The main objective of this study was to quantify changes in physical features of western Canadian wheat kernels caused by moisture increase using a machine vision system. Single wheat kernels of eight western Canadian wheat classes were conditioned to 12, 14, 16, 18, and 20% (wet basis) moisture content, one after another, using headspaces above various concentrations of potassium hydroxide (KOH) solutions which regulated relative humidity. A digital camera of 7.4 x 7.4 μm pixel resolution with an inter-line transfer charge-coupled device (CCD) image sensor was used to acquire images of individual kernels of all samples. A machine vision algorithm developed at the Canadian Wheat Board Centre for Grain Storage Research, University of Manitoba, was implemented to extract 49 morphological features from the wheat kernel images. Of the 49 morphological features, 24, 11, 7, 21, 26, 11, 17, and 9 features of Canada Western Red Spring, Canada Western Amber Durum, Canada Prairie Spring White, Canada Prairie Spring Red, Canada Western Extra Strong, Canada Western Red Winter, Canada Western Hard White Spring, and Canada Western Soft White Spring wheat kernels, respectively, were significantly (α=0.05) different as the moisture content increased from 12 to 20%. Generally the basic morphological features such as area, perimeter, major axis length, minor axis length, maximum radius, minimum radius, and mean radius were linearly increased with increase in moisture content. In all cases the moment and Fourier descriptor features decreased as moisture content increased from 12 to 20%.

The main objective of this study was to quantify changes in physical features of western Canadian wheat kernels caused by moisture increase using a machine vision system. Single wheat kernels of eight western Canadian wheat classes were conditioned to 12, 14, 16, 18, and 20% (wet basis) moisture content, one after another, using headspaces above various concentrations of potassium hydroxide (KOH) solutions which regulated relative humidity. A digital camera of 7.4 x 7.4 μm pixel resolution with an inter-line transfer charge-coupled device (CCD) image sensor was used to acquire images of individual kernels of all samples. A machine vision algorithm developed at the Canadian Wheat Board Centre for Grain Storage Research, University of Manitoba, was implemented to extract 49 morphological features from the wheat kernel images. Of the 49 morphological features, 24, 11, 7, 21, 26, 11, 17, and 9 features of Canada Western Red Spring, Canada Western Amber Durum, Canada Prairie Spring White, Canada Prairie Spring Red, Canada Western Extra Strong, Canada Western Red Winter, Canada Western Hard White Spring, and Canada Western Soft White Spring wheat kernels, respectively, were significantly (α=0.05) different as the moisture content increased from 12 to 20%. Generally the basic morphological features such as area, perimeter, major axis length, minor axis length, maximum radius, minimum radius, and mean radius were linearly increased with increase in moisture content. In all cases the moment and Fourier descriptor features decreased as moisture content increased from 12 to 20%.