1 We propose to use statistical models of shape and texture as deformable anatomical atlases. By training on sets of labelled examples these can represent both the mean structure a...
Timothy F. Cootes, C. Beeston, Gareth J. Edwards, ...
A method that combines shape-based object recognition and image segmentation is proposed for shape retrieval from images. Given a shape prior represented in a multiscale curvature...
Matching articulated shapes represented by voxel-sets reduces to maximal sub-graph isomorphism when each set is described by a weighted graph. Spectral graph theory can be used to...
Diana Mateus, Radu Horaud, David Knossow, Fabio Cu...
To analyze time-varying data sets, tracking features over time is often necessary to better understand the dynamic nature of the underlying physical process. Tracking 3D time-vary...
We address the fundamental problem of matching in two static images. The remaining challenges are related to occlusion and lack of texture. Our approach addresses these difficultie...