 39574 annotated examples Color Emotion labels Frontal pose
Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) [4] Speech: Calm, happy, sad, angry, fearful, surprise, disgust, and neutral.

Song: Calm, happy, sad, angry, fearful, and neutral. Each expression at two levels of emotional intensity.

24  7356 video and audio files Color 1280x720 (720p) Facial expression labels

Ratings provided by 319 human raters

Extended Cohn-Kanade Dataset (CK+)[5] neutral, sadness, surprise, happiness, fear, anger, contempt and disgust 123  593 image sequences (327 sequences having discrete emotion labels) Mostly gray 640* 490 Facial expression labels and FACS (AU label for final frame in each image sequence) Posed; spontaneous smiles
Japanese Female Facial Expressions (JAFFE)[6] neutral, sadness, surprise, happiness, fear, anger, and disgust 10 213 static images Gray 256* 256 Facial expression label Posed
MMI Database[7] 43 1280 videos and over 250 images Color 720* 576 AU label for the image frame with apex facial expression in each image sequence Posed and Spontaneous
Belfast Database[8] Set 1 (disgust, fear, amusement, frustration, surprise) 114 570 video clips Color 720*576 Natural Emotion
Set 2 (disgust, fear, amusement, frustration, surprise, anger, sadness) 82 650 video clips Color
Set 3 (disgust, fear, amusement) 60 180 video clips Color 1920*1080
Indian Semi-Acted Facial Expression Database (iSAFE)[9] Happy, Sad, Fear, Surprise, Angry, Neutral, Disgust 44 395 clips Color 1920x1080

(60 fps)

Emotion labels Spontaneous
DISFA[10] - 27 4,845 video frames Color 1024*768; 20 fps AU intensity for each video frame (12 AUs) Spontaneous
Multimedia Understanding Group (MUG)[11] neutral, sadness, surprise, happiness, fear, anger, and disgust 86 1462 sequences Color 896*896, 19fps Emotion labels Posed
Indian Spontaneous Expression Database (ISED)[12] sadness, surprise, happiness, and disgust 50 428 videos  Color 1920* 1080, 50 fps Emotion labels Spontaneous
Radboud Faces Database (RaFD)[13] neutral, sadness, contempt, surprise, happiness, fear, anger, and disgust 67 Three different gaze directions and five camera angles (8*67*3*5=8040 images) Color 681*1024 Emotion labels Posed
Oulu-CASIA NIR-VIS database surprise, happiness, sadness, anger, fear and disgust 80 three different illumination conditions: normal, weak and dark (total 2880 video sequences) Color 320×240 Posed
FERG (Facial Expression Research Group Database)-DB[14] for stylized characters angry, disgust, fear, joy, neutral, sad, surprise 6 55767 Color 768x768 Emotion labels Frontal pose
AffectNet[15] neutral, happy, sad, surprise, fear, disgust, anger, contempt ~450,000 manually annotated

~ 500,000 automatically annotated

Color Various Emotion labels, valence, arousal Wild setting
IMPA-FACE3D[16] neutral frontal, joy, sadness, surprise, anger, disgust, fear, opened, closed, kiss, left side, right side, neutral sagittal left, neutral sagittal right, nape and forehead (acquired sometimes) 38 534 static images Color 640X480 Emotion labels Posed
FEI Face Database neutral,smile 200 2800 static images Color 640X480 Emotion labels Posed
Aff-Wild[17][18] valence and arousal 200 ~1,250,000 manually annotated Color Various (average = 640x360) Valence, Arousal In-the-Wild setting
Aff-Wild2[19][20] neutral, happiness, sadness, surprise, fear, disgust, anger + valence-arousal + action units 1,2,4,6,12,15,20,25 458 ~2,800,000 manually annotated Color Various (average = 1030x630) Valence, Arousal, 7 basic expressions, action units for each video frame In-the-Wild setting
Real-world Affective Faces Database (RAF-DB)[21][22] 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


  1. ^ "collection of emotional databases". Archived from the original on 2018-03-25.
  2. ^ "facial expression databases".
  3. ^ 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.
  4. ^ 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
  5. ^ 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
  6. ^ Lyons, Michael; Kamachi, Miyuki; Gyoba, Jiro (1998). The Japanese Female Facial Expression (JAFFE) Database. doi:10.5281/zenodo.3451524.
  7. ^ 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
  8. ^ 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
  9. ^ Singh, Shivendra; Benedict, Shajulin (2020). "Indian Semi-Acted Facial Expression (ISAFE) Dataset for Human Emotions Recognition". In Thampi, Sabu M.; Hegde, Rajesh M.; Krishnan, Sri; Mukhopadhyay, Jayanta; Chaudhary, Vipin; Marques, Oge; Piramuthu, Selwyn; Corchado, Juan M. (eds.). Advances in Signal Processing and Intelligent Recognition Systems. Communications in Computer and Information Science. Vol. 1209. Singapore: Springer. pp. 150–162. doi:10.1007/978-981-15-4828-4_13. ISBN 978-981-15-4828-4.
  10. ^ 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
  11. ^ 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.
  12. ^ S L Happy, P. Patnaik, A. Routray, and R. Guha, "The Indian Spontaneous Expression Database for Emotion Recognition," in IEEE Transactions on Affective Computing, 2016, doi:10.1109/TAFFC.2015.2498174.
  13. ^ 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
  14. ^ "Facial Expression Research Group Database (FERG-DB)". grail.cs.washington.edu. Retrieved 2016-12-06.
  15. ^ Mollahosseini, A.; Hasani, B.; Mahoor, M. H. (2017). "AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild". IEEE Transactions on Affective Computing. PP (99): 18–31. arXiv:1708.03985. doi:10.1109/TAFFC.2017.2740923. ISSN 1949-3045. S2CID 37515850.
  16. ^ "IMPA-FACE3D Technical Reports". visgraf.impa.br. Retrieved 2018-03-08.
  17. ^ Zafeiriou, S.; Kollias, D.; Nicolaou, M.A.; Papaioannou, A.; Zhao, G.; Kotsia, I. (2017). "Aff-Wild: Valence and Arousal 'In-the-Wild' Challenge" (PDF). 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). pp. 1980–1987. doi:10.1109/CVPRW.2017.248. ISBN 978-1-5386-0733-6. S2CID 3107614.
  18. ^ Kollias, D.; Tzirakis, P.; Nicolaou, M.A.; Papaioannou, A.; Zhao, G.; Schuller, B.; Kotsia, I.; Zafeiriou, S. (2019). "Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond". International Journal of Computer Vision. 127 (6–7): 907–929. arXiv:1804.10938. doi:10.1007/s11263-019-01158-4. S2CID 13679040.
  19. ^ Kollias, D.; Zafeiriou, S. (2019). "Expression, affect, action unit recognition: Aff-wild2, multi-task learning and arcface" (PDF). British Machine Vision Conference (BMVC), 2019. arXiv:1910.04855.
  20. ^ Kollias, D.; Schulc, A.; Hajiyev, E.; Zafeiriou, S. (2020). "Analysing Affective Behavior in the First ABAW 2020 Competition". 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020). pp. 637–643. arXiv:2001.11409. doi:10.1109/FG47880.2020.00126. ISBN 978-1-7281-3079-8. S2CID 210966051.
  21. ^ Li., S. "RAF-DB". Real-world Affective Faces Database.
  22. ^ Li, S.; Deng, W.; Du, J. (2017). "Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild". 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). pp. 2584–2593. doi:10.1109/CVPR.2017.277. ISBN 978-1-5386-0457-1. S2CID 11413183.