Predicting pork quality using Vis/NIR spectroscopy

Abstract

Visible and near-infrared reflectance spectroscopy (Vis/NIRS) was used to predict the ultimate pH (pHu), color, intramuscular fat (IMF) and shear force (WBSF) of pork samples and to build classifiers capable of categorizing the samples by tenderness (tender or tough) and juiciness (juicy and dry). Spectra were collected from 400 to 1495nm, and 200 data points were generated for every sample (n=134). Sixty-seven percent of the sample set was used for calibration, and 33% was used for validation. Partial least squares (PLS) calibration models were developed for each characteristic measured. A coefficient of determination (R(2)) and residual prediction deviation (RPD) were used to evaluate the accuracy of the calibration models. The pHu and color prediction models developed in this study fit this classification, indicating that these predictive models can be used to predict quality traits of intact pork samples. The Vis/NIRS offered great potential for correctly classifying pork Longissimus into two tenderness and two juiciness classes.

Keywords: NIR spectroscopy; Pork; Quality classification; Quality prediction.