Cited by 1,745Face recognition and analysisEmotion and Mood RecognitionFace and Expression Recognition

Recognizing action units for facial expression analysis

Open access
Tian, Y.-I., Kanade, T., Cohn, J.F.·2001·IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

Most automatic expression analysis systems attempt to recognize a small set of prototypic expressions, such as happiness, anger, surprise, and fear. Such prototypic expressions, however, occur rather infrequently. Human emotions and intentions are more often communicated by changes in one or a few discrete facial features. In this paper, we develop an Automatic Face Analysis (AFA) system to analyze facial expressions based on both permanent facial features (brows, eyes, mouth) and transient facial features (deepening of facial furrows) in a nearly frontal-view face image sequence. The AFA system recognizes fine-grained changes in facial expression into action units (AUs) of the Facial Action Coding System (FACS), instead of a few prototypic expressions. Multistate face and facial component models are proposed for tracking and modeling the various facial features, including lips, eyes, brows, cheeks, and furrows. During tracking, detailed parametric descriptions of the facial features are extracted. With these parameters as the inputs, a group of action units (neutral expression, six upper face AUs and 10 lower face AUs) are recognized whether they occur alone or in combinations. The system has achieved average recognition rates of 96.4 percent (95.4 percent if neutral expressions are excluded) for upper face AUs and 96.7 percent (95.6 percent with neutral expressions excluded) for lower face AUs. The generalizability of the system has been tested by using independent image databases collected and FACS-coded for ground-truth by different research teams.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/34.908962

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

2 of the 41 references couldn’t be matched to a known paper.

Research works printed but not linked: 7

  1. [7][7].Carroll JM, Russell J. Facial Expression in Hollywood’s Portrayal of Emotion. J. Personality and Social Psychology. 1997;72:164–176. [Google Scholar]
  2. [11][11].Eibl-Eihesfeldt I. Human Ethology. Aldine de Gruvter; New York: 1989. [Google Scholar]
  3. [14][14].Ekman P, Friesen WV. The Facial Action Coding System: A Technique for The Measurement of Facial Movement. Consulting Psychologists Press; San Francisco: 1978. [Google Scholar]
  4. [15][15].Ekman P, Hager J, Methvin CH, Irwin W. Ekman-Hager Facial Action Exemplars. Human Interaction Laboratory, Univ. of California; San Francisco: unpublished data. [Google Scholar]
  5. [19][19].Izard C, Dougherty L, Hembree EA. Univ. of Delaware; 1983. A System for Identifying Affect Expressions by Holistic Judgments. unpublished manuscript. [Google Scholar]
  6. [31][31].Suwa M, Sugie N, Fujimora K. A Preliminary Note on Pattern Recognition of Human Emotional Expression. Proc. Int’l Joint Conf. Pattern Recognition.1978. pp. 408–410. [Google Scholar]
  7. [38][38].Yacoob Y, Lam H, Davis L. Recognizing Face Showing Expressions. Proc. Int’l Workshop Automatic Face and Gesture Recognition. 1995 [Google Scholar]

Cited by

Sorted by citations

Authors
Tian, Y.-I., Kanade, T., & Cohn, J. F.
Affiliations
  • Carnegie Mellon University (US)
  • University of Pittsburgh (US)
Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Published
2001
Volume
23
Issue
2
Pages
97-115
ISSN
0162-8828 (ISSN-L)
OpenAlex
W2106390385
Cited by
1,745
References
41
Citations by year
2026: 34 · 2025: 56 · 2024: 71 · 2023: 70 · 2022: 106 · 2021: 100 · 2020: 78 · 2019: 94 · 2018: 63 · 2017: 70 · 2016: 80 · 2015: 72 · 2014: 85 · 2013: 80 · 2012: 67
FWCI
52.28
Type
journal article
Language
en
Open access
Locations
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
  • PubMed (publishedVersion)
  • Europe PMC (PubMed Central) (acceptedVersion)
  • PubMed Central (acceptedVersion)
Funders
  • University of Pittsburgh
  • National Institute of Mental Health (R01MH051435)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face recognition and analysis
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Face and Expression Recognition
Keywords
facial expression analysis, facial action units, facial action coding system, facial feature tracking, facial expression recognition, neutral expression

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review