Abstract：Hyperspectral image technology has a broad application in the detection and identification of agricultural products. Wild black Goji berries have remarkable economic benefits, and are often impersonated by growing black Goji berries. A nondestructive and fast identification method for wild black Goji berries using hyperspectral image technology is proposed. Obtained results were as follows:(1) a total of 256 samples of black Goji berries (Wild，Growing, 128 each) in the range of 900～1 700 nm were observed, and each average spectra were used as simple spectra. (2) spectral is preprocessed with standardized normal variate transform (SNV) based on the Kennard-Stone(K-S) method, the calibration set and prediction set samples ratio were observed in 2∶1 (pairs). However, the spectra were found reduced in dimension by the successive projections algorithm method (SPA), and the 30 characteristic wavelengths extracted by the full spectra (FS). Then the 30 characteristic wavelengths and the full spectra are used as model inputs, the support vector machine (SVM), extreme learning machine (ELM), and random forest (RF) recognition models were established. (3) In the identification of wild black Goji berries models, the results showed that the calibration identification rate of SVM, ELM, and RF model with reference to FS and SPA were higher than 98.8%, and the prediction set samples rate of SVM, ELM, and RF model were also higher than 97.7%. The identification model of FS was slightly better than the identification model of SPA. However, the characteristic wave constant extracted by SPA is 11.8% less compared to FS, which eventually reduces the calculated model. RF identification model was reported better compared to SVM, and ELM, RF identification rate is 100%. The study has shown that the use of hyperspectral image technology combined with classification models can quickly identify wild black Goji berries.
Key words：Wild black Goji berry; Hyperspectral image technology; Support vector machine; Extreme learning machine; Random forest
[1] Li Y H, Zou X B, Shen T T, et al. Food Analytical Methods, 2016, 10(4): 1.
[2] Tian Zhihao, Aierken Aizezijiang, Pang Huanhuan, et al. Journal of Liquid Chromatography & Related Technologies, 2016, 39(9): 453.
[3] DONG Jin-lei, GUO Wen-chuan(董金磊，郭文川). Food Science(食品科学)，2015，36（16）：101.
[4] LU Na, HAN Ping, WANG Ji-hua(卢 娜，韩 平，王纪华). Journal of Food Safety & Quality(食品安全与检测学报), 2017，8（12）：4594.
[5] Liu Q, Sun K, Peng J, et al. Food Analytical Methods, 2018, 11(5): 1518.
[6] Dong J L, Guo W C, Zhao F, et al. Food Analytical Methods, 2017, 10(2): 477.
[7] BAO Yi-dan, CHEN Na, HE Yong, et al（鲍一丹，陈 纳，何 勇，等）. Optical Precision Engineering（光学精密工程）, 2015, 23(2): 349.
[8] ElMasry G, Wang N, Vigneault C. Postharvest Biology and Technology, 2009, 52(1): 1.
[9] Menesatti P, Zanella A, D’Andrea S, et al. Food and Bioprocess Technology, 2009, 2(3): 308.
[10] Wu D，Shi H, Wang S J, et al. Analytica Chimica Acta, 2012, 726: 57.
[11] KONG Qing-ming, SU Zhong-bin, SHEN Wei-zheng, et al(孔庆明，苏中滨，沈维政，等). Spectroscopy and Spectral Analysis（光谱学与光谱分析），2015, 35(5): 1233.
[12] Yuan Peipei, Chen Hong, Zhou Yicong, et al. Neurocomputing, 2015，167: 528.
[13] Zhang Xiaolong, Lin Xiaoli, Zhao Jiafu, et al. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019，16（3）：774.
[14] LEI Jian-gang, LIU Dun-hua（雷建刚，刘敦华）. Food Science（食品科学）, 2013, 34(20): 148.
