facial expression recognition
play

Facial Expression Recognition Ian Endres April 10, 2009 Expression - PowerPoint PPT Presentation

Facial Expression Recognition Ian Endres April 10, 2009 Expression Overview Given image or video Identify 6 principal emotions: happiness, sadness, surprise, fear, anger, disgust Applications Robotics User/operator feedback


  1. Facial Expression Recognition Ian Endres April 10, 2009

  2. Expression Overview ◮ Given image or video ◮ Identify 6 principal emotions: happiness, sadness, surprise, fear, anger, disgust

  3. Applications ◮ Robotics ◮ User/operator feedback

  4. Method ◮ 1996 - Hand initialization, parametric flow, hand selected predicates, simple hand written rules ◮ 2008 - Single image (Actor Dependent) Dimensionality reduction (using DLLE), SVM classification ◮ 2008 - Motion (Actor Independent) Automatic initialization, keypoint tracking, keypoint flow and displacement, nearest neighbor classification

  5. Initialization ◮ Initialize initial frame, automatically track throughout ◮ Black - Mark box around features, head ◮ Yang ◮ Face detection - model skin with Gaussian color model ◮ Feature detection - Fit model to eye/mouth contours, iris edges

  6. Motion Model (Black) Affine Model u ( x , y ) = a o + a 1 x + a 2 y v ( x , y ) = a 3 + a 4 x + a 5 y divergence = a 1 + a 5 curl = − a 2 + a 4 deformation = a 1 − a 5

  7. Motion Model (Black) Planar, Curvature Models Additional planar terms u : p o x 2 + p 1 xy v : p o xy + p 1 y 2 Additional curvature term: v : cx 2

  8. Model Fitting Write model as ( A ffine, P lanar, C urvature): ◮ Color constancy constraint: I ( x , t ) = I ( x − X ( x ) P , t + 1) ◮ Thus minimize over P : � x ∈ f ρ ( ∇ I · ( X ( x ) P ) + I t , σ ) ◮ Error norm ρ ( x , σ ) is used to ignore outliers

  9. Motion Model (Yang) ◮ Energy Model ◮ Distance from neutral : potential energy ◮ Velocity from optical flow : kinetic energy

  10. Features ◮ Black - Predicates based on flow model parameters Figure: Predicates for motion of 1) Mouth, eyebrows, eyes 2) Head ◮ Yang (Static) - Image embedding in R 2 , each person separate ◮ Yang (Motion) - Energy values for each image point

  11. Learning/Inference ◮ Black - Detect expression change via conjunctions of predicates ◮ Yang (Static) ◮ Train 1v1 polynomial kernel SVM ◮ 20 training examples per expression per person ◮ Inference using these classifiers ◮ Yang (Motion) ◮ “Apex” of expression as region of constant kinetic energy ◮ Label using potential energy states, using exemplar/nearest neighbor method

  12. Learning/Inference (Cont) Figure: 1) Predicate Rules for Black 2) Temporal behavior of expressions

  13. Results (Black)

  14. Results (Yang, Static)

  15. Drawbacks/Limitations ◮ Artifical Datasets ◮ Explicit initialization ◮ Black ◮ No machine learning ◮ Yang ◮ Requires head motion and fast face motions to be avoided ◮ No quantitative results for motion!

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend


More recommend