A novel approach to the application of higher order neural networks to image classification / by Fivos Hatsivasiliou and Kenneth L. Sala, Communications Systems Research Antennas and Integrated Electronics. : Co24-3/7-96-005E-PDF
"The applicability of higher order neural networks to the classification of low resolution imagery is investigated. A novel boundary detection and encoding methodology is developed in order to significantly reduce the large number of third order interconnection weights which must be found during the training stage of the neural network. The higher order neural classifier can be trained by presenting only one sample image per class and so enables rapid network learning with a minimal requirement for training data. An extensive, MatLab compatible toolbox developed specifically to implement this approach is described and documented along with the algorithms employed in the image boundary detection and encoding process"--Abstract, page iii.
Lien permanent pour cette publication :
publications.gc.ca/pub?id=9.892986&sl=1
Ministère/Organisme | Canada. Industry Canada, issuing body. Communications Research Centre (Canada), issuing body. |
---|---|
Titre | A novel approach to the application of higher order neural networks to image classification / by Fivos Hatsivasiliou and Kenneth L. Sala, Communications Systems Research Antennas and Integrated Electronics. |
Titre de la série | CRC report ; no. 96-005 |
Type de publication | Série - Voir l'enregistrement principal |
Langue | [Anglais] |
Format | Électronique |
Document électronique | |
Note(s) | Digitized edition from print [produced by Innovation, Science and Economic Development Canada]. "The work described in this document was sponsored by the Department of National Defence under Task 1410-233." Includes bibliographical references (pages REF1-REF-5). Includes abstract in French. |
Information sur la publication | Ottawa : Communication Research Centre, Industry Canada, May 1996. |
Auteur / Contributeur | Hatsivasiliou, Fivos, author. |
Description | 1 online resource (1 volume (various pagings)) : illustrations, graphs. |
Numéro de catalogue |
|
Descripteurs | Neural networks (Computer science) Image processing. Synthetic aperture radar -- Image quality. Réseaux neuronaux (Informatique) Traitement d'images. Radar à synthèse d'ouverture -- Qualité de l'image. |
Demander des formats alternatifs
Pour demander une publication dans un format alternatif, remplissez le formulaire électronique des publications du gouvernement du Canada. Utilisez le champ du formulaire «question ou commentaire» pour spécifier la publication demandée.- Date de modification :