Application of Near-Infrared Hyperspectral Imaging to Predicting Water Content in Salmon Flesh
ZHU Feng-le1, HE Yong1, 2, SHAO Yong-ni1*
1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China 2. Cyrus Tang Center for Sensor Materials and Applications, Zhejiang University, Hangzhou 310058, China
Abstract：Near-infrared hyperspectral imaging technique was employed in the present study to determine water contents in salmon flesh rapidly and nondestructively. Altogether 90 samples from different positions of salmon fish were collected for hyperspectral image scanning, and mean spectra were extracted from the region of interest (ROI) inside each image. Sixty samples were randomly selected as calibration set, and the remaining 30 samples formed prediction set. The full-spectrum and water contents were correlated using partial least squares regression (PLSR) and least-squares support vector machines (LS-SVM), which were then applied to predict water contents for prediction samples. A novel variable extraction method called random frog was applied to select effective wavelengths (EWs) from the full-spectrum. PLSR and LS-SVM calibration models were established respectively to detect water contents in salmon based on the EWs. Though the performances of EWs-based models were worse than models using full-spectrum, only 12 wavelengths were used to substitute for the original 151 wavelengths, thus models were greatly simplified and more suitable for practical application. For EWs-based PLSR and LS-SVM models, satisfactory results were achieved with correlation coefficient of prediction (Rp) of 0.92 and 0.93 respectively, and root mean square error of prediction (RMSEP) of 1.31% and 1.18% respectively. The results indicated that near-infrared hyperspectral imaging combined with chemometrics allows accurate prediction of water contents in salmon flesh, providing important reference for the rapid inspection of fish quality.
Key words：Hyperspectral imaging;Salmon;Water contents;Random frog;Least-squares support vector machines
[1] Shimasaki T, Miake K, Tsukamasa Y, et al. Nippon Suisan Gakkaishi, 1994, 60: 569. [2] Wold J P, Isaksson T. Journal of Food Science, 1997, 62(4): 734. [3] Downey G. Food Chemistry, 1996, 55(3): 305. [4] Cen H Y, He Y. Trends in Food Science & Technology, 2007, 18(2): 72. [5] Sivertsen A H, Kimiya T, Heia K. Journal of Food Engineering, 2011, 103(3): 317. [6] Zhu F L, Zhang D R, He Y, et al. Food and Bioprocess Technology, 2013, 6(10): 2931. [7] Wu D, Sun D W. Talanta, 2013, 116(15): 266. [8] Wu D, Sun D W. Talanta, 2013, 111(15): 39. [9] Li H D, Xu Q S, Liang Y Z. Analytica Chimica Acta, 2012, 740: 20. [10] Geladi P, Kowalski B R. Analytica Chimica Acta, 1986, 185: 1. [11] Suykens J A K, De Brabanter J, Lukas L, et al. Neurocomputing, 2002, 48(1-4): 85. [12] GU Yan-ping, ZHAO Wen-jie, WU Zhan-song(顾燕萍, 赵文杰, 吴占松). Journal of Tsinghua University(清华大学学报), 2010, 50(7): 1063. [13] Rasco B A, Miller C E, King T L. Journal of Agricultural and Food Chemistry, 1991, 39(1): 67. [14] Ye S F, Wang D, Min S G. Chemometrics and Intelligent Laboratory Systems, 2008, 91(2): 194.
