On Growth and Formlets: Sparse Multi-Scale Coding of Planar Shape
Oleskiw, Timothy D.; Elder, James; Peyré, Gabriel (2010), On Growth and Formlets: Sparse Multi-Scale Coding of Planar Shape, CVPR 2010 23rd IEEE Conference on Computer Vision and Pattern Recognition, 2010-06, San Francisco, États-Unis
TypeCommunication / Conférence
External document linkhttp://hal.archives-ouvertes.fr/hal-00470560/fr/
Conference titleCVPR 2010 23rd IEEE Conference on Computer Vision and Pattern Recognition
Conference citySan Francisco
MetadataShow full item record
Abstract (EN)This paper presents a sparse representation of 2D planar shape through the composition of warping functions, termed formlets, localized in scale and space. Each formlet subjects the 2D space in which the shape is embedded to a localized isotropic radial deformation. By constraining these localized warping transformations to be diffeomorphisms, the topology of shape is preserved, and the set of simple closed curves is closed under any sequence of these warpings. A generative model based on a composition of formlets applied to an embryonic shape, e.g., an ellipse, has the advantage of synthesizing only those shapes that could correspond to the boundaries of physical objects. To compute the set of formlets that represent a given boundary, we demonstrate a greedy coarse-to-fine formlet pursuit algorithm that serves as a non-commutative generalization of matching pursuit for sparse approximations. We evaluate our method by pursuing partially occluded shapes, comparing performance against a contour-based sparse shape coding framework.
Subjects / KeywordsSparsity; Shapes; Formlets
Showing items related by title and author.
A panorama on multiscale geometric representations, intertwining spatial, directional and frequency selectivity Jacques, Laurent; Duval, Laurent; Chaux, Caroline; Peyré, Gabriel (2011) Article accepté pour publication ou publié