An efficient matching algorithm by a Hybrid Hopfield Network for object recognition

Jung H. Kim; Sung H. Yoon; Yong H. Kim; Eui H. Park; C. Ntuen; Kwang H. Sohn; Winser E. Alexander

doi:10.1109/ISCAS.1992.230647

An efficient matching algorithm by a Hybrid Hopfield Network for object recognition

Jung H. Kim, Sung H. Yoon, Yong H. Kim, Eui H. Park, C. Ntuen, Kwang H. Sohn, Winser E. Alexander

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Hopfield proposed two types of neural networks; Discrete Hopfield Network(DHN) and Continuous Hopfield Network(CHN). Those have been used for solving the famous traveling salesman problem in a sense of optimization. DHN, a stochastic model is simple to implement and fast in computing, but it uses binary value for states of neurons resulting in an approximate solution. On the other hand, CHN gives a near-optimal solution. However, it takes too much time to simulate a differential equation which provides a main characteristic of CHN. A matching problem using a graph matching technique can be cast into an optimization problem. A new method for two-dimensional object recognition using a Hopfield neural network is proposed. A Hybrid Hopfield Network(HHN), which combines the merit of both the Continuous Hopfield Network and the Discrete Hopfield Network, is proposed and some of the advantages such as reliability and speed are shown in this paper. Stable states of neurons are analyzed and predicted based upon theory CHN after the convergence in DHN.

Original language	English
Title of host publication	1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2888-2892
Number of pages	5
ISBN (Electronic)	0780305930
DOIs	https://doi.org/10.1109/ISCAS.1992.230647
Publication status	Published - 1992
Event	1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 - San Diego, United States Duration: 1992 May 10 → 1992 May 13

Publication series

Name	Proceedings - IEEE International Symposium on Circuits and Systems
Volume	6
ISSN (Print)	0271-4310

Conference

Conference	1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992
Country/Territory	United States
City	San Diego
Period	92/5/10 → 92/5/13

Bibliographical note

Funding Information:
Partially supported by the ARO grant no. DAAL03-90-0913

Publisher Copyright:
© 1992 IEEE.

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering

Access to Document

10.1109/ISCAS.1992.230647

Cite this

Kim, J. H., Yoon, S. H., Kim, Y. H., Park, E. H., Ntuen, C., Sohn, K. H., & Alexander, W. E. (1992). An efficient matching algorithm by a Hybrid Hopfield Network for object recognition. In 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 (pp. 2888-2892). [230647] (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS.1992.230647

@inproceedings{628bc0deb9524900a800c7f4949fb704,

title = "An efficient matching algorithm by a Hybrid Hopfield Network for object recognition",

abstract = "Hopfield proposed two types of neural networks; Discrete Hopfield Network(DHN) and Continuous Hopfield Network(CHN). Those have been used for solving the famous traveling salesman problem in a sense of optimization. DHN, a stochastic model is simple to implement and fast in computing, but it uses binary value for states of neurons resulting in an approximate solution. On the other hand, CHN gives a near-optimal solution. However, it takes too much time to simulate a differential equation which provides a main characteristic of CHN. A matching problem using a graph matching technique can be cast into an optimization problem. A new method for two-dimensional object recognition using a Hopfield neural network is proposed. A Hybrid Hopfield Network(HHN), which combines the merit of both the Continuous Hopfield Network and the Discrete Hopfield Network, is proposed and some of the advantages such as reliability and speed are shown in this paper. Stable states of neurons are analyzed and predicted based upon theory CHN after the convergence in DHN.",

author = "Kim, {Jung H.} and Yoon, {Sung H.} and Kim, {Yong H.} and Park, {Eui H.} and C. Ntuen and Sohn, {Kwang H.} and Alexander, {Winser E.}",

note = "Funding Information: Partially supported by the ARO grant no. DAAL03-90-0913 Publisher Copyright: {\textcopyright} 1992 IEEE.; 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 ; Conference date: 10-05-1992 Through 13-05-1992",

