AI techniques for face detection.
Dragoş Datcu, Léon J. M. Rothkrantz · Belgium-Netherlands Conference on Artificial Intelligence · 2005
Facial related analysis represented milestones in the fields of computer vision for many decades. Lots of methods have been designed and implemented so as to solve the specific requirements. One of the methods, Relevance Vector Machines (RVM) stands for a novel supervised learning technique that is based on a probabilistic approach of Support Vector Machines. The data for training were selected from the Cohn-Kanade Facial Expression Database. The application associated with the current research aims at demonstrating the use of the RVM as a novel classifier for face detection.