OSA's Digital Library

Applied Optics

Applied Optics

APPLICATIONS-CENTERED RESEARCH IN OPTICS

  • Editor: Joseph N. Mait
  • Vol. 49, Iss. 22 — Aug. 1, 2010
  • pp: 4144–4151

Neural network model for rotation invariant recognition of object shapes

Mausumi Pohit  »View Author Affiliations


Applied Optics, Vol. 49, Issue 22, pp. 4144-4151 (2010)
http://dx.doi.org/10.1364/AO.49.004144


View Full Text Article

Enhanced HTML    Acrobat PDF (1257 KB)





Browse Journals / Lookup Meetings

Browse by Journal and Year


   


Lookup Conference Papers

Close Browse Journals / Lookup Meetings

Article Tools

Share
Citations

Abstract

A multichannel, multilayer feed forward neural network model is proposed for rotation invariant recognition of objects. In the M channel network, each channel consists of a one dimensional slice of the two dimensional (2D) Fourier transform (FT) of the input pattern that connects fully to the weight matrix. Each slice is taken at different angles from the 2D FT of the object. From each channel, only one neuron can fire in the presence of the training object. The output layer sums up the response of the hidden layer neuron and confirms the presence of the object. Rotation invariant recognition from 0 ° to 360 ° is obtained even in the case of degraded images.

© 2010 Optical Society of America

OCIS Codes
(070.4550) Fourier optics and signal processing : Correlators
(150.0150) Machine vision : Machine vision

ToC Category:
Machine Vision

History
Original Manuscript: March 1, 2010
Revised Manuscript: June 24, 2010
Manuscript Accepted: June 25, 2010
Published: July 22, 2010

Citation
Mausumi Pohit, "Neural network model for rotation invariant recognition of object shapes," Appl. Opt. 49, 4144-4151 (2010)
http://www.opticsinfobase.org/ao/abstract.cfm?URI=ao-49-22-4144

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

You do not have subscription access to this journal. Figure files 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. Article level metrics 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