Evaluation of poultry meat colour using computer vision system and colourimeter

Abstract

Purpose The purpose of this paper is to investigate the ability of the computer vision system (CVS) to evaluate the colour of poultry meat. The advantages of the CVS over traditional methods were also explored. Design/methodology/approach The research was carried out on m. pectoralis major samples of three animals for each of the following four species: chicken, turkey, duck and goose. The total colour difference (ΔE) and the degree of difference of hue, chroma and lightness between the methods were calculated. In addition, a trained panel of 14 people was used to carry out three different similarity tests analysed using χ2 one sample test and one-way ANOVA. The correlation coefficient between CVS and colourimeter measures was evaluated using the Spearman rank correlation test. Findings The total colour difference (ΔE) between the methods employed was so large that the generated colour(s) could be considered more opposite than similar. The CVS-generated colour chips were more similar to the sample of the meat products visualised on the monitor compared to colourimeter-generated colour chips in all (100 per cent) individual trials performed. The use of the colourimeter for colour evaluation of lighter coloured poultry meat (chicken and turkey) was unrepresentative. Practical implications In this study, a CVS was developed to measure the colour of poultry meat as an alternative to conventional colourimeters. Originality/value The research has demonstrated that the use of a CVS should be considered a superior alternative to the traditional method for measuring colour of chicken, turkey, duck and goose meat.