OSA's Digital Library

Chinese Optics Letters

Chinese Optics Letters

| PUBLISHED MONTHLY BY CHINESE LASER PRESS AND DISTRIBUTED BY OSA

  • Vol. 2, Iss. 4 — Apr. 10, 2004
  • pp: 213–216

Hopfield neural network and its applications on image edge detection

Yonghong Zhang, Dejin Hu, Kai Zhang, and Junjie Xu  »View Author Affiliations


Chinese Optics Letters, Vol. 2, Issue 4, pp. 213-216 (2004)


View Full Text Article

Acrobat PDF (615 KB)





Browse Journals / Lookup Meetings

Browse by Journal and Year


   


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools

Share
Citations
  • Export Citation/Save Click for help

Abstract

A method of image edge detection using the Hopfield neural network (HNN) is proposed in this paper. The image edge parameters are introduced in detail, and the energy function of HNN is given based on the edge parameters. Tests on the image edge detection show that images detected by the proposed method have good edge closeness and true edge, at the same time it has good anti-noise performance. The image edge detection using HNN is better than that obtained by some other edge detection operators.

© 2005 Chinese Optics Letters

OCIS Codes
(100.2000) Image processing : Digital image processing
(100.2960) Image processing : Image analysis
(100.3010) Image processing : Image reconstruction techniques
(110.2970) Imaging systems : Image detection systems

Citation
Yonghong Zhang, Dejin Hu, Kai Zhang, and Junjie Xu, "Hopfield neural network and its applications on image edge detection," Chin. Opt. Lett. 2, 213-216 (2004)
http://www.opticsinfobase.org/col/abstract.cfm?URI=col-2-4-213

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Log in to access OSA Member Subscription

« Previous Article  |  Next Article »

OSA is a member of CrossRef.

CrossCheck Deposited