TR95-15

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

    •  Eero P. Simoncelli, William T. Freeman, "The Steerable Pyramid: A Flexible Architecture for Multi-Scale Derivative Computation", Tech. Rep. TR95-15, Mitsubishi Electric Research Laboratories, Cambridge, MA, October 1995.
      BibTeX TR95-15 PDF
      • @techreport{MERL_TR95-15,
      • author = {Eero P. Simoncelli, William T. Freeman},
      • title = {The Steerable Pyramid: A Flexible Architecture for Multi-Scale Derivative Computation},
      • institution = {MERL - Mitsubishi Electric Research Laboratories},
      • address = {Cambridge, MA 02139},
      • number = {TR95-15},
      • month = oct,
      • year = 1995,
      • url = {https://www.merl.com/publications/TR95-15/}
      • }
  • Research Area:

    Computer Vision

Abstract:

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