A computer vision system (CVS) and a colorimeter were compared for their abilities to measure the colour of twenty-seven different milks and milk products. The frequency of similarity test showed that CVS-generated colour chips were similar to the actual sample colour in all trials (100%). The CVS-obtained colours were found to be more similar to the colour of sample visualised on the monitor, compared with colorimeter-generated colour chips, with values of 83.3–100.0% depending on the milk product. The third test showed that there was difference between colour measured by CVS and the colorimeter; colorimeter readings resulted in a darker and yellower colour based on average L∗a∗b∗ values, while CVS readings resulted in lighter and less yellow appearance. Compared with a colorimeter, measuring colour by CVS was, therefore, found to be reliable and should be considered as a superior tool for replacing traditional devices by offering improved representativeness and accuracy.