Edge detection using a neural network

Joon K. Paik*, Aggelos K. Katsaggelos

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

12 Scopus citations

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 D. Marr and E. Hildreth's (1980) edge detector for similar performance. An application of the proposed edge detector to adaptive image restoration is also presented.

Original languageEnglish (US)
Pages (from-to)2145-2148
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume4
StatePublished - 1990
Event1990 International Conference on Acoustics, Speech, and Signal Processing: Speech Processing 2, VLSI, Audio and Electroacoustics Part 2 (of 5) - Albuquerque, New Mexico, USA
Duration: Apr 3 1990Apr 6 1990

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Edge detection using a neural network'. Together they form a unique fingerprint.

Cite this