Abstract:There is existence of poor universality and low prediction precision in citrus canker hyperspectral models in previous research. It is necessary to investigate an approach to improve the robustness of hyperspetral model transfer between different instruments which proposed to improve the robustness of the calibration model. Hyperspectral images of two different varieties including Navel Orange 52andCaraCarawere acquired using a laboratory hyperspectral imaging system (System 1, S1) and a portable hyperspectral imaging system (System 2, S2). The discriminant models for the citrus canker detection were developed based on the images from S1 and S2, respectively, and different pretreatment and classification methods were also investigated. Meanwhile, direct standardization (DS) algorithm was used to calibrate hyperspectral images collected by S2 which was considered as the slave while S1 as the master, and the performance of the discriminant model were evaluated before and after the model transfer. It was shown that the best discriminant results were achieved by the extreme learning machine (ELM) combined with the second-order derivative with the classification accuracies of 97.5% by S1 and 98.3% by S2, respectively. By using DS,the classification accuracy increased from 38.1% to 86.2% after the model transfer. It is demonstrated that the DS algorithm is useful for the calibration model transfer between different instruments, which would be helpful for developing a robust method for the citrus canker detection.
Key words:Citrus; Canker; Model transfer; Hyperspectral image; Direct standardization algorithm
翁海勇,岑海燕,何 勇. 直接校正算法的柑橘溃疡病高光谱模型传递[J]. 光谱学与光谱分析, 2018, 38(01): 235-239.
WENG Hai-yong, CEN Hai-yan, HE Yong. Hyperspectral Model Transfer for Citrus Canker Detection Based on Direct Standardization Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2018, 38(01): 235-239.
[1] Li J Y, Wang N. Phytopathology, 2014, 104 (2): 134.
[2] Moschini R C, Canteros B I, Martínez M I, et al. Australasian Plant Pathology, 2014, 43(6): 653.
[3] Song M A, Park J S, Kim K D, et al. Plant Pathol. J, 2015, 31(4): 343.
[4] Gambley C F, Miles A K, Ramsden M, et al. Australasian Plant Pathology, 2009, 38(6): 547.
[5] Li J B, Rao X Q, Ying Y B. Journal of the Science of Food and Agriculture, 2012, 92(1): 125.
[6] Li J B, Rao X Q, Guo J, et al. 5th International Symposium on Advanced Optical Manufacturing and Testing Technologies, 2010, 7656:76562C.
[7] Qin J, Burks T F, Ritenour M A, et al. Journal of Food Engineering, 2009, 93(2): 183.
[8] Zhao X, Burks T F, Qin J, et al. Sensing and Instrumentation for Food Quality and Safety, 2010, 4(3): 126.
[9] Balasundaram D, Burks T F, Bulanon D M, et al. Postharvest Biology and Technology, 2009, 51(2): 220.
[10] Feudale R N, Woody N A, Tan H, et al. Chemometrics and Intelligent Laboratory Systems, 2002, 64(2): 181.
[11] Lira D E, Vasconcelos D E, Claudete, et al. Fuel, 2010, 89(2): 405.
[12] Salguero-Chaparro L, Palagos B, Pea-Rodríguez F, et al. Computers and Electronics in Agriculture, 2013, 96(6): 202.
[13] LIU Jiao, LI Xiao-yu, GUO Xiao-xu, et al(刘 娇,李小昱,郭小许,等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2014, 30(17): 276.
[14] WANG Ju-xiang, MENG Fan-lei, LIU Lin-mi, et al(王菊香,孟凡磊,刘林密, 等). Acta Armamentarii(兵工学报), 2016, 37(1): 91.
[15] Schimleck L R, Kube P D, Raymond C A, et al. Journal of Wood Chemistry and Technology, 2006, 26(4): 299.
[16] CHEN Yi-yun, QI Kun, LIU Yao-lin, et al(陈奕云,漆 锟,刘耀林,等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015, 35(6): 1705.