Locating facial features using genetic algorithms

Abstract

Detection of facial features is difficult because face images are highly variable. Sources of variability include individual appearance, 3D pose, facial expression and lighting. We describe a system for locating facial features, which uses flexible models of appearance as a means of providing prior knowledge about the expected appearance of j'katures and the spatial relationships between them. A global search procedure based on Genetic Algorithms is used to fit the model to new face images, so that the exact position of a face and facial features can be recovered.