Abstract
In this paper, we present an intelligent facial emotion recognition system with real-time face tracking for a humanoid robot. The system is able to detect facial actions and emotions from images with up to 60 degrees of pose variations. We employ the Active Appearance Model to perform real-time face tracking and extract both texture and geometric representations of images. A POSIT algorithm is also used to identify head rotations. The extracted texture and shape features are employed to detect 18 facial actions and seven basic emotions. The overall system is integrated with a humanoid robot platform to further extend its vision APIs. The system is proved to be able to deal with challenging facial emotion recognition tasks with various pose variations.
| Original language | English |
|---|---|
| Title of host publication | The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014) |
| Publisher | IEEE |
| Pages | 1-8 |
| Number of pages | 8 |
| ISBN (Electronic) | 978-1-4799-6399-7 |
| DOIs | |
| Publication status | Published - 1 Dec 2014 |
Keywords
- application program interfaces
- emotion recognition
- face recognition
- feature extraction
- human-robot interaction
- humanoid robots
- image representation
- image texture
- object detection
- object tracking
- pose estimation
- robot vision
- shape recognition
- POSIT algorithm
- active appearance model
- facial action detection
- head rotations
- humanoid robot
- image geometric representation
- intelligent appearance
- intelligent facial emotion recognition system
- pose variations
- real-time face tracking
- shape based facial emotion recognition
- shape feature extraction
- texture representation extraction
- vision API
- Active appearance model
- Emotion recognition
- Face
- Fitting
- Shape
- Training
- Action Unit
- Facial Action Coding System
- Neural Network