6533b82efe1ef96bd1294579
RESEARCH PRODUCT
An Efficient Method for the Visualization of Spectral Images Based on a Perception-Oriented Spectrum Segmentation
Jon Yngve HardebergAlamin MansouriYvon VoisinSteven Le Moansubject
business.industrymedia_common.quotation_subjectMultispectral imageSpectrum (functional analysis)ThresholdingIndependent component analysisVisualizationPerceptionPrincipal component analysisSegmentationComputer visionArtificial intelligencebusinessMathematicsmedia_commondescription
We propose a new method for the visualization of spectral images. It involves a perception-based spectrum segmentation using an adaptable thresholding of the stretched CIE standard observer colormatching functions. This allows for an underlying removal of irrelevant channels, and, consequently, an alleviation of the computational burden of further processings. Principal Components Analysis is then used in each of the three segments to extract the Red, Green and Blue primaries for final visualization. A comparison framework using two different datasets shows the efficiency of the proposed method.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2010-01-01 |