XXXI International Mineral Processing Congress 2024 Proceedings/Washington, DC/Sep 29–Oct 3 423
These identified areas can further be compared with the
threshold parameters during sorting. This gives another
possibility to recognize particles on the base of their color
and color texture.
In the recent years, the new types of cameras were intro-
duced on the market, using hyperspectral imaging in the
infra-red light spectrum. While standard color cameras pro-
duce three color planes (RGB), the hyperspectral cameras
generate image cubes where over 250 wavelength channels
are recognized, typically in the range of 900–2500 nm. The
light reflectance in this wavelength range is different for
various materials and therefore such cameras can be used
for recognizing specific materials. This type of recognition
is already used for drill core scanning, where mineralogi-
cal composition of the processed material can be identified.
The example of such analysis is shown in Figure 5, where
Figure 3. New sensor response indicating high-density fine intrusions of Au in the low density rock material
Figure 4. RGB camera response indicating different color and shade zones recognized with the specified
threshold parameters