NIR hyperspectral imaging for fat quantification in minced pork

Minced meats are offered to the consumers with different levels of fat. In addition, they are the main ingredients in a large assortment of processed products like hamburgers, patties and sausages. There is a need for a fast determination technique of different chemical composition in minced meat to ensure that the right amount is presented. In this study, a pushbroom hyperspectral imaging system in the reflectance mode was used as a fast and non-destructive determination method of fat content in minced pork. Near-infrared (NIR) hyperspectral images (900-1700 nm) were acquired and the mean spectra from the minced samples were extracted by automatic segmentation of the region of interest (ROI). Fat content was determined by nuclear magnetic resonance (NMR) and related to the spectral information by partial least-squares regression (PLSR) models. The coefficient of determination obtained by cross-validated PLSR models indicated that the NIR spectral range has good ability to predict the amount of fat (R = 0.95) in pork. Feature-related wavelengths were selected to predict the fat amount using reduced spectral data. The regression model obtained from selected wavelengths was applied back to the spectral image to display the amount of fat in each pixel of the image. The proposed approach permits the quantification and visualisation of the spatial distribution of fat within the sample. This technique represents a potential tool for high-speed assessment of fat content in meat products.