Retrainable neural networks for image analysis and classification

Doulamis Anastasios, D; Doulamis Nikolaos, D; Kollias Stefanos, D

dc.contributor.author	Doulamis Anastasios, D	en
dc.contributor.author	Doulamis Nikolaos, D	en
dc.contributor.author	Kollias Stefanos, D	en
dc.date.accessioned	2014-03-01T02:41:30Z
dc.date.available	2014-03-01T02:41:30Z
dc.date.issued	1997	en
dc.identifier.issn	08843627	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/30493
dc.subject	Image Analysis	en
dc.subject	Image Recognition	en
dc.subject	Map Estimation	en
dc.subject	Neural Network Classifier	en
dc.subject	Neural Network	en
dc.subject.other	Estimation	en
dc.subject.other	Feature extraction	en
dc.subject.other	Image analysis	en
dc.subject.other	Image coding	en
dc.subject.other	Image segmentation	en
dc.subject.other	Maximum a posteriori (MAP) estimation technique	en
dc.subject.other	Neural networks	en
dc.title	Retrainable neural networks for image analysis and classification	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICSMC.1997.633215	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICSMC.1997.633215	en
heal.publicationDate	1997	en
heal.abstract	A novel approach is presented in this paper for improving the performance of neural network classifiers in image recognition, segmentation or coding applications, based on a retraining procedure at the user level. The procedure includes a maximum a posteriori (MAP) estimation technique for optimally selecting a retraining data set from the image applied to the network during real life operation, a decision mechanism for automatic activation of network retraining and a neural network module which performs the classification task. The extracted feature set, used for retraining the network, can include additional elements compared to those used in the network initial training phase, so that it better fits the specific application data under consideration. Results are presented which illustrate the theoretical developments as well as the performance of the proposed approach in real life experiments.	en
heal.publisher	IEEE, Piscataway, NJ, United States	en
heal.journalName	Proceedings of the IEEE International Conference on Systems, Man and Cybernetics	en
dc.identifier.doi	10.1109/ICSMC.1997.633215	en
dc.identifier.volume	4	en
dc.identifier.spage	3558	en
dc.identifier.epage	3563	en