Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/62351
Title: Invariant object recognition using a neural template classifier
Authors: Tang, H.W.
Srinivasan, V. 
Ong, S.H. 
Keywords: Invariance
Neural networks
Object recognition
Template classifier
Issue Date: Jul-1996
Citation: Tang, H.W., Srinivasan, V., Ong, S.H. (1996-07). Invariant object recognition using a neural template classifier. Image and Vision Computing 14 (7) : 473-483. ScholarBank@NUS Repository.
Abstract: This paper describes an efficient two-stage neural network for invariant object recognition. It consists of a feature extractor trained by an ART-like fast saturation learning scheme and a delta-rule trained classifier. Objects, represented as edge strength maps derived from raw input images, are scaled to a normalized size and rotated in discrete steps to generate a sequence of localized input feature vectors. The network outputs identify the object and permit the calculation of a confidence level. Experiments show that the system works well even when there is noise and occlusion.
Source Title: Image and Vision Computing
URI: http://scholarbank.nus.edu.sg/handle/10635/62351
ISSN: 02628856
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

5
checked on Feb 27, 2018

WEB OF SCIENCETM
Citations

3
checked on Apr 16, 2018

Page view(s)

25
checked on Mar 12, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.