Detection of linear features using a localized Radon transform

Author

Warrick, Abbie L. ; Delaney, Pamela A.

Author_Institution

Imaging & Detection Program, Lawrence Livermore Nat. Lab., CA, USA

fYear

1996

fDate

3-6 Nov. 1996

Firstpage

1245

Abstract

The Radon transform accentuates linear features and has been applied to detection and enhancement problems in images with linear features. However, several difficulties occur when the Radon transform is applied to images which have features with some curvature or features which do not cover the entire extent of the image. A localized Radon transform was established in Copeland et al. (1995) which successfully enhanced line segments and slightly curved features. In this paper an alternate derivation of the localized Radon transform to that of Copeland et al. is provided. Several properties not considered in in that paper are derived and a detection scheme for line segments is developed.

Keywords

Radon transforms; edge detection; feature extraction; image enhancement; curvature; detection scheme; image enhancement; line segments; linear features; localized Radon transform; slightly curved features; Computer vision; Detection algorithms; Detectors; Laboratories; Light rail systems; Maximum likelihood detection; Noise level; Nonlinear filters; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 1996. Conference Record of the Thirtieth Asilomar Conference on

Conference_Location

Pacific Grove, CA, USA

ISSN

1058-6393

Print_ISBN

0-8186-7646-9

Type

conf

DOI

10.1109/ACSSC.1996.599144

Filename

599144