A Caltech Library Service

Steerable-scalable kernels for edge detection and junction analysis

Perona, Pietro (1992) Steerable-scalable kernels for edge detection and junction analysis. In: Computer Vision -- ECCV '92. Lecture Notes in Computer Science. No.588. Springer-Verlag , New York, pp. 3-18. ISBN 0-387-55426-2.

PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


Families of kernels that are useful in a variety of early vision algorithms may be obtained by rotating and scaling in a continuum a `template' kernel. These multiscale multi-orientation families may be approximated by linear interpolation of a discrete finite set of appropriate `basis' kernels. A scheme for generating such a basis, together with the appropriate interpolation weights, is described. Unlike previous schemes by Perona and Simoncelli et al., it is guaranteed to generate the most parsimonious basic kernel. Additionally, it is shown how to exploit two symmetries in edge-detection kernels for reducing storage and computational costs, and for generating simultaneously endstop- and junction-tuned filters for free.

Item Type:Book Section
Related URLs:
URLURL TypeDescription ReadCube access ItemJournal Article
Perona, Pietro0000-0002-7583-5809
Additional Information:© Springer-Verlag Berlin Heidelberg 1992. This work was partially conducted while at MIT-LIDS with the Center for Intelligent Control systems sponsored by ARO grant DAAL 03-86-K-0171. I have had useful conversations concerning this work with Ted Adelson, Stefano Casadei, Charles Desoer, David Donoho, Peter Falb, Bill Freeman, Federico Girosi, Takis Konstantopoulos, Paul Kube, Olaf Kübler, Jitendra Malik, Stephane Mallat, Sanjoy Mitter, Richard Murray, Massimo Porrati. Federico Girosi and Peter Falb helped with references to the functional analysis textbooks. The simulations have been carried out using Paul Kube's "viz" image-manipulation package. The images have been printed with software provided by Eero Simoncelli. Some of the simulations have been run on a workstation generously made available by prof. Canali of the Università di Padova. Part of this work was conducted while at the M.I.T. I am very grateful to Sanjoy Mitter and the staff of LIDS for their warm year-long hospitality.
Funding AgencyGrant Number
Army Research Office (ARO)DAAL 03-86-K-0171
Subject Keywords:Early Vision, Grouping, Diffusions
Series Name:Lecture Notes in Computer Science
Issue or Number:588
Record Number:CaltechAUTHORS:20140730-101725088
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:47663
Deposited By: Caroline Murphy
Deposited On:05 Aug 2014 23:01
Last Modified:10 Nov 2021 17:48

Repository Staff Only: item control page