Automatic Interpretation and Coding of Face Images Using Flexible Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Pattern Recognition: A Review
IEEE Transactions on Pattern Analysis and Machine Intelligence
Looking at People: Sensing for Ubiquitous and Wearable Computing
IEEE Transactions on Pattern Analysis and Machine Intelligence
Facial Expression Recognition and Its Degree Estimation
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
WACV '96 Proceedings of the 3rd IEEE Workshop on Applications of Computer Vision (WACV '96)
| Hi-index | 0.00 |
In this paper we address the problem of facial expression recognition. We have developed a new facial model based only on visual information. This model describes a set of bidimensional regions corresponding to those elements which most clearly define a facial expression. The problem of facial gestures classification has been divided into three subtasks: face segmentation, finding and describing relevant facial components and, finally, classifying them into one of the predefined categories. Each of these tasks can be solved independently using different techniques already applied to a wide range of problems. This have led us to the definition of a modular, generic and extensible process architecture. A prototype has been developed which makes use of different simple solutions for each module, using a controlled environment and a low-cost vision system. We report the experimental results achieved by the prototype on a set of test images.