This paper presents a fusion of the active appearance model (AAM) and the Riemannian elasticity framework which yields a non-linear shape model and a linear texture model -the active elastic appearance model (EAM).The non-linear elasticity shape model is more flexible than the usual linear subspace model, and it is therefore able to capture more complex shape variations.Local rotation and translation invariance are the primary explanation for the additional flexibility.In addition, we introduce global scale invariance into the Riemannian elasticity framework which together with the local translation and rotation invariances eliminate the need for separate pose estimation.The new approach was tested against AAM in three experiments; face labeling, face labeling with poor initialization and corpus callosum segmentation.In all the examples the EAM performed significantly better than AAM.Our Matlab implementation can be downloaded through svn from https://svn.imm.dtu.dk/AAMLab/svn/AAMLab/trunk/ .

In this paper we present a new method for constructing diffeomorphic statistical deformation models in arbitrary dimensional images with a nonlinear generative model and a linear parameter space. Our deformation model is a modified version of the diffeomorphic model introduced by Cootes et al. The modifications ensure that no boundary restriction has to be enforced on the parameter space to prevent folds or tears in the deformation field. For straightforward statistical analysis, principal component analysis and sparse methods, we assume that the parameters for a class of deformations lie on a linear manifold and that the distance between two deformations are given by the metric introduced by the L2-norm in the parameter space. The chosen L2-norm is shown to have a clear and intuitive interpretation on the usual nonlinear manifold. Our model is validated on a set of MR images of corpus callosum with ground truth in form of manual expert annotations, and compared to Cootes's model. We anticipate applications in unconstrained diffeomorphic synthesis of images, e.g. for tracking, segmentation, registration or classification purposes.

Magnetic resonance (MR) images often exhibit grayscale nonuniformities, caused by radio frequency (RF) coil design or acquisition sequences. Many algorithms to remove these nonuniformities have been proposed in the past decade. However, only minor attention has been given to the performance evaluation of existing methods. We derive a link between the estimation performance and underlying image structure. For a piecewise constant 1D signal model with equal size regions we demonstrate that the variance in estimation grows as M/sup 2/ , where M is the number of regions. In 2D case the growth becomes linear in M.