Shanmukh, K and Murthy, CNS Ganesh and Venkatesh, YV (1999) Applications of self-organization networks spatially isomorphic to patterns. In: Information Sciences, 114 (1-4). pp. 23-39.
arti.pdf - Published Version
Restricted to Registered users only
Download (753Kb) | Request a copy
A new technique based on self-organization is proposed for classifying patterns (which include characters, and two- and three-dimensional objects). A neuronal network, created to be a physical replica of each exemplar, is mapped onto the given test pattern by self-organization, during which the network undergoes deformation in an attempt to match the given test pattern. The extent of deformation is inversely proportional to the correctness of the match: smaller the deformation, better is the match. A deformation measure is proposed, leading to the classification of the test pattern. Also presented are some algorithmic improvements (including the choice of other deformation measures) to speed up computation. Examples illustrate the versatility of the technique. (C) 1999 Elsevier Science Inc. All rights reserved.
|Item Type:||Journal Article|
|Additional Information:||Copyright of this article belongs to Elsevier Science.|
|Keywords:||Deformation of patterns;Isomorphism;Mapping of patterns; Pattern exemplars;Pattern classification;Self-organization.|
|Department/Centre:||Division of Electrical Sciences > Electrical Engineering|
|Date Deposited:||27 Feb 2009 09:27|
|Last Modified:||19 Sep 2010 04:59|
Actions (login required)