year = "1992",

doi = "10.1109/ISCAS.1992.230647",

language = "English",

series = "Proceedings - IEEE International Symposium on Circuits and Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2888--2892",

booktitle = "1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992",

address = "United States",

}

Kim, JH, Yoon, SH, Kim, YH, Park, EH, Ntuen, C, Sohn, KH & Alexander, WE 1992, An efficient matching algorithm by a Hybrid Hopfield Network for object recognition. in 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992., 230647, Proceedings - IEEE International Symposium on Circuits and Systems, vol. 6, Institute of Electrical and Electronics Engineers Inc., pp. 2888-2892, 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992, San Diego, United States, 92/5/10. https://doi.org/10.1109/ISCAS.1992.230647

An efficient matching algorithm by a Hybrid Hopfield Network for object recognition. / Kim, Jung H.; Yoon, Sung H.; Kim, Yong H. et al.
1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992. Institute of Electrical and Electronics Engineers Inc., 1992. p. 2888-2892 230647 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 6).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An efficient matching algorithm by a Hybrid Hopfield Network for object recognition

AU - Kim, Jung H.

AU - Yoon, Sung H.

AU - Kim, Yong H.

AU - Park, Eui H.

AU - Ntuen, C.

AU - Sohn, Kwang H.

AU - Alexander, Winser E.

PY - 1992

Y1 - 1992

N2 - Hopfield proposed two types of neural networks; Discrete Hopfield Network(DHN) and Continuous Hopfield Network(CHN). Those have been used for solving the famous traveling salesman problem in a sense of optimization. DHN, a stochastic model is simple to implement and fast in computing, but it uses binary value for states of neurons resulting in an approximate solution. On the other hand, CHN gives a near-optimal solution. However, it takes too much time to simulate a differential equation which provides a main characteristic of CHN. A matching problem using a graph matching technique can be cast into an optimization problem. A new method for two-dimensional object recognition using a Hopfield neural network is proposed. A Hybrid Hopfield Network(HHN), which combines the merit of both the Continuous Hopfield Network and the Discrete Hopfield Network, is proposed and some of the advantages such as reliability and speed are shown in this paper. Stable states of neurons are analyzed and predicted based upon theory CHN after the convergence in DHN.

AB - Hopfield proposed two types of neural networks; Discrete Hopfield Network(DHN) and Continuous Hopfield Network(CHN). Those have been used for solving the famous traveling salesman problem in a sense of optimization. DHN, a stochastic model is simple to implement and fast in computing, but it uses binary value for states of neurons resulting in an approximate solution. On the other hand, CHN gives a near-optimal solution. However, it takes too much time to simulate a differential equation which provides a main characteristic of CHN. A matching problem using a graph matching technique can be cast into an optimization problem. A new method for two-dimensional object recognition using a Hopfield neural network is proposed. A Hybrid Hopfield Network(HHN), which combines the merit of both the Continuous Hopfield Network and the Discrete Hopfield Network, is proposed and some of the advantages such as reliability and speed are shown in this paper. Stable states of neurons are analyzed and predicted based upon theory CHN after the convergence in DHN.

UR - http://www.scopus.com/inward/record.url?scp=0347716641&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0347716641&partnerID=8YFLogxK

U2 - 10.1109/ISCAS.1992.230647

DO - 10.1109/ISCAS.1992.230647

M3 - Conference contribution

AN - SCOPUS:0347716641

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

SP - 2888

EP - 2892

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992

Y2 - 10 May 1992 through 13 May 1992

ER -

Kim JH, Yoon SH, Kim YH, Park EH, Ntuen C, Sohn KH et al. An efficient matching algorithm by a Hybrid Hopfield Network for object recognition. In 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992. Institute of Electrical and Electronics Engineers Inc. 1992. p. 2888-2892. 230647. (Proceedings - IEEE International Symposium on Circuits and Systems). doi: 10.1109/ISCAS.1992.230647

An efficient matching algorithm by a Hybrid Hopfield Network for object recognition

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this