Neural network model for rotation invariant recognition of object shapes
Applied Optics, Vol. 49, Issue 22, pp. 4144-4151 (2010)
http://dx.doi.org/10.1364/AO.49.004144
Enhanced HTML 
Acrobat PDF (1257 KB)
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
© 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
Related Journal Articles 
- Apochromatic optical correlation (OL)
- Real-time holograms generated by second-harmonic cross correlation of object and reference optical wave fields (OL)
- Shape from shading for multiple light sources (JOSAA)
- Bayesian theory for target location in noise with unknown spectral density (JOSAA)
- Statistical Performance of Cascaded Linear Shift-Invariant Processing (AO)
Related Conference Papers
- Fisher Information of 3D Rotating Point Spread Functions
- Large Area Pyroelectric Motion Tracking System
- Spatial Position Detection of Three-Dimensional Object Using Complex Amplitude Derived from Fourier Transform Profilometry
- Shift-Invariant Real-Time Edge-Enhanced VanderLugt Correlator Using Video-Rate Compatible Photorefractive Polymer
- Compact Laser Scanning Distance Sensor with a Two-Axis Gimbaled Microscanner for Volumetric Imaging
« Previous Article | Next Article »
OSA is a member of 