Minimising the energy of active contour model using a Hopfield network

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Active contour models (snakes) are commonly used for locating the boundary of an object in computer vision applications. The minimisation procedure is the key problem to solve in the technique of active contour models. In this paper, a minimisation method for an active contour model using Hopfield networks is proposed. Due to its network structure, it lends itself admirably to parallel implementation and is potentially faster than conventional methods. In addition, it retains the stability of the snake model and the possibility for inclusion of hard constraints. Experimental results are given to demostrate the feasibility of the proposed method in applications of industrial pattern recognition and medical image processing.

Original languageEnglish
Pages (from-to)297-303
Number of pages7
JournalIEE Proceedings E: Computers and Digital Techniques
Volume140
Issue number6
Publication statusPublished - 1993 Nov

Fingerprint

Medical image processing
Computer vision
Pattern recognition

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Cite this

@article{8282701b43c644ad90fde22f91fcae5c,
title = "Minimising the energy of active contour model using a Hopfield network",
abstract = "Active contour models (snakes) are commonly used for locating the boundary of an object in computer vision applications. The minimisation procedure is the key problem to solve in the technique of active contour models. In this paper, a minimisation method for an active contour model using Hopfield networks is proposed. Due to its network structure, it lends itself admirably to parallel implementation and is potentially faster than conventional methods. In addition, it retains the stability of the snake model and the possibility for inclusion of hard constraints. Experimental results are given to demostrate the feasibility of the proposed method in applications of industrial pattern recognition and medical image processing.",
author = "Tsai, {C. T.} and Yung-Nien Sun and Pau-Choo Chung",
year = "1993",
month = "11",
language = "English",
volume = "140",
pages = "297--303",
journal = "IEE Proceedings E: Computers and Digital Techniques",
issn = "0143-7062",
publisher = "Institution of Electrical Engineers (IEE)",
number = "6",

}

Minimising the energy of active contour model using a Hopfield network. / Tsai, C. T.; Sun, Yung-Nien; Chung, Pau-Choo.

In: IEE Proceedings E: Computers and Digital Techniques, Vol. 140, No. 6, 11.1993, p. 297-303.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Minimising the energy of active contour model using a Hopfield network

AU - Tsai, C. T.

AU - Sun, Yung-Nien

AU - Chung, Pau-Choo

PY - 1993/11

Y1 - 1993/11

N2 - Active contour models (snakes) are commonly used for locating the boundary of an object in computer vision applications. The minimisation procedure is the key problem to solve in the technique of active contour models. In this paper, a minimisation method for an active contour model using Hopfield networks is proposed. Due to its network structure, it lends itself admirably to parallel implementation and is potentially faster than conventional methods. In addition, it retains the stability of the snake model and the possibility for inclusion of hard constraints. Experimental results are given to demostrate the feasibility of the proposed method in applications of industrial pattern recognition and medical image processing.

AB - Active contour models (snakes) are commonly used for locating the boundary of an object in computer vision applications. The minimisation procedure is the key problem to solve in the technique of active contour models. In this paper, a minimisation method for an active contour model using Hopfield networks is proposed. Due to its network structure, it lends itself admirably to parallel implementation and is potentially faster than conventional methods. In addition, it retains the stability of the snake model and the possibility for inclusion of hard constraints. Experimental results are given to demostrate the feasibility of the proposed method in applications of industrial pattern recognition and medical image processing.

UR - http://www.scopus.com/inward/record.url?scp=0027698690&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027698690&partnerID=8YFLogxK

M3 - Article

VL - 140

SP - 297

EP - 303

JO - IEE Proceedings E: Computers and Digital Techniques

JF - IEE Proceedings E: Computers and Digital Techniques

SN - 0143-7062

IS - 6

ER -