DSpace
 

EPrints@IIT Delhi >
Faculty Research Publicatons  >
Computer Science and Engineering >

Please use this identifier to cite or link to this item: http://eprint.iitd.ac.in/handle/2074/1163

Full metadata record

DC FieldValueLanguage
dc.contributor.authorBasak, Jayanta-
dc.contributor.authorDas, Anirban-
dc.date.accessioned2006-01-18T03:43:32Z-
dc.date.available2006-01-18T03:43:32Z-
dc.date.issued2003-
dc.identifier.citationNeurocomputing, 51, 125-145en
dc.identifier.urihttp://eprint.iitd.ac.in/dspace/handle/2074/1163-
dc.description.abstractA class of structure seeking neural networks is presented which are capable of learning parametric structures under unsupervised mode. The functionality of the class of networks is analogous to that of the classical Hough transform, one of the most widely used algorithms in visual pattern recognition. However, the present class of networks provide a much more efficient representation with a highly reduced storage space, capability of quantifying the impreciseness in the input, and ability to handle sparse data sets. The effectiveness of the network and its newly defined learning rules is demonstrated on different data sets under noisy conditions.en
dc.format.extent585372 bytes-
dc.format.mimetypeapplication/pdf-
dc.language.isoenen
dc.subjectHough transformen
dc.subjectUnsupervised learningen
dc.subjectParametric representationen
dc.titleHough transform network: a class of networks for identifying parametric structuresen
dc.typeArticleen
Appears in Collections:Computer Science and Engineering

Files in This Item:

File Description SizeFormat
basakhou2003.pdf571.65 kBAdobe PDFView/Open
View Statistics

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

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback