Classification of Fishness Based on Hyperspectra Imaging Technology
ZHANG Hai-liang1, CHU Bing-quan2, YE Qing1, LIU Xue-mei1, LUO Wei1*
1. School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang 330013, China
2. School of Biological and Chemical Engineering, Zhejiang University of Science & Technology, Hangzhou 310023, China
摘要： 采用高光谱成像技术对鱼新鲜度进行检测研究。首先，提取鱼样本感兴趣区域(region of interest, ROI)光谱，分别采用竞争性自适应重加权算法(CARS)，连续投影算法(SPA)和遗传算法(GA)提取特征波长，三种算法分别得到57，31和66个特征变量，采用最小二乘支持向量机和SIMCA作为分类模型，将57，31和66个特征变量作为LS-SVM和SIMCA模型的输入变量建立分类模型，基于SPA-LS-SVM和CARS-LS-SVM模型预测集识别率分别达到了98%和96%，而采用SIMCA建立的模型取得了较差的预测结果，GA-SIMCA, SPA-SIMCA和CARS-SIMCA模型预测集识别率都只是达到了52%。结果表明，LS-SVM作为分类模型优于SIMCA模型，SPA和CARS选择的特征波长，不但可以简化模型，还可以提高模型的预测精度，采用高光谱成像技术可以有效检测鱼的新鲜度，并能准确检测出鱼不同冻融次数和冷冻时间。
关键词：竞争性自适应重加权; 连续投影; 遗传; LS-SVM; SIMCA
Abstract：This study investigated the feasibility of using near infrared hyperspectral imaging system (NIR-HIS) technique for non-destructiveidentification of fresh and frozen-thawed fish fillets. Hyperspectral images of freshness, storage time, and frozen-thawed times offillets for turbot flesh were obtained in the spectral region of 380~1 023 nm. Reflectance values were extracted from each region of interest (ROI) of each sample. Competitive adaptive reweighted sampling (CARS) algorithm, successive projections algorithm (SPA) and genetic algorithm (GA) were carried out to identify the most significant wavelengths. Based on the fifty-seven, thirty-one and sixty-six wavelengths suggested by CARS, SPA and GA, respectively, two classified models (least squares-support vector machine, LS-SVM and SIMCA) were established. Among the established models, SPA-LS-SVM model performed well withthe highest classification rate (100%) in calibration and 98% in prediction sets. SPA-LS-SVM and CARS-LS-SVM models obtainedbetter results 98% and 96% of classification rate in prediction set with thirty-one and fifty-seven effective wavelengths respectively. The CARS-SIMCA, GA-SIMCA and SPA-SIMCA models obtained poor results with 52% of classification rate in prediction set. The results showedthat NIR-HIS technique could be used to identify the varieties of fresh and frozen-thawed fish fillets rapidly and non-destructively, and SPA and CARS were effective wavelengths selection methods.
章海亮，楚秉泉，叶 青，刘雪梅，罗 微. 高光谱成像技术鉴别鱼新鲜度[J]. 光谱学与光谱分析, 2018, 38(02): 559-563.
ZHANG Hai-liang, CHU Bing-quan, YE Qing, LIU Xue-mei, LUO Wei. Classification of Fishness Based on Hyperspectra Imaging Technology. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(02): 559-563.
[1] LIU Xiao-hua，MA Li-zhen，GUO Yao-hua, et al(刘晓华，马俪珍，郭耀华, 等). Food Science(食品科学), 2014，35(24): 316.
[2] Rzepka M, Ozogul F, Surowka K, et al. International Journal of Food Science and Technology, 2013, 48(6): 1318.
[3] Kimiya T, Sivertsen A H, Heia K. Journal of Food Engineering, 2013, 116(3): 758.
[4] Liu D, Zeng X A, Sun D W. Applied Spectroscopy Reviews, 2013, 48(8): 609.
[5] He H, Sun D. Trends in Food Science & Technology, 2015, 46(1): 99.
[6] Cheng J, Sun D. Trends in Food Science & Technology, 2014, 37(2): 78.
[7] Khojastehnazhand M, Khoshtaghaza M H, Mojaradi B, et al. Food Research International, 2014, 56: 25.
[8] Zhu F, Zhang D, He Y, et al. Food and Bioprocess Technology, 2013, 6(10): 2931.
[9] ZHANG Hai-liang，ZHU Feng-le，LIU Xue-mei, et al(章海亮，朱逢乐，刘雪梅, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2014，(6): 272.
[10] LI Jiang-bo, PENG Yan-kun, CHEN Li-ping, et al(李江波，彭彦昆，陈立平, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2014，34(5): 1264.
[11] YU Lei, ZHU Ya-xing, HONG Yong-sheng, et al(于 雷，朱亚星，洪永胜，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报)，2016，32(33)：138.
[12] Li H D, Liang Y Z, Xu Q S, et al. Analytica Chimica Acta, 2009, 648(1): 77.
[13] Liu K, Chen X, Li L, et al. Analytica Chimica Acta, 2015, 858: 16.
[14] Guan X C, Chen X J, Jiang J. African Journal of Agricultural Research, 2011, 6(27): 5987.
[15] Senseney C T, Krahenbuhl R A, Mooney M A. International Journal of Geomechanics, 2013, 13(4): 473.
[16] Vohland M, Besold J, Hill J, et al. Geoderma, 2011, 166(1): 198.
[17] Liu X, Liu J. Measurement, 2013, 46(10): 3808.
[18] Shao Y N, Zhao C J, Bao Y D, et al. Food and Bioprocess Technology, 2012, 5(1): 100.
[19] Makio T, Hiroaki I, Tomohiro T, et al. Classification of Pesticide Residues in the Agricultural Products Based on Diffuse Reflectance IR Spectroscopy. New York: IEEE, 2007. 216.
