Rapid discrimination of Chinese dry-cured hams based on Tri-step infrared spectroscopy and computer vision technology

Abstract The aim of this study was to establish rapid and efficient methods based on a Tri-step infrared spectroscopy (Fourier transform infrared spectroscopy (FT-IR) integrated with second derivative infrared spectroscopy (SD-IR) and two-dimensional correlation infrared spectroscopy (2DCOS-IR)) and computer vision technology to identify and evaluate the quality of three Chinese dry-cured hams (Jinhua, Xuanwei and Rugao hams). 9 dry-cured hams (3 different quality grades of each geographical origin) had similar IR spectra. Nevertheless, they could be further discriminated visually by SD-IR and 2DCOS-IR spectra. All samples can be separated by the computer vision technology incorporated with Principal Component Analysis (PCA) and Cluster analysis (CA). This study not only preliminarily verified the possibility of using Tri-step infrared spectroscopy and computer vision technology to discriminate the geographical origins and quality grades of Chinese dry-cured hams, but also provided prospects of the application of infrared spectroscopy and computer vision technology to authenticate other meat products.