Steerable pyramid: a flexible architecture for multi-scale derivative computation

Eero P. Simoncelli, William T. Freeman

Research output: Contribution to conferencePaper

Abstract

An architecture for efficient and accurate linear decomposition of an image into scale and orientation subbands is described. The basis functions of this decomposition are directional derivative operators of any desired order. The decomposition is the latest incarnation of the so-called steerable pyramid. The scale tuning of the filters is constrained by a recursive system diagram. The orientation tuning is constrained by the property of steerability. In addition, the transform is designed to be 'self-inverting' and is essentially aliasing-free. Most importantly, the pyramid can be designed to produce any number of orientation bands.

Original languageEnglish (US)
Pages444-447
Number of pages4
StatePublished - 1995
EventProceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3) - Washington, DC, USA
Duration: Oct 23 1995Oct 26 1995

Other

OtherProceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3)
CityWashington, DC, USA
Period10/23/9510/26/95

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Steerable pyramid: a flexible architecture for multi-scale derivative computation'. Together they form a unique fingerprint.

  • Cite this

    Simoncelli, E. P., & Freeman, W. T. (1995). Steerable pyramid: a flexible architecture for multi-scale derivative computation. 444-447. Paper presented at Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3), Washington, DC, USA, .