Efficient neural network implementation of morphological operations

Aldo Morales, Sung Jea Ko

Research output: Contribution to journalConference article

4 Citations (Scopus)

Abstract

In this paper we introduce a neural network implementation of gray scale operators. In this structure, synaptic weights are represented by a gray scale structuring element and trained by a learning algorithm based on an optimal criterion called the overall equality index. It will be shown that the proposed algorithm leads to a computationally simple implementation. Numerical examples will be presented to illustrate its performance.

Original languageEnglish
Pages (from-to)276-286
Number of pages11
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume1658
DOIs
Publication statusPublished - 1992 Apr 1
Externally publishedYes
EventNonlinear Image Processing III 1992 - San Jose, United States
Duration: 1992 Feb 91992 Feb 14

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Efficient neural network implementation of morphological operations'. Together they form a unique fingerprint.

  • Cite this