A spread neural network with fuzzy clustering technique applied to color image coding in the MDT domain

Chi Yuan Lin, Chin-Hsing Chen, Ruey Maw Chen

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

Abstract

In this paper an unsupervised parallel approach called fuzzy competitive learning network (FCLN) for vector quantization (VQ) and spread FCLN (SFCLN) for color image compression in the mean value/difference value transform (MDT) domain are proposed. In the FCLN, the codebook design is conceptually considered as a clustering problem. Here, it is a kind of competitive learning network model imposed by the fuzzy clustering strategies working toward minimizing an objective function defined as the average distortion measure between any two training vectors within the same class. The color image information transformed by the MDT operation was separated into RGB 3-plane mean value and detail coefficients. Then the detail coefficients for each plane were trained using the proposed SFCLN method to generate the VQ codebook. The experimental results show that promising codebooks can be obtained using the proposed FCLN and SFCLN for color image compression in the MDT domain.

Original languageEnglish
Title of host publicationProceedings - 9th International Conference on Parallel and Distributed Systems, ICPADS 2002
PublisherIEEE Computer Society
Pages583-588
Number of pages6
ISBN (Electronic)0769517609
DOIs
Publication statusPublished - 2002 Jan 1
Event9th International Conference on Parallel and Distributed Systems, ICPADS 2002 - Taiwan, China
Duration: 2002 Dec 172002 Dec 20

Publication series

NameProceedings of the International Conference on Parallel and Distributed Systems - ICPADS
Volume2002-January
ISSN (Print)1521-9097

Other

Other9th International Conference on Parallel and Distributed Systems, ICPADS 2002
CountryChina
CityTaiwan
Period02-12-1702-12-20

Fingerprint

Fuzzy clustering
Image coding
Vector quantization
Image compression
Color
Neural networks

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture

Cite this

Lin, C. Y., Chen, C-H., & Chen, R. M. (2002). A spread neural network with fuzzy clustering technique applied to color image coding in the MDT domain. In Proceedings - 9th International Conference on Parallel and Distributed Systems, ICPADS 2002 (pp. 583-588). [1183460] (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS; Vol. 2002-January). IEEE Computer Society. https://doi.org/10.1109/ICPADS.2002.1183460
Lin, Chi Yuan ; Chen, Chin-Hsing ; Chen, Ruey Maw. / A spread neural network with fuzzy clustering technique applied to color image coding in the MDT domain. Proceedings - 9th International Conference on Parallel and Distributed Systems, ICPADS 2002. IEEE Computer Society, 2002. pp. 583-588 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS).
@inproceedings{412376f84e09453381cbf09db92669a5,
title = "A spread neural network with fuzzy clustering technique applied to color image coding in the MDT domain",
abstract = "In this paper an unsupervised parallel approach called fuzzy competitive learning network (FCLN) for vector quantization (VQ) and spread FCLN (SFCLN) for color image compression in the mean value/difference value transform (MDT) domain are proposed. In the FCLN, the codebook design is conceptually considered as a clustering problem. Here, it is a kind of competitive learning network model imposed by the fuzzy clustering strategies working toward minimizing an objective function defined as the average distortion measure between any two training vectors within the same class. The color image information transformed by the MDT operation was separated into RGB 3-plane mean value and detail coefficients. Then the detail coefficients for each plane were trained using the proposed SFCLN method to generate the VQ codebook. The experimental results show that promising codebooks can be obtained using the proposed FCLN and SFCLN for color image compression in the MDT domain.",
author = "Lin, {Chi Yuan} and Chin-Hsing Chen and Chen, {Ruey Maw}",
year = "2002",
month = "1",
day = "1",
doi = "10.1109/ICPADS.2002.1183460",
language = "English",
series = "Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS",
publisher = "IEEE Computer Society",
pages = "583--588",
booktitle = "Proceedings - 9th International Conference on Parallel and Distributed Systems, ICPADS 2002",
address = "United States",

}

Lin, CY, Chen, C-H & Chen, RM 2002, A spread neural network with fuzzy clustering technique applied to color image coding in the MDT domain. in Proceedings - 9th International Conference on Parallel and Distributed Systems, ICPADS 2002., 1183460, Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS, vol. 2002-January, IEEE Computer Society, pp. 583-588, 9th International Conference on Parallel and Distributed Systems, ICPADS 2002, Taiwan, China, 02-12-17. https://doi.org/10.1109/ICPADS.2002.1183460

A spread neural network with fuzzy clustering technique applied to color image coding in the MDT domain. / Lin, Chi Yuan; Chen, Chin-Hsing; Chen, Ruey Maw.

Proceedings - 9th International Conference on Parallel and Distributed Systems, ICPADS 2002. IEEE Computer Society, 2002. p. 583-588 1183460 (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS; Vol. 2002-January).

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

TY - GEN

T1 - A spread neural network with fuzzy clustering technique applied to color image coding in the MDT domain

AU - Lin, Chi Yuan

AU - Chen, Chin-Hsing

AU - Chen, Ruey Maw

PY - 2002/1/1

Y1 - 2002/1/1

N2 - In this paper an unsupervised parallel approach called fuzzy competitive learning network (FCLN) for vector quantization (VQ) and spread FCLN (SFCLN) for color image compression in the mean value/difference value transform (MDT) domain are proposed. In the FCLN, the codebook design is conceptually considered as a clustering problem. Here, it is a kind of competitive learning network model imposed by the fuzzy clustering strategies working toward minimizing an objective function defined as the average distortion measure between any two training vectors within the same class. The color image information transformed by the MDT operation was separated into RGB 3-plane mean value and detail coefficients. Then the detail coefficients for each plane were trained using the proposed SFCLN method to generate the VQ codebook. The experimental results show that promising codebooks can be obtained using the proposed FCLN and SFCLN for color image compression in the MDT domain.

AB - In this paper an unsupervised parallel approach called fuzzy competitive learning network (FCLN) for vector quantization (VQ) and spread FCLN (SFCLN) for color image compression in the mean value/difference value transform (MDT) domain are proposed. In the FCLN, the codebook design is conceptually considered as a clustering problem. Here, it is a kind of competitive learning network model imposed by the fuzzy clustering strategies working toward minimizing an objective function defined as the average distortion measure between any two training vectors within the same class. The color image information transformed by the MDT operation was separated into RGB 3-plane mean value and detail coefficients. Then the detail coefficients for each plane were trained using the proposed SFCLN method to generate the VQ codebook. The experimental results show that promising codebooks can be obtained using the proposed FCLN and SFCLN for color image compression in the MDT domain.

UR - http://www.scopus.com/inward/record.url?scp=84948743728&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84948743728&partnerID=8YFLogxK

U2 - 10.1109/ICPADS.2002.1183460

DO - 10.1109/ICPADS.2002.1183460

M3 - Conference contribution

T3 - Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS

SP - 583

EP - 588

BT - Proceedings - 9th International Conference on Parallel and Distributed Systems, ICPADS 2002

PB - IEEE Computer Society

ER -

Lin CY, Chen C-H, Chen RM. A spread neural network with fuzzy clustering technique applied to color image coding in the MDT domain. In Proceedings - 9th International Conference on Parallel and Distributed Systems, ICPADS 2002. IEEE Computer Society. 2002. p. 583-588. 1183460. (Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS). https://doi.org/10.1109/ICPADS.2002.1183460