CPC G06T 7/90 (2017.01) [G01J 3/0291 (2013.01); G01J 3/10 (2013.01); G01J 3/462 (2013.01); G01J 3/463 (2013.01); G01J 3/465 (2013.01); G01J 3/51 (2013.01); G01J 3/524 (2013.01); G01N 21/57 (2013.01); G06T 7/11 (2017.01); G06T 2207/10024 (2013.01); G06T 2207/10152 (2013.01); G06T 2207/20012 (2013.01); G06T 2207/20216 (2013.01)] | 18 Claims |
18. A hyperspectral imaging system for measuring one or more colors of a sample surface, comprising:
a sample measurement area;
a pick-up optics assembly including a plurality of selectable spectral filters having different nominal peak wavelengths and a two-dimensional image sensor, where a field of view of the image sensor includes at least a portion the sample measurement area;
at least one processor coupled to the pick-up optics assembly, the at least one processor being configured with instructions stored in non-volatile memory to:
operate the image sensor provide a live view of the field of view of the image sensor;
operate the pick-up optics assembly to obtain at least one two-dimensional image of the sample measurement area for each spectral filter of the plurality of selectable spectral filters;
assemble the images into a hyperspectral image cube having two dimensions corresponding to the image sensor and a third dimension corresponding to the nominal peak wavelengths of the plurality of selectable filters;
wherein the at least one processor is further configured with instructions to:
identify a region of interest in the image cube;
analyze the region of interest to determine whether a sufficient area of uniform color exists to permit a simple color averaging function; and
if a sufficient area of uniform color exists, perform a simple color averaging process to determine a color of the region of interest; and
if a sufficient area of uniform color does not exist, segment pixels of an image to exclude pixels including shadowed surfaces and to exclude pixels including specular reflections resulting in a set of remaining pixels, and to determine a color of the remaining pixels.
|