Edge detection using a neural network

Author

Paik, Joon ; Katsaggelos, Aggelos

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., Northwestern Univ., Evanston, IL, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

2145

Abstract

An edge detection algorithm using multistate ADALINES (adaptive linear neurons) is presented. The proposed algorithm can suppress noise effects without increasing the mask size. The input states are defined using the local mean in a predefined mask, and the one-dimensional edges are defined so that they are linearly separable from nonedges. The two-dimensional edges are obtained using the rotation invariant property of layered neural networks. The proposed algorithm requires much less computation compared with Marr and Hildreth´s (1980) edge detector for similar performance. An application of the proposed edge detector to adaptive image restoration is also presented

Keywords

neural nets; picture processing; adaptive image restoration; adaptive linear neurons; edge detection algorithm; edge detector; image processing; input states; layered neural networks; local mean; rotation invariant property; Adaptive systems; Detectors; Image edge detection; Image processing; Image restoration; Laplace equations; Matched filters; Neural networks; Neurons; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115962

Filename

115962