Abstract：Soluble protein and glutathione (GSH) are important physiological and biochemical indicators of mutton, which are also significant in measuring the body’s antioxidant capacity. However, the traditional detection methods are complicated and time-consuming. This report applied visible-near-infrared (400～1 000 nm) hyperspectral imaging technology to achieve nondestructive and rapid detection of soluble protein and glutathione (GSH) content in mutton. Four methods are used to preprocess the original spectral information of the collected 180 mutton samples, and then use the competitive adaptive weighting algorithm (CARS), the wavelength space iterative shrinkage algorithm-iteration and retained information variable method (iVISSA-IRIV) method for characteristics band extraction. At the same time, the gray level co-occurrence matrix method (GLCM) is used to extract the texture information of the principal component image with the highest contribution rate. Finally, the optimized preprocessing method and the characteristic wavelength information are combined with multiple linear regression (MLR), and least squares support vector machine (LS-SVM) prediction models respectively, as spectral information and spectral-texture fusion information, to establish the prediction models of soluble protein and glutathione content of mutton. The results illustrate that the PLSR model of mutton soluble protein content established by the original spectrum without pretreatment has the best effect, and its Rc and Rp are 0.875 7 and 0.854 7, respectively; the PLSR model of mutton GSH content established by the spectra after pretreatment with SNV method work best, with Rc and Rp of 0.804 8 and 0.826 5, respectively. A total of 31 characteristic wavelengths were screened using iVISSA-IRIV, and the Rc and Rp of the established mutton soluble protein LS-SVM model were 0.914 6 and 0.881 8 respectively, which are the best. The meanwhile, 29 characteristic wavelengths were screened using iVISSA-IRIV, and the Rc and Rp of the established mutton GSH-MLR model were optimal, 0.844 6 and 0.870 5, respectively. The comparison of the spectral feature information and the fusion model of the map information revealed that the establishment of the iVISSA-IRIV-LS-SVM model was the best for the prediction of soluble protein in mutton, with Rc and Rp of 0.914 6 and 0.881 8, respectively. The MLR model established by fusion of the spectral feature information extracted by SNV-iVISSA-IRIV method with the texture information is the optimal model for predicting the GSH content of mutton, and its Rc and Rp are 0.849 5 and 0.890 4, respectively. The optimal iVISSA-IRIV-LS-SVM and iVISSA-IRIV-MLR models and imaging processing methods visually represented the spatial distribution of soluble protein and GSH contents of mutton samples in combination with pseudo-color images. The current study demonstrated that the spectral and textural information from hyperspectral images could predict soluble protein and GSH content of mutton.
Key words：Hyperspectral imaging technology; Characteristic wavelength selection; Soluble protein and GSH contents; Textural features; Distribution visualization
乔 芦，王松磊，郭建宏，贺晓光. 结合高光谱图像的光谱和纹理信息预测羊肉可溶性蛋白和GSH含量[J]. 光谱学与光谱分析, 2022, 42(01): 176-183.
QIAO Lu, WANG Song-lei, GUO Jian-hong, HE Xiao-guang. Combination of Spectral and Textural Informations of Hyperspectral Imaging for Predictions of Soluble Protein and GSH Contents in Mutton. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(01): 176-183.
[1] Zhu Y, Wu J, Wang K, et al. Talanta, 2020, 224: 121852.
[2] Chen J, Li Y, Feng X, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 246: 119041.
[3] Ke J, Rao L, Zhou L, et al. Infrared Physics & Technology, 2020, 105: 103185.
[4] Lu Y, Wang W, Ni X, et al. Infrared Physics & Technology, 2020, 111: 103509.
[5] Xiong Z, Sun D, Pu H, et al. LWT - Food Science and Technology, 2015, 60(2, Part 1): 649.
[6] SUN Zong-bao，LIANG Li-ming，LI Jun-kui, et al(孙宗保，梁黎明，李君奎, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(11): 3530.
[7] Lin H, Zhao J, Chen Q, et al. Food Research International, 2013, 54(1): 821.
[8] Yang D, He D, Lu A, et al. Infrared Physics & Technology, 2017, 83: 206.
[9] Zhang H, Zhang S, Chen Y, et al. Journal of Food Composition and Analysis, 2020, 92: 103567.
[10] DUAN Yu-fei，WANG Qiao-hua(段宇飞，王巧华). Food Science(食品科学), 2020, 41(12): 273.
[11] Zhang C, Wu W, Zhou L, et al. Food Chemistry, 2020, 319: 126536.
[12] Li H, Zhu J, Jiao T, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2020, 243: 118765.
[13] Zhang R, Zhang F, Chen W, et al. Chemometrics and Intelligent Laboratory Systems, 2019, 184: 132.
[14] Cozzolino D, Murray I. LWT—Food Science and Technology, 2004, 37(4): 447.
