In spite of its success, the standard 2-D discrete wavelet transform (2D-DWT) is not completely adapted to
represent image entities like edges or oriented textures. Indeed the DWT is limited by the spatial isotropy of
its basis functions that can not take advantage of edges regularity and moreover, direction edge that is neither
vertical or horizontal is represented using many of these wavelet basis functions which does mean that DWT
does not provide a sparse representation for such discontinuities. Several representations have been proposed
to overcome this lack. Some of them deal with more orientations while introducing redundancy (e.g. ridgelets,
curvelets, contourlets) and their implementations are not trivial or require 2-D non separable filtering. We present
two oriented lifting-based schemes using separable filtering, lead by edge extraction, and inspired from bandelets
and curved wavelets. An image is decomposed into a quadtree according to the edge elements orientation. For
each leaf, a wavelet transform is performed along the most regular orientation, and then along its orthogonal
direction. Different adapted filters may be used for these two directions in order to achieve anisotropic filtering.
Our method permits also a perfect reconstruction and a critical sampling.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.