A Rotation-Invariant Pattern Signature
Eero P Simoncelli
Published in:
Proc. 3rd International Conference on Image Processing
Lausanne, Switzerland. September, 1996.
doi: 10.1109/ICIP.1996.560415
© IEEE Signal Processing Society
We propose a ``signature'' for rotation-invariant representation of
local image structure. The signature is a complex-valued vector
constructed analytically from the projections of the image onto a set
of oriented basis kernels. The components of the signature form an
overcomplete set of algebraic invariants, but are chosen to avoid
instabilities associated with previously developed algebraic
invariants. We demonstrate the use of this signature for representing
and classifying junctions in grayscale imagery.
Full Text (PostScript, 348k)
/
EPS Web-Available Publications
/ Home Page