Preliminary Analysis of RGB Images for the Identification of Defective Maize Kernels

Giorgia Orlandi, Rosalba Calvini, Giorgia Foca, Alessandro Ulrici

Abstract

In order to investigate the effectiveness of multivariate image analysis for the evaluation of maize defects, RGB images of maize samples containing different percentages of defective kernels were acquired and then converted into colourgrams, i.e., signals codifying colour-related features. Multivariate analysis of the colourgrams matrix showed a distribution of the acquired samples according to the amount of defective kernels.

Keywords

maize kernels; defects identification; RGB image; multivariate analysis

Download

IMEKO-TC23-2016-052.pdf

DOI

-

IMEKO TC

TC23 - Metrology in Food and Nutrition

Back to the proceedings