Comparison of rapid techniques for classification of ground meat

Abstract

Computer vision and near infrared spectroscopy are fast and non-invasive techniques currently available for processing control in the meat industry. These techniques can be used, either separately or combined, for on-line assessment of meat quality parameters. This study aimed to compare a portable near-infrared (NIR) spectrometer, near infrared hyperspectral imaging (NIR-HSI) and red, green and blue imaging (RGB-I) to differentiate ground samples from beef, pork and chicken meat; and to quantify amounts of each in mixtures. Chicken breast meat was adulterated with either pork leg meat or beef round meat from 0 to 50% (w/w). Partial Least Squares regression (PLSR) models were performed using full spectra and after selecting most important wavelengths. The best results were obtained with NIR-HSI, with coefficient of prediction (RP2) of 0.83 and 0.94, ratio performance to deviation (RPD) of 1.96 and 3.56, and ratio of error range (RER) of 10.0 and 18.1, for samples of chicken adulterated with pork and beef, respectively. In addition, the results obtained using NIR spectroscopy and RGB-I confirm that these techniques provide an alternative for rapid, on-line inspection of ground meat in the food industry.