Abstract
Confocal Reflectance Microscope images the skin in 4 dimensions. The third and fourth dimensions being the wavelength and the depth, respectively. We compare traditional methods with new techniques for component separation. The components from the skin images are cell/nuclei, mitochondria, melanin, organelles and other minor components. The spectral unmixing method N-finder is used to extract end members. The results of this method will be compared with ICA methods that will be developed for the 4-dimensional data. The components and their concentrations (abundances) will be output from these methods.
Keywords
CRM, ICA
Subject Categories
Imaging systems
Disciplines
Engineering
Publisher
Bernard M. Gordon Center for Subsurface Sensing and Imaging Systems (Gordon-CenSSIS)
Publication Date
2007
Rights Holder
Bernard M. Gordon Center for Subsurface Sensing and Imaging Systems (Gordon-CenSSIS)
Permanent URL
Recommended Citation
Cruz Rivera, Sol M.; Manian, Vidya; and DiMarzio, Charles A., "Component extraction from CRM skin images" (2007). Research Thrust R2 Presentations. Paper 12. http://hdl.handle.net/2047/d10008974
Click button above to open, or right-click to save.
Notes
Poster presented at the 2007 Thrust R2C Multi Spectral Discrimination Methods Conference