Full metadata record
DC FieldValueLanguage
dc.contributor.authorKANELLOPOULOS Ioannisen_GB
dc.date.accessioned2010-02-25T16:34:49Z-
dc.date.available1996-04-04en_GB
dc.date.available2010-02-25T16:34:49Z-
dc.date.issued1997en_GB
dc.date.submitted1996-04-01en_GB
dc.identifier.citationIntern. Journal of Remote Sensing vol. 18 no. 4 p. 711-725en_GB
dc.identifier.urihttp://publications.jrc.ec.europa.eu/repository/handle/JRC13112-
dc.description.abstractThis paper examines a number of experimental investigations of neural networks used for the classification of remotely sensed satellite imagery at the Joint Research Centre over a period of five years and attemps to draw some conclusions about "best practice" techniques to optimize network training and overall classification performance. The paper examines best practice in such areas as: network architecture selection, use of optimization algorithms, scaling of input data, avoidance of chaos effects, use of enhanced feature sets, and use of hybrid classifier methods. It is concluded that a vast body of accumulated experience is now available and that neural networks can be used reliably and with much confidence for routine operational requirements in remote sensing.en_GB
dc.description.sponsorshipJRC.(SAI)-Space Application Instituteen_GB
dc.format.mediumPrinteden_GB
dc.languageENGen_GB
dc.relation.ispartofseriesJRC13112en_GB
dc.titleStrategies and Best Practice for Neural Network Image Classification.en_GB
dc.typeArticles in periodicals and booksen_GB
JRC Directorate:Joint Research Centre Historical Collection

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


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