Show simple item record

dc.contributor.authorAurdal, Larsen_GB
dc.contributor.authorBrattli, Alvin Andreasen_GB
dc.contributor.authorGlimsdal, Eiriken_GB
dc.contributor.authorKlausen, Runhild Aaeen_GB
dc.contributor.authorLøkken, Kristin Hammarstrømen_GB
dc.contributor.authorPalm, Hans Christianen_GB
dc.date.accessioned2019-01-10T09:57:39Z
dc.date.accessioned2019-01-16T12:55:02Z
dc.date.available2019-01-10T09:57:39Z
dc.date.available2019-01-16T12:55:02Z
dc.date.issued2018
dc.identifier.citationAurdal L, Brattli AA, Glimsdal EG, Klausen RA, Løkken KH, Palm HC. Supporting artificial intelligence with artificial images. Proceedings of SPIE, the International Society for Optical Engineering. 2018en_GB
dc.identifier.urihttp://hdl.handle.net/123456789/77611
dc.identifier.urihttp://hdl.handle.net/20.500.12242/2515
dc.descriptionAurdal, Lars; Brattli, Alvin Andreas; Glimsdal, Eirik; Klausen, Runhild Aae; Løkken, Kristin Hammarstrøm; Palm, Hans Christian. Supporting artificial intelligence with artificial images. Proceedings of SPIE, the International Society for Optical Engineering 2018en_GB
dc.description.abstractInfrared (IR) imagery is frequently used in security/surveillance and military image processing applications. In this article we will consider the problem of outlining military naval vessels in such images. Obtaining these outlines is important for a number of applications, for instance in vessel classification. Detecting this outline is basically a very complex image segmentation task. We will use a special neural network for this purpose. Neural networks have recently shown great promise in a wide range of image processing applications, image segmentation is no exception in this regard. The main drawback when using neural networks for this purpose is the need for substantial amounts of data in order to train the networks. This problem is of particular concern for our application due to the difficulty in obtaining IR images of military vessels. In order to alleviate this problem we have experimented with using alternatives to true IR images for the training of the neural networks. Although such data in no way can capture the exact nature of real IR images, they do capture the nature of IR images to a degree where they contribute substantially to the training and final performance of the neural network.en_GB
dc.language.isoenen_GB
dc.subjectTermSet Emneord::Kunstig intelligens
dc.subjectTermSet Emneord::Bildebehandling
dc.subjectTermSet Emneord::Infrarød avbildning
dc.titleSupporting artificial intelligence with artificial imagesen_GB
dc.typeArticleen_GB
dc.date.updated2019-01-10T09:57:39Z
dc.identifier.cristinID1643514
dc.identifier.cristinID1643514
dc.identifier.doi10.1117/12.2324969
dc.source.issn0277-786X
dc.source.issn1996-756X
dc.type.documentJournal article
dc.relation.journalProceedings of SPIE, the International Society for Optical Engineering


Files in this item

This item appears in the following Collection(s)

Show simple item record