1. EMPATH: A Neural Network that Categorizes Facial Expressions Matthew N. Dailey and Garrison W. Cottrell University of California, San Diego Curtis Padgett California Institute of Technology

2. Facial Expression Recognition (Theory 1) Categorical Perception Categories are discrete entities Sharp categorical boundaries Discrimination of similar pairs of expressive faces is enhanced when near category boundaries

3. Facial Expression Recognition (Theory 2) Graded and expressions considered points in a continuous, low-dimensional space e.g. “Surprise” between “Happiness” and “Fear”

4. Historical Research (Categorical) Ekman and Friesen (1976) 10-step photos between pairs of caricatures Ekman 1999 essay on basic emotions Harnad, 1987 Categorical Perception Beale and Keil (1995) morph image sequence with famous faces Etcoff and Magee (1992) facial expression recognition tied to perceptual mechanism

5. Historical Research (Continuous) Schlosberg (1952) category ratings and subjects “errors” predicted accurately by arranging categories around an ellipse Russell (1980) structure theory of emotions Russell and Bullock (1986) emotion categories best thought of as fuzzy sets Russel et al. (1989),Katsikitis (1997), Schiano et al. (2000) continuous multidimensional perceptual space for facial expression perception

6. Young et al.’s (1997) “Megamix” Experiments Experiment 1: Subjects identify the emotional category in 10%, 30%, 50%, 70%, and 90% morphs between all pairs of the 6 prototypical expressions  6-way forced choice identification Experiment 2: Same as experiment 1 with the addition of the “neutral” face  7-way forced choice

7. Young et al.’s (1997) “Megamix” Experiments Experiment 3: Discriminate pairs of stimuli along the six transitions  Sequential discrimination task (ABX)  Simultaneous discrimination task (same-different) Experiment 4: Determine what expression is “mixed- in” to a faint morph  Given a morph or prototype stimulus, indicate the most apparent, second-most apparent, and third-most apparent emotion

8. “Megamix” Experiment Results Results from experiments 1-3 support the categorical view of facial expression perception Results from experiment 4 showed that subjects were significantly likely to detect mixed-in emotion at 30%. This supports the continuous, dimentional accounts of facial expression perception Rather than settling the issue of categorical vs. continuous theories they found evidence to support BOTH theories Until now, no computational model has ever been able to simultaneously explain these seemingly contradictory data

9. The Model Three layer neural network  Perceptual analysis  Object representation  Categorization Feedforward network (no backpropagation at later levels) Input is 240 x 292 grayscale face image

10. Perceptual Analysis Layer Neurons whose response properties are similar to complex cells in the visual cortex This is modeled by “Gabor Filters” Basically, these units do nonlinear edge detection at five different scales and eight different orientations

11. Object Representation Layer Extract small set of features from high dimensional data Equal to an “image compression” network that extracts global representations of the data Principal components analysis is used to model this layer 50 linear hidden units

12. Categorization Layer Simple perceptron with six outputs (one for each “basic” emotion) The network is set up so that the output can be interpreted as probabilities (i.e. they are all positive and sum to 1)

13. The Model

14. Experiments & Results Same experiments as the Young et al. “Megamix” experiments Results  The model and humans find the same expressions difficult or easy to interpret  When presented with morphs between pairs of expressions, the model and humans place similar sharp category boundaries between prototypes  The model and humans are similarly sensitive to mixed-in expressions in morph stimuli

15. More Results Network generalization to unseen faces, compared to human agreement on the same face (six-way forced choice)

16. More Results

17. Conclusion This model was able to simulate both the categorical and continuous nature of facial classification consistent with the human experiments conducted by Young et al. Categorical or Continuous?  Conclusion leans toward both theories being complimentary instead of mutually exclusive  “tapping different computational levels of processing”  Which method is dictated by the task and the data