Performance evaluation of dimensionality reduction techniques for multispectral images
2007 (English)In: International journal of imaging systems and technology (Print), ISSN 0899-9457, E-ISSN 1098-1098, Vol. 17, no 3, 202-217 p.Article in journal (Refereed) Published
We consider several collections of multispectral color signals and describe how linear and non-linear methods can be used to investigate their internal structure. We use databases consisting of blackbody radiators, approximated and measured daylight spectra, multispectral images of indoor and outdoor scenes under different illumination conditions and numerically computed color signals. We apply Principal Components Analysis, group-theoretical methods and three manifold learning methods: Laplacian Eigenmaps, ISOMAP and Conformal Component Analysis. Identification of low-dimensional structures in these databases is important for analysis, model building and compression and we compare the results obtained by applying the algorithms to the different databases.
Place, publisher, year, edition, pages
Institutionen för teknik och naturvetenskap , 2007. Vol. 17, no 3, 202-217 p.
Engineering and Technology
IdentifiersURN: urn:nbn:se:liu:diva-10423DOI: 10.1002/ima.20107OAI: oai:DiVA.org:liu-10423DiVA: diva2:17162
This is a postprint of an article published in: Pedro Latorre Carmona & Reiner Lenz, Performance evaluation of dimensionality reduction techniques for multispectral images, 2007, International Journal of Imaging Systems and Technology, (17), 3, 202-217. http://dx.doi.org/ 10.1002/ima.20107 . Copyright: John Wiley & Sons Inc., http://www3.interscience.wiley.com/journal/37666/home2007-12-112007-12-112016-08-31