260 likes | 462 Views
Outline. MotivationBackgroundFacial expression recognition methodResults on a data setResults with a robot (the paper contribution)Conclusions. Motivation: Goal. Our Robotics group goals:To create mobile robotic assistants for humansTo make robots easier to customize and to program by end us
E N D
1. 19 February 2008
2. Outline Motivation
Background
Facial expression recognition method
Results on a data set
Results with a robot (the paper contribution)
Conclusions
3. Motivation: Goal Our Robotics group goals:
To create mobile robotic assistants for humans
To make robots easier to customize and to program
by end users
To enhance interactions between robots and humans
Applications: healthcare, eg aged care
Applications: agriculture (eg Ian's previous presentation)
(Lab visit this afternoon)?
4. Motivation: robots in human spaces Increasingly, robots live in human spaces and interact closely
5. Motivation: close interactions RI-MAN
6. Motivation: different types of robot Robots have many forms; how do people react?
Pyxis HelpMate SP Robotic Courier System
Delta Regional Medical Centre, Greenville, Mississippi
7. Motovation: different robot behaviour
8. Motivation: supporting the emotion dimension Robots must give support with psychological dimensions
home and hospital help
therapy
companionship
We must understand/design the psychology of the exchange
Emotions play a significant role
Robots must respond to and display emotions
Emotions support cognition
Robots must have emotional intelligence
Eg during robot assisted learning
Eg security screening robots
Humans’ anxiety can be reduced if a robot responds well [Rani et al, 2006]
9. Motivation: functionality of emotion response Not just to be “nice”; the emotion dimension is essential to effective robot functionality [Breazeal]
10. Motivation: robots must distinguish human emotional state
However, recognition of human emotions is not straightforward
Outward expression versus internal mood states
People smile when happy AND they are interacting with humans
Olympic medalists don’t smile until the presenter appears (eg 1948 football team)
Ten pin bowlers smile when they turn back to their friends
11. Motivation: deciphering human emotions Self-reports are more accurate than observer ratings
Current research attempts to decipher human emotions
facial expressions
speech expression
heart rate, skin temperature, skin conductivity
12. Motivation: Our focus is on facial expressions Despite the limitations, we focus on facial expression interpretation from visual information.
Portable, contactless
Needs no special nor additional sensors
Similar to humans' interpretation of emotions (which is by vision and speech)?
No interference with normal HRI
13. Background Six universal facial expressions (Ekman et al.)
Laughing, surprised, afraid, disgusted, sad, angry
Cohn-Kanade-Facial-Expression database (488 sequences, 97 people)
Performed
Exaggerated
Determined by
Shape
Muscle motion Further persons: 82, 77, 32!!!, 26?!?, 11!?!
Further persons: 82, 77, 32!!!, 26?!?, 11!?!
14. Background: Why are they difficult to estimate? Participants could annotate as long as they wanted.Participants could annotate as long as they wanted.
15. Background Typical FER process [Pantic & Rothkrantz, 2000]
16. Background: Challenges 1. Face detection and 2. feature extraction challenges:
Varying shape, colour, texture, feature location, hair
Spectacles, hats
Lighting conditions including shadows
3. Facial expression classification challenges:
Machine learning
17. Background: related work Cohen et al: 3D wireframe with 16 surface patches
Bezier volume parameters for patches
Bayesian network classifiers
HMMs model muscle activity over time
Bartlett et al: Gabor filters using AdaBoost, Support Vector
93% accuracy on Cohn-Kanade DB
Is tuned to DB
18. Background: challenges for robots Less constrained face pose and distance from camera
Human may not be facing the robot
Human may be moving
More difficulty in controlling lighting
Robots move away!
Real time result is needed (since the robot moves)
19. Facial expression recognition (FER) methodMatt’s model based approach
20. FER method Cootes et al statistics based deformable model (134 points)
Translation, scaling, rotation
Vector b of 17 face configuration parameters
Rotate head b1, open mouth b3, change gaze direction b10
21. FER method: Model-based image interpretation The model The model contains a parameter vector that represents the model’s configuration.
The objective function Calculates a value that indicates how accurately a parameterized model matches an image.
The fitting algorithm Searches for the model parameters that describe the image best, i.e. it minimizes the objective function.
What is MODEL-BASED IMAGE INTERPRETATION all about?
Interpret images with a GEOMETRIC model.“
Models contains a vector of parameters.
It affects
- position
- pose
- the deformation.What is MODEL-BASED IMAGE INTERPRETATION all about?
Interpret images with a GEOMETRIC model.“
Models contains a vector of parameters.
It affects
- position
- pose
- the deformation.
22. FER method Two step process for skin colour: see [Wimmer et al, 2006]
Viola & Jones technique detects a rectangle around the face
Derive affine transformation parameters of the face model
Estimate b parameters
Viola & Jones repeated
Features are learned to localize face features
Objective function compares an image to a model
Fitting algorithm searches for a good model
23. FER method: learned objective function Reduce manual processing requirements by learning the objective function [Wimmer et al, 2007a & 2007b]
Fitting method: hill-climbing
24. FER method Facial feature extraction:
Structural (configuration b) and temporal features (2 secs)
Expression classification
Binary decision tree classifier is trained on 2/3 of data set
25. Results on a dataset
26. Results on a robot B21r robot
Some controlled lighting
Human about 1m away
120 readings of three facial expressions
12 frames a second possible
Tests at 1 frame per second
27. Conclusions Robots must respond to human emotional states
Model based FER technique (Wimmer)
70% accuracy on Cohn-Kanade data set (6 expressions)
67% accuracy on a B21r robot (3 expressions)
Future work: better FER is needed
Improved techniques
Better integration with robot software
Improve accuracy by fusing vital signs measurements