Title :
Effective compression and reconstruction of human skin hyperspectral reflectance databases
Author :
Tenn F. Chen;Gladimir V. G. Baranoski
Author_Institution :
Natural Phenomena Simulation Group, School of Computer Science, University of Waterloo, 200 University Avenue, Ontario, Canada N2L 3G1
Abstract :
In this paper, we investigate techniques for reducing the dimensionality of skin hyperspectral reflectance databases and maintaining a high degree of fidelity during data reconstruction. We compare results obtained using principal components analysis (PCA) with results provided by a piecewise PCA approach that explores the different roles performed by the main light attenuation agents acting within the cutaneous tissues in the ultraviolet (UV), visible and near-infrared (NIR) domains. Our investigation encapsulates not only skin spectral responses obtained by varying the contents of these agents, but also responses resulting from the absence of melanin pigmentation associated with the vitiligo condition.
Keywords :
"Skin","Principal component analysis","Databases","Hyperspectral imaging","Computational modeling","Lighting","Attenuation"
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE
Electronic_ISBN :
1558-4615
DOI :
10.1109/EMBC.2015.7320010