SELECTION OF SPECTRAL BANDS OR FILTERS FOR MATERIAL CLASSIFICATION UNDER MULTIPLEXED ILLUMINATION
Patent №
US 9,606,056
Granted
2017-03-28
Filed 2014
Owner
CANON KABUSHIKI KAISHA
Lab
—
AI components
3
ml · vision · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
14309771
Material classification using multiplexed illumination by broadband spectral light from multiple different incident angles, coupled with multi-spectral narrow band spectral measurement of light reflected from the illuminated object of unknown material, wherein selection of spectral bands for illumination or for narrow-band capture may comprise analysis of a database of labeled training material samples within a multi-class classification framework, captured using a relatively large number of spectral bands (such as 32 spectral bands), so as to select a subset of a relatively fewer number of spectral bands (such as 5 spectral bands), wherein the selected spectral bands in the subset retain a significant aptitude for distinguishing between different classifications of materials.
AI classification
Ownership
CANON KABUSHIKI KAISHA
assignment · 337210157
Assignors
LIU, CHAO, SKAFF, SANDRA
On an employer assignment, the assignors are typically the inventors.