Facial Expression Recognition

1
Facial Expression Recognition

• Shane Steward

2
Facial Action Coding System

• Anatomically based
• Splits face into upper and lower regions
• Action units (AU)

3
Hidden Markov Models

• Finite State Machine
• Current state not observable
• Each transition and initial state has a
  probability
• Each state has output with probability

4
Noise Filtering

• Used to isolate important features of face
• Principal Component Analysis (PCA)
• Independent Component Analysis (ICA)

5
3D Wireframe

• Pros
• Easy to see
• Deformable object that can be manipulated
• Cons
• Initial mapping of 2D image
• Resources

6
Comparison to Neutral Image

• Subtract image from neutral expression

7
Comparison to Neutral Image

• Basic expressions
• Joy Fear Anger
• Disgust Sadness Surprise
• Stylized images
• Specific to subject

8
Facial Feature Tracking

• Based on sequence of images
• Looks densely at key areas
• Detect subtleties in movement
• Detect degree of muscle activation

9
Points Tracking

• Key points on the face are tracked
• Based off Medial Canthus and Philtrum
• Movement stored as vector

10
Dense Optical Flow

• Detailed motion info
• Gathered in grid of entire face
• Reduced with PCA

11
Line Detection

• Looks for furrows
• Account for natural face features

12
Facial Feature Tracking

• Identifies AUs
• Uses results as input to HMM
• Expression with highest probability
• Detects intensity of emotion
• Identifies subtle emotions

13
Homework

• Name the six basic Facial Expressions
• Name the three parts of Facial Feature tracking.