A contextual-constraint based Hopfield neural cube for medical image segmentation

Chuan Yu Chang, Pau-Choo Chung

研究成果: Conference contribution

1 引文 (Scopus)

摘要

Proposes a 3-D Hopfield neural network called Contextual-Constraint Based Hopfield Neural Cube (CCBHNC) taking both each single pixel's feature and its surrounding contextual information for image segmentation, mimicking a high-level vision system. Different from other neural networks, CCBHNC extends the two-dimensional Hopfield neural network into a three-dimensional Hopfield neural cube for it to easily take each pixel's surrounding contextual information into its network operation. As CCBHNC uses a high-level image segmentation model, disconnected fractions arising in the course of tiny details or noises will be effectively removed. Furthermore, the CCBHNC follows the competitive learning rule to update the neuron states, thus precluding the necessity of determining the values for the hard constraints in the energy function, which is usually required in a Hopfield neural network, and facilitating the energy function to converge fast. The simulation results indicate that CCBHNC can produce more continued, more intact, and smoother images in comparison with the other methods.

原文English
主出版物標題IEEE Region 10 Annual International Conference, Proceedings/TENCON
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1170-1173
頁數4
ISBN(電子)0780357396, 9780780357396
DOIs
出版狀態Published - 1999 一月 1
事件1999 IEEE Region 10 Conference, TENCON 1999 - Cheju Island, Korea, Republic of
持續時間: 1999 九月 151999 九月 17

出版系列

名字IEEE Region 10 Annual International Conference, Proceedings/TENCON
2
ISSN(列印)2159-3442
ISSN(電子)2159-3450

Other

Other1999 IEEE Region 10 Conference, TENCON 1999
國家Korea, Republic of
城市Cheju Island
期間99-09-1599-09-17

指紋

Hopfield neural networks
Image segmentation
Pixels
Neurons
Neural networks

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

引用此文

Chang, C. Y., & Chung, P-C. (1999). A contextual-constraint based Hopfield neural cube for medical image segmentation. 於 IEEE Region 10 Annual International Conference, Proceedings/TENCON (頁 1170-1173). (IEEE Region 10 Annual International Conference, Proceedings/TENCON; 卷 2). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TENCON.1999.818634
Chang, Chuan Yu ; Chung, Pau-Choo. / A contextual-constraint based Hopfield neural cube for medical image segmentation. IEEE Region 10 Annual International Conference, Proceedings/TENCON. Institute of Electrical and Electronics Engineers Inc., 1999. 頁 1170-1173 (IEEE Region 10 Annual International Conference, Proceedings/TENCON).
@inproceedings{e83d6915195048e291755944c86f8810,
title = "A contextual-constraint based Hopfield neural cube for medical image segmentation",
abstract = "Proposes a 3-D Hopfield neural network called Contextual-Constraint Based Hopfield Neural Cube (CCBHNC) taking both each single pixel's feature and its surrounding contextual information for image segmentation, mimicking a high-level vision system. Different from other neural networks, CCBHNC extends the two-dimensional Hopfield neural network into a three-dimensional Hopfield neural cube for it to easily take each pixel's surrounding contextual information into its network operation. As CCBHNC uses a high-level image segmentation model, disconnected fractions arising in the course of tiny details or noises will be effectively removed. Furthermore, the CCBHNC follows the competitive learning rule to update the neuron states, thus precluding the necessity of determining the values for the hard constraints in the energy function, which is usually required in a Hopfield neural network, and facilitating the energy function to converge fast. The simulation results indicate that CCBHNC can produce more continued, more intact, and smoother images in comparison with the other methods.",
author = "Chang, {Chuan Yu} and Pau-Choo Chung",
year = "1999",
month = "1",
day = "1",
doi = "10.1109/TENCON.1999.818634",
language = "English",
series = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1170--1173",
booktitle = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",
address = "United States",

}

Chang, CY & Chung, P-C 1999, A contextual-constraint based Hopfield neural cube for medical image segmentation. 於 IEEE Region 10 Annual International Conference, Proceedings/TENCON. IEEE Region 10 Annual International Conference, Proceedings/TENCON, 卷 2, Institute of Electrical and Electronics Engineers Inc., 頁 1170-1173, 1999 IEEE Region 10 Conference, TENCON 1999, Cheju Island, Korea, Republic of, 99-09-15. https://doi.org/10.1109/TENCON.1999.818634

A contextual-constraint based Hopfield neural cube for medical image segmentation. / Chang, Chuan Yu; Chung, Pau-Choo.

IEEE Region 10 Annual International Conference, Proceedings/TENCON. Institute of Electrical and Electronics Engineers Inc., 1999. p. 1170-1173 (IEEE Region 10 Annual International Conference, Proceedings/TENCON; 卷 2).

研究成果: Conference contribution

TY - GEN

T1 - A contextual-constraint based Hopfield neural cube for medical image segmentation

AU - Chang, Chuan Yu

AU - Chung, Pau-Choo

PY - 1999/1/1

Y1 - 1999/1/1

N2 - Proposes a 3-D Hopfield neural network called Contextual-Constraint Based Hopfield Neural Cube (CCBHNC) taking both each single pixel's feature and its surrounding contextual information for image segmentation, mimicking a high-level vision system. Different from other neural networks, CCBHNC extends the two-dimensional Hopfield neural network into a three-dimensional Hopfield neural cube for it to easily take each pixel's surrounding contextual information into its network operation. As CCBHNC uses a high-level image segmentation model, disconnected fractions arising in the course of tiny details or noises will be effectively removed. Furthermore, the CCBHNC follows the competitive learning rule to update the neuron states, thus precluding the necessity of determining the values for the hard constraints in the energy function, which is usually required in a Hopfield neural network, and facilitating the energy function to converge fast. The simulation results indicate that CCBHNC can produce more continued, more intact, and smoother images in comparison with the other methods.

AB - Proposes a 3-D Hopfield neural network called Contextual-Constraint Based Hopfield Neural Cube (CCBHNC) taking both each single pixel's feature and its surrounding contextual information for image segmentation, mimicking a high-level vision system. Different from other neural networks, CCBHNC extends the two-dimensional Hopfield neural network into a three-dimensional Hopfield neural cube for it to easily take each pixel's surrounding contextual information into its network operation. As CCBHNC uses a high-level image segmentation model, disconnected fractions arising in the course of tiny details or noises will be effectively removed. Furthermore, the CCBHNC follows the competitive learning rule to update the neuron states, thus precluding the necessity of determining the values for the hard constraints in the energy function, which is usually required in a Hopfield neural network, and facilitating the energy function to converge fast. The simulation results indicate that CCBHNC can produce more continued, more intact, and smoother images in comparison with the other methods.

UR - http://www.scopus.com/inward/record.url?scp=11244327951&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11244327951&partnerID=8YFLogxK

U2 - 10.1109/TENCON.1999.818634

DO - 10.1109/TENCON.1999.818634

M3 - Conference contribution

AN - SCOPUS:11244327951

T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON

SP - 1170

EP - 1173

BT - IEEE Region 10 Annual International Conference, Proceedings/TENCON

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chang CY, Chung P-C. A contextual-constraint based Hopfield neural cube for medical image segmentation. 於 IEEE Region 10 Annual International Conference, Proceedings/TENCON. Institute of Electrical and Electronics Engineers Inc. 1999. p. 1170-1173. (IEEE Region 10 Annual International Conference, Proceedings/TENCON). https://doi.org/10.1109/TENCON.1999.818634