The Steerable Pyramid: A Flexible Architecture for Multi-Scale Derivative Computation

Eero P Simoncelli and William T Freeman

Published in:

Proc. 2nd Int'l Conf on Image Processing.
Washington, DC. October 1995.
doi: 10.1109/ICIP.1995.537667
© IEEE Signal Processing Society

We describe an architecture for efficient and accurate linear decomposition of an image into scale and orientation subbands. The basis functions of this decomposition are directional derivative operators of any desired order. We describe the construction and implementation of the transform.

Source code and filter kernels for the steerable pyramid are available via anonymous ftp.

Full PostScript (75k) / EPS Web-Available Publications / Home Page