Real-time Facial Expression Recognition in Image Sequences Using an AdaBoost-based Multi-classifier
Year: 2009
Type: conference-paper
Abstract: In this paper, a highly automatic facial expression recognition system without choosing characteristic blocks in advance is presented. The system is able to detect and locate human faces in image sequences acquired in real environments. To achieve efficient facial expression recognition, we evaluate the performance of three different classifiers using multi-layer perceptrons (MLPs), support vector machines (SVMs), and Adaboost algorithms (ABAs). From the experimental outcomes, we can observe that the average recognition rates obtained from both ABAs and MLPs are better than that from SVMs, but the training of MLPs takes quite a long time. Comparatively, ABAs have an advantage of facilitating the speed of convergence, which are chosen as the core technique to implement our strong facial expression classifier. Through conducting many experiments, the statistics of performance reveals that the accuracy rate of our facial expression recognition system reaches more than 90% for a single kind or multiple kinds of expressions appearing in an image sequence.
Authors: Chin‐Shyurng Fahn, Minghui Wu, Chang-Yi Kao
Institution: National Taiwan University of Science and Technology
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: National Science Council
Award: G7996248560
OpenAlex ID: W7441514
