الفهرس | Only 14 pages are availabe for public view |
Abstract Accurate face landmarks localization is one of the fundamental steps in many computer vision problems. In this thesis we propose a method for accurately localizing these landmarks based on: (1) modeling faces as non- linear combination of exemplars; (2) the model and optimization is done using genetic algorithm to best model this problem. Performance evaluation of our EC-GA algorithm showed that our algorithm outperformed many sate-of-art methods on di{uFB00}erent public datasets |