不同波长提取方法的高光谱成像技术检测番茄叶片早疫病的研究

doi:10.3964/j.issn.1000-0593(2014)05-1362-05

摘要
参考文献
相关文章 (15)

全文: PDF (2174 KB)
输出: BibTeX | EndNote (RIS)

摘要：提出了基于连续投影算法(successive projections algorithm，SPA)、载荷系数法(x-loading weights，x-LW)和格拉姆-施密特正交(gram-schmidt orthogonalization，GSO)提取特征波长的高光谱成像技术检测番茄叶片早疫病的方法。首先获取380～1 023 nm波段范围内70个健康和70个染病番茄叶片的高光谱图像信息，然后提取健康和染病叶片感兴趣区域(region of interest, ROI)的光谱反射率值，建立番茄叶片早疫病的最小二乘-支持向量机(least squares-support vector machine，LS-SVM)鉴别模型，建模集和预测集的鉴别率都是100%。再通过SPA 、x-LW和GSO提取特征波长(effective wavelengths，EW)，并建立EW-LS-SVM和特征波长-线性判别分析(ew-linear discriminant analysis，EW-LDA)鉴别模型。结果显示，每个模型的鉴别效果都很好，EW-LS-SVM模型中预测集的鉴别率都达到了100%，EW-LDA模型中预测集的鉴别率分别是100%, 100%和97.83%。基于SPA, x-LW和GSO所建模型的输入变量分别是4个(492，550，633和680nm)，3个(631，719和747 nm)和2个(533和657 nm)，较少的特征波长便于实时检测仪器的开发。结果表明，高光谱成像技术检测番茄叶片早疫病是可行的，SPA，x-LW和GSO都是非常有效的特征波长提取方法。

关键词：高光谱成像;特征波长;线性判别分析;最小二乘-支持向量机;番茄;早疫病

Abstract：Identification of early blight on tomato leaves by using hyperspectral imaging technique based on different effective wavelengths selection methods (successive projections algorithm，SPA; x-loading weights, x-LW; gram-schmidt orthogonalization，GSO) was studied in the present paper. Hyperspectral images of seventy healthy and seventy infected tomato leaves were obtained by hyperspectral imaging system across the wavelength range of 380～1023 nm. Reflectance of all pixels in region of interest (ROI) was extracted by ENVI 4.7 software. Least squares-support vector machine (LS-SVM) model was established based on the full spectral wavelengths. It obtained an excellent result with the highest identification accuracy (100%) in both calibration and prediction sets. Then, EW-LS-SVM and EW-LDA models were established based on the selected wavelengths suggested by SPA, x-LW and GSO, respectively. The results showed that all of the EW-LS-SVM and EW-LDA models performed well with the identification accuracy of 100% in EW-LS-SVM model and 100%, 100% and 97.83% in EW-LDA model, respectively. Moreover, the number of input wavelengths of SPA-LS-SVM，x-LW-LS-SVM and GSO-LS-SVM models were four (492，550，633 and 680 nm), three (631，719 and 747 nm) and two (533 and 657 nm), respectively. Fewer input variables were beneficial for the development of identification instrument. It demonstrated that it is feasible to identify early blight on tomato leaves by using hyperspectral imaging, and SPA, x-LW and GSO were effective wavelengths selection methods.

Key words：Hyperspectral imaging;Effective wavelengths (EW);Linear discriminant analysis (LDA);Least square-support vector machines (LS-SVM);Tomato;Early blight

收稿日期: 2013-08-07 修订日期: 2013-11-09

中图分类号:	TP391
	S436.4

通讯作者: 何勇 E-mail: yhe@zju.edu.cn

引用本文:

程术希，谢传奇，王巧男，何勇^*，邵咏妮 . 不同波长提取方法的高光谱成像技术检测番茄叶片早疫病的研究 [J]. 光谱学与光谱分析, 2014, 34(05): 1362-1366.
CHENG Shu-xi, XIE Chuan-qi, WANG Qiao-nan, HE Yong^*, SHAO Yong-ni . Different Wavelengths Selection Methods for Identification of Early Blight on Tomato Leaves by Using Hyperspectral Imaging Technique . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2014, 34(05): 1362-1366.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2014)05-1362-05 或 https://www.gpxygpfx.com/CN/Y2014/V34/I05/1362

[1] LU Jia-yun(陆家云). Plant disease diagnose(植物病害诊断). Bejjing: China Agriculture Press(北京：中国农业出版社)，2004, 427.
[2] YE Gong-yin(叶恭银). Plant Protection(植物保护学). Hangzhou: Zhejiang University Press(杭州：浙江大学出版社), 2006, 351.
[3] Sankaran S, Mishra A, Ehsani R, et al. Computers and Electronics in Agriculture, 2010, 72(1): 1.
[4] Kamruzzaman M, Elmasry G, Sun D W, et al. Analytica Chimica Acta, 2011, 714: 57.
[5] Serranti S, Cesare D, Marini F, et al. Talanta, 2013, 103: 276.
[6] Zhang X L, Liu F, He Y, et al. Sensors, 2012, 12(12): 17234.
[7] Barbin D F, ElMasry G, Sun D W, et al. Analytica Chimca Acta, 2012, 719: 30.
[8] Rumpf T, Mahlein A K, Steiner U, et al. Computers and Electronics in Agriculture, 2010, 74(1): 91.
[9] Bauriegel E, Giebel A, Geyer M, et al. Computers and Electronics in Agriculture, 2010, 75(2): 304.
[10] Fiore A D, Reverberi M, Ricelli A, et al. International Journal of Food Microbiology, 2010, 144(1): 64.
[11] Elmasry G, Sun D W, Allen P. Journal of Food Engineering, 2012, 110(1): 127.
[12] Liu F, He Y. Food Research International, 2008, 41(5): 562.
[13] Zhang X L, Liu F, He Y, et al. Biosystems Engineering, 2013, 115(1): 56.
[14] Wu D, Feng L, He Y, et al. Transactions of the ASABE, 2008, 51(6): 2193.
[15] CHU Xiao-li(褚小立). Molecular Spectroscopy Analytical Technology Combined with Chemometrics and its Applications(化学计量学方法与分子光谱分析技术). Beijing: Chemical Industry Press(北京: 化学工业出版社, 2011. 66.
[16] Kamruzzaman M, Elmasry G, Sun D W, et al. Journal of Food Engineering, 2011, 104(3): 332.
[17] Riovanto R, Cynkar W U, Berzaghi P, et al. Journal of Agricultural and Food Chemistry, 2011, 59: 10356.
[18] Wei X, Xu N, Wu D, et al. Food and Pro-Bioprocess Technology, 2014, 7(1): 184.
[19] Zhang X L, He Y. Industrial Crop and Products, 2013, 42: 416.
[20] Liu F, Jiang Y H, He Y. Analytica Chimica Acta, 2009, 635(1), 45.
[21] Wu D, Nie P C, He Y, et al. Food and Bioprocess Technology, 2012, 5(4): 1402.
[22] Liu F, He Y, Wang L. Analytica Chimica Acta, 2008, 615(1): 10.
[23] YIN Xiao-jun，LI Man-chun, ZHAO Si-feng, et al(尹小君，李满春，赵思峰，等). Tanscation of the Chinese Society of Agricultural Engineering(农业工程学报), 2011, 27(12): 136.