Vis enkel innførsel

dc.contributor.authorBjorgan, Asgeir
dc.contributor.authorRandeberg, Lise Lyngsnes
dc.date.accessioned2019-05-23T12:36:53Z
dc.date.available2019-05-23T12:36:53Z
dc.date.created2019-03-06T13:52:45Z
dc.date.issued2019
dc.identifier.citationProceedings of SPIE. 2019, 10889nb_NO
dc.identifier.issn0277-786X
dc.identifier.urihttp://hdl.handle.net/11250/2598591
dc.description.abstractHyperspectral imaging is a useful tool for characterization of human tissue. However, the vast amount of data created makes it challenging and tedious to manually select spatial regions of interest for further processing. In this study, a random forest-based method was evaluated on basis of its ability to segment human skin regions from the background. The method was compared to the performance of two alternative methods, spectral angle mapper (SAM) and a K-means clustering-based method. The methods were tested on hyperspectral images of ex vivo and in vivo human skin in the wavelength range 400-1000 nm. The random forest approach was found to be robust and perform well regardless of image type. The method is simple to train, and requires minimal parameter tuning for good skin segmentation results.nb_NO
dc.language.isoengnb_NO
dc.publisherSociety of Photo Optical Instrumentation Engineers (SPIE)nb_NO
dc.titleA random forest-based method for selection of regions of interest in hyperspectral images of ex vivo human skinnb_NO
dc.typeJournal articlenb_NO
dc.typePeer reviewednb_NO
dc.description.versionpublishedVersionnb_NO
dc.source.volume10889nb_NO
dc.source.journalProceedings of SPIE, the International Society for Optical Engineeringnb_NO
dc.identifier.doihttps://doi.org/10.1117/12.2506620
dc.identifier.cristin1682609
dc.description.localcode© 2019 Society of Photo Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.nb_NO
cristin.unitcode194,63,35,0
cristin.unitnameInstitutt for elektroniske systemer
cristin.ispublishedtrue
cristin.fulltextpreprint
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel