Recognizing Action Units for Facial Expression Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing
| Hi-index | 0.00 |
Vision-based systems become more and more popular due to increasing computation speed of the computer and quality of cheap webcams available for home users. Such systems can be implemented as human-computer interfaces supporting people with alternative, hands free communication with computers. The paper presents a vision-based face gesture recognition system that can be used as face features analysis module or a human-computer interface. It enables analysis of the following face features: eyes, eyebrows, mouth, tongue and face speed. The overall accuracy of the system is equal to 98%.