Minimising the energy of active contour model using a Hopfield network

C. T. Tsai, Y. N. Sun, P. C. Chung

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
DOIs
Publication statusPublished - 1993

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'Minimising the energy of active contour model using a Hopfield network'. Together they form a unique fingerprint.

  • Cite this