Quality assessment of broiler meat using Computer vision technology

The paper presents the application of image analysis and computer vision technology in quality evaluation of broiler meat. Computer vision is a rapid, non-destructive, economic and objective inspection technique, which has expanded into many diverse industries. In this experiment, images were captured from pectoralis major muscle in broiler at 24 hours post-mortem. The software Matlab (R2015a) has been used for image analysis. The physicochemical, proximate, biochemical and microbiological tests were followed to determine different reference values of the sample. Reference color values were measured with the help of a colorimeter. Different color value (L*,a*,b*), pH, drip loss, cooking loss, dry matter, moisture, crude protein, ether extract, ash, Thiobarbituric acid reactive substance (TBARS), Peroxide value (POV), Free fatty acid (FFA), Total coliform count (TCC), Total viable count (TVC) and Total yeast-mould count (TYMC) were measured for this experiment. All determination was done in triplicate and the mean value was reported. Data analysis was carried out using the programme Stat graphics Centurion XV.I. Calibration and validation model were fitted using the software Unscrambler X version 9.7. A higher correlation was found in pH (r=0.64) with L* value obtained from imaging analysis and cooking loss (r=0.60) with ‘a*’ value obtained from imaging analysis and the highest calibration and prediction accuracy was found in pH (R²c =0.64, R²p=0.56) in broiler breast meat. Results of this work indicate the probability of using computer vision technology in predicting quality of meats in the meat processing plant.