低温冷冻和机械损伤条件下马铃薯高光谱图像特征响应特性研究

doi:10.3964/j.issn.1000-0593(2019)11-3571-08

Abstract
References
Related Citation (15)

Download: PDF (3530 KB)
Export: BibTeX | EndNote (RIS)

Abstract The hyperspectral imaging technology was used to detect the frozen and mechanical damaged potatoes. The Zolix’s Image~λ “spectrum” series of hyperspectral imaging device was employed to obtain the intact, frozen and mechanical damaged potato hyperspectral data within band range of 387～1 035 nm; Secondly, the 60×60 pixel sizes of region of interest in the intact, frozen and mechanically damaged potato hyperspectral image was cropped to calculate the average reflectance values; The reflectance spectral curves of frozen potato samples had the obvious absorption peaks near the visible wavelengths of 440, 560 and 680 nm; The reflectance spectral curves ofmechanical damaged potato samples had the obvious absorption peaks near the visible wavelengths of 560 and 680 nm, and the absorption peaks and valleys near the visible wavelength of 680 nm were significantly lower than the frozen potato samples; The reflectance spectral curves of intact potato samples were relatively smooth, and there were no obvious absorption peaks appearing near the visible wavelengths of 560 and 680 nm; There were three absorption peaks near the visible wavelengths of 440, 560 and 680 nm in the bruised samples, and there was a significant reflectance peak near the visible wavelength of 410 nm. Four categories of potato samples demonstrated the different fingerprint characteristics in the reflectance spectral curves, which could be further used for the aim of potato quality discrimination. The instrument, detection environment, illumination intensity and other factors would add the noise variables to the obtained raw spectral data, so thirdly, the chemometric pretreatment methods were employed to eliminate the influence of noise in the raw spectral curves. There were 70 percent of the four kinds of potato samples randomly selected as the training dataset and the remaining 30 percent as test dataset; Fourthly, the method of local outlier factor (LOF) was used to identify the neighborhood point density of the spatial region of the collected potato spectral curves in order to find the abnormal non-nearest neighbor sample distribution to eliminate the abnormal samples; Fifthly, three types of boosting algorithms of extreme gradient boosting (XGBoost), categorical boost (CatBoost) andlight gradient boosting machine (LightGBM) were used to extract the effective characteristic spectral bands from the potato hyperspectral curves, so that the dimensions of massive hyperspectral data for the subsequent classification modeling were reduced; Finally, the characteristic wavelengths of extracted effective spectral data were used to construct the discriminant model of potato quality. The established classification model by using the LightGBM+Logistic regression reached the highest discriminant accuracy of 98.86%. Our study provided the theoretical basis and technical support for effectively monitoring potato quality in the process of modern agricultural production.

Key words：Potato; Quality; Hyperspectral; Frozen; Mechanically damaged

Received: 2019-07-22 Accepted: 2019-09-30

ZTFLH:

S24

Corresponding Authors: LIN Ping E-mail: binglvcha007@126.com

Cite this article:

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2019)11-3571-08 OR https://www.gpxygpfx.com/EN/Y2019/V39/I11/3571

[1] LI Yan, ZHANG Hai-fang, HAN Yu-mei, et al（李艳，张海芳，韩育梅，等）. Food Science and Thchnology(食品科技), 2018, 43(12): 206.
[2] Griffel L M, Delparte D, Edwards J. Computers and Electronics in Agriculture, 2018, 153: 318.
[3] López A, Arazuri S, García I, et al. Journal of Agricultural and Food Chemistry, 2013, 61(23): 5413.
[4] DUAN Ding-ding, HE Ying-bin, YU Jin-kuan, et al（段丁丁，何英彬，于金宽，等）. Journal of Anhui Agricultural University(安徽农业大学学报), 2019, 46(3): 521.
[5] JIN Rui, LI Xiao-yu, YAN Yi-yun, et al（金瑞，李小昱，颜伊芸，等）. Transactions of the Chinese Society of Agricultural Engineering（农业工程学报）, 2015, 31(16): 258.
[6] LI Xiao-yu, XU Sen-miao, FENG Yao-ze, et al（李小昱，徐森淼，冯耀泽，等）. Transactions of the Chinese Society for Agricultural Machinery（农业机械学报）, 2016, 47(1): 221.
[7] Ma Xiaojun, Sha Jinglan, Wang Dehua, et al. Electronic Commerce Research and Applications, 2018, 31: 24.
[8] WANG Fang-jie, WANG Fu-jian, WANG Yu-chen, et al（王芳杰，王福建，王雨晨，等）. Joumal of Transportation Systems Engineering and Information Technology（交通运输系统工程与信息）, 2019, 19(2): 19.
[9] LI Hong-xiang, HUANG Hao, ZHENG Zi-xuan（李鸿祥，黄浩，郑子旋）. Finance（金融）, 2019, 9(3): 137.
[10] Ma Xiaojun, Sha Jinglan, Wang Dehua, et al. Electronic Commerce Research and Applications, 2018, 31: 24.
[11] SHI Jia-qi, ZHANG Jian-hua（史佳琪, 张建华）. Proceedings of the CSEE（中国电机工程学报）, 2019, 5: 23.
[12] Aishwarya Kakade, Baby Kumari, Pankaj Singh Dholaniya. Journal of Theoretical Biology, 2018, 457: 14.
[13] XU Shao-cheng, LI Dong-xi（徐少成，李东喜）. Statistics and Decision(统计与决策), 2018, 34(18): 25.
[14] Trajdos P, Kurzynski M. International Journal of Neural Systems, 2017, 28(9): 1750062.