Efficient neural network implementation of morphological operations

Aldo Morales; Sung Jea Ko

doi:10.1117/12.58386.full

Efficient neural network implementation of morphological operations

Aldo Morales
, Sung Jea Ko

Research output: Contribution to journal › Conference article › peer-review

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 language	English
Pages (from-to)	276-286
Number of pages	11
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1658
DOIs	https://doi.org/10.1117/12.58386.full
Publication status	Published - 1992 Apr 1
Externally published	Yes
Event	Nonlinear Image Processing III 1992 - San Jose, United States Duration: 1992 Feb 9 → 1992 Feb 14

ASJC Scopus subject areas

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

Access to Document

10.1117/12.58386.full

Cite this

@article{ac4d450580a64a74917f7d3246981d0f,

title = "Efficient neural network implementation of morphological operations",

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.",

author = "Aldo Morales and Ko, \{Sung Jea\}",

year = "1992",

month = apr,

day = "1",

doi = "10.1117/12.58386.full",

language = "English",

volume = "1658",

pages = "276--286",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

note = "Nonlinear Image Processing III 1992 ; Conference date: 09-02-1992 Through 14-02-1992",

}

TY - JOUR

T1 - Efficient neural network implementation of morphological operations

AU - Morales, Aldo

AU - Ko, Sung Jea

PY - 1992/4/1

Y1 - 1992/4/1

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/0042316542

UR - https://www.scopus.com/pages/publications/0042316542#tab=citedBy

U2 - 10.1117/12.58386.full

DO - 10.1117/12.58386.full

M3 - Conference article

AN - SCOPUS:0042316542

SN - 0277-786X

VL - 1658

SP - 276

EP - 286

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Nonlinear Image Processing III 1992

Y2 - 9 February 1992 through 14 February 1992

ER -

Efficient neural network implementation of morphological operations

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this