Neural network representation and implementation of gray scale morphological operators

Sung-Jea Ko, Aldo Morales

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (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. Two learning algorithms are used to train the fuzzy morphological neural networks. The first algorithm utilizes the overall equality index. The second algorithm is based on the averaged least-mean square. It is shown that the LMS based algorithm is simpler and more robust.

Original languageEnglish
Title of host publication1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages105-108
Number of pages4
ISBN (Electronic)0780305930
DOIs
Publication statusPublished - 1992 Jan 1
Externally publishedYes
Event1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 - San Diego, United States
Duration: 1992 May 101992 May 13

Publication series

NameProceedings - IEEE International Symposium on Circuits and Systems
Volume1
ISSN (Print)0271-4310

Conference

Conference1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992
CountryUnited States
CitySan Diego
Period92/5/1092/5/13

Fingerprint

Neural networks
Fuzzy neural networks
Learning algorithms

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Ko, S-J., & Morales, A. (1992). Neural network representation and implementation of gray scale morphological operators. In 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 (pp. 105-108). [230003] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 1). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.1992.230003

Neural network representation and implementation of gray scale morphological operators. / Ko, Sung-Jea; Morales, Aldo.

1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992. Institute of Electrical and Electronics Engineers Inc., 1992. p. 105-108 230003 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ko, S-J & Morales, A 1992, Neural network representation and implementation of gray scale morphological operators. in 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992., 230003, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 1, Institute of Electrical and Electronics Engineers Inc., pp. 105-108, 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992, San Diego, United States, 92/5/10. https://doi.org/10.1109/ISCAS.1992.230003
Ko S-J, Morales A. Neural network representation and implementation of gray scale morphological operators. In 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992. Institute of Electrical and Electronics Engineers Inc. 1992. p. 105-108. 230003. (Proceedings - IEEE International Symposium on Circuits and Systems). https://doi.org/10.1109/ISCAS.1992.230003
Ko, Sung-Jea ; Morales, Aldo. / Neural network representation and implementation of gray scale morphological operators. 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992. Institute of Electrical and Electronics Engineers Inc., 1992. pp. 105-108 (Proceedings - IEEE International Symposium on Circuits and Systems).
@inproceedings{eb91b9d0cbf94872a44b28f5a1eae7b6,
title = "Neural network representation and implementation of gray scale morphological operators",
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. Two learning algorithms are used to train the fuzzy morphological neural networks. The first algorithm utilizes the overall equality index. The second algorithm is based on the averaged least-mean square. It is shown that the LMS based algorithm is simpler and more robust.",
author = "Sung-Jea Ko and Aldo Morales",
year = "1992",
month = "1",
day = "1",
doi = "10.1109/ISCAS.1992.230003",
language = "English",
series = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "105--108",
booktitle = "1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992",

}

TY - GEN

T1 - Neural network representation and implementation of gray scale morphological operators

AU - Ko, Sung-Jea

AU - Morales, Aldo

PY - 1992/1/1

Y1 - 1992/1/1

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. Two learning algorithms are used to train the fuzzy morphological neural networks. The first algorithm utilizes the overall equality index. The second algorithm is based on the averaged least-mean square. It is shown that the LMS based algorithm is simpler and more robust.

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. Two learning algorithms are used to train the fuzzy morphological neural networks. The first algorithm utilizes the overall equality index. The second algorithm is based on the averaged least-mean square. It is shown that the LMS based algorithm is simpler and more robust.

UR - http://www.scopus.com/inward/record.url?scp=85067200544&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067200544&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.1992.230003

DO - 10.1109/ISCAS.1992.230003

M3 - Conference contribution

AN - SCOPUS:85067200544

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

SP - 105

EP - 108

BT - 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992

PB - Institute of Electrical and Electronics Engineers Inc.

ER -