Share Email Print
cover

Proceedings Paper

Edge Detection By Differences Of Gaussians
Author(s): Ph. Marthon; B. Thiesse; A. Bruel
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The Differences of Gaussians (DOGs) are of fundamental importance in edge detection. They belong to the human vision system as shown by Enroth-Cugell and Robson [ENR66]. The zero-crossings of their outputs mark the loci of the intensity changes. The set of descriptions from different operator sizes forms the input for later visual processes, such as stereopsis and motion analysis. We show that DOGs uniformly converge to the Laplacian of a Gaussian (ΔG2,σ) when both the inhibitory and excitatory variables converge to σ. Spatial and spectral properties of DOGs and ΔGs are compared: width and height of their central positive regions, bandiwidths... Finally, DOGs' responses to some features such as ideal edge, right angle corner, general corner..., are presented and magnitudes of error on edge position are given.

Paper Details

Date Published: 9 June 1986
PDF: 10 pages
Proc. SPIE 0595, Computer Vision for Robots, (9 June 1986); doi: 10.1117/12.952277
Show Author Affiliations
Ph. Marthon, Laboratoire L.S.I. (France)
B. Thiesse, Laboratoire L.S.I. (France)
A. Bruel, Laboratoire L.S.I. (France)


Published in SPIE Proceedings Vol. 0595:
Computer Vision for Robots
Olivier D. Faugeras; Robert B. Kelley, Editor(s)

© SPIE. Terms of Use
Back to Top