This paper tackles the problem of accurately matching a 3D deformable face model to sequences of images in challenging real-world scenarios with large amounts of head movement, occlusion, and difficult lighting conditions. A baseline system involves searching with a set of view-dependent local patches to locate image features, and using these to update the face shape model parameters. We show here two modifications that lead to improvements in performance and can be applied in other similar systems. These are: explicitly searching for occluding boundaries, which prevents the model from rotating rather than changing shape; and a simple method for weighting the relative importance of each located match for model fit. We demonstrate the improvements on both standard test sets and on a series of difficult in-car driver videos, showing more accurate matching and fewer search failures. © 2010. The copyright of this document resides with its authors.

In this paper we present the first steps in the development of a statistical shape model, specifically a point distribution model (PDM), of the cortical surface of the brain. This will ultimately be used to locate, label, and describe the cortex, for visualisation, diagnosis, and quantification. In order to produce the model it was necessary to find and label the sulcal fissures on a series of MR images. Due to the complexity of the surface, an automated method was developed to facilitate development of a full surface model. Automating the marking process introduced the problem of identifying correspondences between examples, the knowledge of which is essential to the development of a PDM. Various methods were investigated to solve this problem including simple point matching and more complex curve matching. Each is outlined and discussed. The models obtained so far provide interesting insights into the shape and cortical pattern variations over a group of normal subjects.