a fuzzy hopfield neural network for medical image segmentation

Jzau-Sheng Lin Jzau-Sheng, Kuo-Sheng Cheng, Chi Wu Mao

研究成果: Article

52 引文 (Scopus)

摘要

In this paper, an unsupervised parallel segmentation approach using a fuzzy Hopfield neural network (FHNN) is proposed. The main purpose is to embed fuzzy clustering into neural networks so that on-line learning and parallel implementation for medical image segmentation are feasible. The idea is to cast a clustering problem as a minimization problem where the criteria for the optimum segmentation is chosen as the minimization of the Euclidean distance between samples to class centers. In order to generate feasible results, a fuzzy c-means clustering strategy is included in the Hopfleld neural network to eliminate the need of finding weighting factors in the energy function, which is formulated and based on a basic concept commonly used in pattern classification, called the within-class scatter matrix principle. The suggested fuzzy c-means clustering strategy has also been proven to be convergent and to allow the network to learn more effectively than the conventional Hopfleld neural network. The fuzzy Hopfleld neural network based on the withinclass scatter matrix shows the promising results in comparison with the hard c-means method.

原文English
頁(從 - 到)2389-2398
頁數10
期刊IEEE Transactions on Nuclear Science
43
發行號4 PART 2
DOIs
出版狀態Published - 1996 十二月 1

指紋

Hopfield neural networks
Fuzzy neural networks
Image segmentation
Neural networks
Fuzzy clustering
Pattern recognition
optimization
matrices
learning
casts

All Science Journal Classification (ASJC) codes

  • Nuclear and High Energy Physics
  • Nuclear Energy and Engineering
  • Electrical and Electronic Engineering

引用此文

Lin Jzau-Sheng, Jzau-Sheng ; Cheng, Kuo-Sheng ; Mao, Chi Wu. / a fuzzy hopfield neural network for medical image segmentation. 於: IEEE Transactions on Nuclear Science. 1996 ; 卷 43, 編號 4 PART 2. 頁 2389-2398.
@article{23b8a30fb9384de88e040d178f645e6b,
title = "a fuzzy hopfield neural network for medical image segmentation",
abstract = "In this paper, an unsupervised parallel segmentation approach using a fuzzy Hopfield neural network (FHNN) is proposed. The main purpose is to embed fuzzy clustering into neural networks so that on-line learning and parallel implementation for medical image segmentation are feasible. The idea is to cast a clustering problem as a minimization problem where the criteria for the optimum segmentation is chosen as the minimization of the Euclidean distance between samples to class centers. In order to generate feasible results, a fuzzy c-means clustering strategy is included in the Hopfleld neural network to eliminate the need of finding weighting factors in the energy function, which is formulated and based on a basic concept commonly used in pattern classification, called the within-class scatter matrix principle. The suggested fuzzy c-means clustering strategy has also been proven to be convergent and to allow the network to learn more effectively than the conventional Hopfleld neural network. The fuzzy Hopfleld neural network based on the withinclass scatter matrix shows the promising results in comparison with the hard c-means method.",
author = "{Lin Jzau-Sheng}, Jzau-Sheng and Kuo-Sheng Cheng and Mao, {Chi Wu}",
year = "1996",
month = "12",
day = "1",
doi = "10.1109/23.531787",
language = "English",
volume = "43",
pages = "2389--2398",
journal = "IEEE Transactions on Nuclear Science",
issn = "0018-9499",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4 PART 2",

}

a fuzzy hopfield neural network for medical image segmentation. / Lin Jzau-Sheng, Jzau-Sheng; Cheng, Kuo-Sheng; Mao, Chi Wu.

於: IEEE Transactions on Nuclear Science, 卷 43, 編號 4 PART 2, 01.12.1996, p. 2389-2398.

研究成果: Article

TY - JOUR

T1 - a fuzzy hopfield neural network for medical image segmentation

AU - Lin Jzau-Sheng, Jzau-Sheng

AU - Cheng, Kuo-Sheng

AU - Mao, Chi Wu

PY - 1996/12/1

Y1 - 1996/12/1

N2 - In this paper, an unsupervised parallel segmentation approach using a fuzzy Hopfield neural network (FHNN) is proposed. The main purpose is to embed fuzzy clustering into neural networks so that on-line learning and parallel implementation for medical image segmentation are feasible. The idea is to cast a clustering problem as a minimization problem where the criteria for the optimum segmentation is chosen as the minimization of the Euclidean distance between samples to class centers. In order to generate feasible results, a fuzzy c-means clustering strategy is included in the Hopfleld neural network to eliminate the need of finding weighting factors in the energy function, which is formulated and based on a basic concept commonly used in pattern classification, called the within-class scatter matrix principle. The suggested fuzzy c-means clustering strategy has also been proven to be convergent and to allow the network to learn more effectively than the conventional Hopfleld neural network. The fuzzy Hopfleld neural network based on the withinclass scatter matrix shows the promising results in comparison with the hard c-means method.

AB - In this paper, an unsupervised parallel segmentation approach using a fuzzy Hopfield neural network (FHNN) is proposed. The main purpose is to embed fuzzy clustering into neural networks so that on-line learning and parallel implementation for medical image segmentation are feasible. The idea is to cast a clustering problem as a minimization problem where the criteria for the optimum segmentation is chosen as the minimization of the Euclidean distance between samples to class centers. In order to generate feasible results, a fuzzy c-means clustering strategy is included in the Hopfleld neural network to eliminate the need of finding weighting factors in the energy function, which is formulated and based on a basic concept commonly used in pattern classification, called the within-class scatter matrix principle. The suggested fuzzy c-means clustering strategy has also been proven to be convergent and to allow the network to learn more effectively than the conventional Hopfleld neural network. The fuzzy Hopfleld neural network based on the withinclass scatter matrix shows the promising results in comparison with the hard c-means method.

UR - http://www.scopus.com/inward/record.url?scp=0030213049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030213049&partnerID=8YFLogxK

U2 - 10.1109/23.531787

DO - 10.1109/23.531787

M3 - Article

AN - SCOPUS:0030213049

VL - 43

SP - 2389

EP - 2398

JO - IEEE Transactions on Nuclear Science

JF - IEEE Transactions on Nuclear Science

SN - 0018-9499

IS - 4 PART 2

ER -