Optimal detection of blurred edges

J A Robinson

Optimal detection of blurred edges

Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

I develop a variational model for the detection of blurred edges. Though yielding a complicated general solution, the model gives insight into edge detection models previously proposed for step edges. In particular it shows that a previous Ill? solution for step edges is correct even in the FIR case, and suggests why operators approximating the first derivative of a gaussian are successful, despite their suboptimality for step edge detection.

Original language	English
Title of host publication	16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL III, PROCEEDINGS
Editors	R Kasturi, D Laurendeau, C Suen
Place of Publication	LOS ALAMITOS
Publisher	IEEE Computer Society
Pages	831-834
Number of pages	4
ISBN (Print)	0-7695-1695-X
Publication status	Published - 2002
Event	16th International Conference on Pattern Recognition (ICPR) - QUEBEC CITY Duration: 11 Aug 2002 → 15 Aug 2002

Conference

Conference	16th International Conference on Pattern Recognition (ICPR)
City	QUEBEC CITY
Period	11/08/02 → 15/08/02

Cite this

@inproceedings{1186445c151d4f4a83131b30cd23406f,

title = "Optimal detection of blurred edges",

abstract = "I develop a variational model for the detection of blurred edges. Though yielding a complicated general solution, the model gives insight into edge detection models previously proposed for step edges. In particular it shows that a previous Ill? solution for step edges is correct even in the FIR case, and suggests why operators approximating the first derivative of a gaussian are successful, despite their suboptimality for step edge detection.",

author = "Robinson, {J A}",

year = "2002",

language = "English",

isbn = "0-7695-1695-X",

pages = "831--834",

editor = "R Kasturi and D Laurendeau and C Suen",

booktitle = "16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL III, PROCEEDINGS",

publisher = "IEEE Computer Society",

address = "United States",

note = "16th International Conference on Pattern Recognition (ICPR) ; Conference date: 11-08-2002 Through 15-08-2002",

}

TY - GEN

T1 - Optimal detection of blurred edges

AU - Robinson, J A

PY - 2002

Y1 - 2002

N2 - I develop a variational model for the detection of blurred edges. Though yielding a complicated general solution, the model gives insight into edge detection models previously proposed for step edges. In particular it shows that a previous Ill? solution for step edges is correct even in the FIR case, and suggests why operators approximating the first derivative of a gaussian are successful, despite their suboptimality for step edge detection.

AB - I develop a variational model for the detection of blurred edges. Though yielding a complicated general solution, the model gives insight into edge detection models previously proposed for step edges. In particular it shows that a previous Ill? solution for step edges is correct even in the FIR case, and suggests why operators approximating the first derivative of a gaussian are successful, despite their suboptimality for step edge detection.

M3 - Conference contribution

SN - 0-7695-1695-X

SP - 831

EP - 834

BT - 16TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL III, PROCEEDINGS

A2 - Kasturi, R

A2 - Laurendeau, D

A2 - Suen, C

PB - IEEE Computer Society

CY - LOS ALAMITOS

T2 - 16th International Conference on Pattern Recognition (ICPR)

Y2 - 11 August 2002 through 15 August 2002

ER -