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

Eero Simoncelli, William T. Freeman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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)
Title of host publicationIEEE International Conference on Image Processing
Editors Anon
PublisherIEEE
Pages444-447
Number of pages4
Volume3
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

Fingerprint

Derivatives
Decomposition
Tuning
Mathematical operators

ASJC Scopus subject areas

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

Cite this

Simoncelli, E., & Freeman, W. T. (1995). Steerable pyramid: a flexible architecture for multi-scale derivative computation. In Anon (Ed.), IEEE International Conference on Image Processing (Vol. 3, pp. 444-447). IEEE.

Steerable pyramid : a flexible architecture for multi-scale derivative computation. / Simoncelli, Eero; Freeman, William T.

IEEE International Conference on Image Processing. ed. / Anon. Vol. 3 IEEE, 1995. p. 444-447.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Simoncelli, E & Freeman, WT 1995, Steerable pyramid: a flexible architecture for multi-scale derivative computation. in Anon (ed.), IEEE International Conference on Image Processing. vol. 3, IEEE, pp. 444-447, Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3), Washington, DC, USA, 10/23/95.
Simoncelli E, Freeman WT. Steerable pyramid: a flexible architecture for multi-scale derivative computation. In Anon, editor, IEEE International Conference on Image Processing. Vol. 3. IEEE. 1995. p. 444-447
Simoncelli, Eero ; Freeman, William T. / Steerable pyramid : a flexible architecture for multi-scale derivative computation. IEEE International Conference on Image Processing. editor / Anon. Vol. 3 IEEE, 1995. pp. 444-447
@inproceedings{4d9d6c253b2a44d8807b5b36c057d4ca,
title = "Steerable pyramid: a flexible architecture for multi-scale derivative computation",
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.",
author = "Eero Simoncelli and Freeman, {William T.}",
year = "1995",
language = "English (US)",
volume = "3",
pages = "444--447",
editor = "Anon",
booktitle = "IEEE International Conference on Image Processing",
publisher = "IEEE",

}

TY - GEN

T1 - Steerable pyramid

T2 - a flexible architecture for multi-scale derivative computation

AU - Simoncelli, Eero

AU - Freeman, William T.

PY - 1995

Y1 - 1995

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0029487233&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029487233&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0029487233

VL - 3

SP - 444

EP - 447

BT - IEEE International Conference on Image Processing

A2 - Anon, null

PB - IEEE

ER -