Abstract
Hierarchical Geometrical Image Representation with Plain Wavelets
Stéphane Mallat
École Polytechnique
Is it possible to build geometric image representations with local transformations over separable wavelet coefficients ? Following this approach, we construct wavelet-bandelet orthogonal bases, that lead to asymptotically optimal approximations of geometrically regular images. These bases remain orthogonal for discrete images and their structures share some similarities with neurons in the V2 visual area.
No video available