CoChat
Sign Up
Cited by 36Emotion and Mood RecognitionFace Recognition and PerceptionPsychiatry, Mental Health, Neuroscience

Machine Interpretation of Emotion: Design of a Memory‐Based Expert System for Interpreting Facial Expressions in Terms of Signaled Emotions

Open access
Kearney, Garrett D., McKenzie, Sati·1993·Cognitive Science
DOI 10.1207/s15516709cog1704_5
Open this paper in CoChat — free accountOpen PDF

Abstract

As a first step in involving user emotion in human‐computer interaction, a memory‐based expert system (JANUS; Kearney, 1991) was designed to interpret facial expression in terms of the signaled emotion. Anticipating that a VDU‐mounted camera will eventually supply face parameters automatically, JANUS now accepts manually made measurements on a digitized full‐face photograph and returns emotion labels used by college students. An intermediate representation in terms of face actions (e.g., mouth open) is also used. Production rules convert the geometry into these. A dynamic memory (Kolodner, 1984; Schank, 1982) interprets the face actions in terms of emotion labels. The memory is dynamic in the sense that new emotion labels can be learned with experience. A prototype system has been implemented on a Sun 2/120 system using POPLOG. Validation studies on the prototype suggest that the interpretations achieved are generally consistent with those of college students without formal instruction in emotion signals.

Integrity signals

Registry

Crossref · 10.1207/s15516709cog1704_5

Cites

48 of 48 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

  • Although Hong et al. utilize the PersonSpotter system, which deals with real-time processing of video sequences, they perform facial expression analysis from static images.

    “Although Hong et al. utilize the PersonSpotter system [81], which deals with real-time processing of video sequences, they perform facial expression analysis from static images.”

    From Automatic analysis of facial expressions: the state of the art (2000) · cites this paper as [81]

  • The PersonSpotter system performs well in the presence of background motion but fails in the case of covered or too much rotated faces.

    “Steffens et al. [81] reported that their system performs well in the presence of background motion, but fails in the case of covered or too much rotated faces.”

    From Automatic analysis of facial expressions: the state of the art (2000) · cites this paper as [81]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Kearney, G. D., & McKenzie, S.
Affiliations
University of Greenwich (GB)
Corresponding author
Kearney, Garrett D.
Venue
Cognitive Science
Publisher
Wiley
Published
1993-10
Volume
17
Issue
4
Pages
589-622
ISSN
  • 0364-0213 (ISSN-L)
  • 1551-6709
DOI
10.1207/s15516709cog1704_5
OpenAlex
W2097755513
Cited by
36
References
48
Citations by year
2023: 1 · 2019: 1 · 2018: 1 · 2017: 1 · 2016: 1 · 2013: 2 · 2012: 1
FWCI
2.14
Type
journal article
Language
en
Open access
Licence
onlinelibrary.wiley.com/termsAndConditions#vor (vor, 5977 d)
Locations
Cognitive Science (publishedVersion)
Topics
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Face Recognition and Perception
  • Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
Keywords
facial expression interpretation, emotion recognition, dynamic memory, production rules, emotion labeling, face geometry

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