Face Shape Recovery from a Single Image View

The problem of acquiring surface models of faces is an important one with potentially significant applications in biometrics, computer games and production graphics. For such task, the use of shape-from-shading (SFS) is appealing since it is a non-invasive method that mimics the capabilities of the human visual system. In this thesis, our interest lies on the recovery of facial shape from single image views. We make four novel contributions to this area. We commence by describing an algorithm for ensuring data-closeness and integrability in Shape-from-Shading. The combination of these constraints is aimed to overcome the problem of high dependency on the image irradiance. Next, we focus on developing a practical scheme for face analysis using SFS. We describe a local-shape based method for imposing a novel convexity constraint. We show how to modify the orientations in the surface gradient field using critical points on the surface and local shape indicators. Then, we explore the use of statistical models that can be used in conjunction with SFS to reconstruct facial shape. We describe four different ways of constructing the 3D statistical models of faces using Cartesian representations: the surface height, the surface gradient, the surface normal azimuthal angle and finally a model based on Fourier domain basis functions. The models can be fitted to input images using a data-driven procedure which satisfies the image irradiance equation as a hard constraint and is also integrable. Finally, we propose a coupled statistical model that can be used to recover facial shape from brightness images of faces. We jointly capture variations in intensity and surface shape. The model is constructed by performing principal components analysis (PCA) on sets of parameters describing the contents of the intensity images and the facial shape representations. By fitting the coupled model to intensity data, facial shape is implicitly recovered from the shape parameters.