Human faces are an example of a class of objects in which each example exhibits significant variation in shape and appearance, but which is composed of a fixed number of sub-parts which have a similar configuration in every case. For such objects we can define landmark points on each example which imply a correspondence between different examples. We can then build statistical models of the shape by considering the relative positions of landmarks, and can model the pattern of intensities across the object by warping them into a common reference frame. Such combined models of shape and appearance have been found to be powerful tools for image interpretation. They are generative models, capable of synthesizing new examples similar to those in the training set. The formulation of such models is described, and their application to face location and recognition investigated. Particular attention is paid to methods of matching such models to new images in a multi-stage process.