Peanut kernels from grade samples were sorted into damaged and undamaged categories based on their optical characteristics. A machine vision system used grey level information to detect certain types of damage. Also color coordinate information collected from a colorimeter provided additional damage information. Certain damage categories were correctly classified with 95 accuracy. 1 .
Floyd E. Dowell,
J. H. Powell,
"Damage detection in peanut grade samples using chromaticity and luminance", Proc. SPIE 1379, Optics in Agriculture, (1 February 1991); doi: 10.1117/12.25083; https://doi.org/10.1117/12.25083