1. 浙江大学生物系统工程与食品科学学院，浙江 杭州 310058 2. Agricultural and Biological Engineering Department, University of Florida, Gainesville, Florida 32611, USA
Study on the Color Determination of Tomato Leaves Stressed by the High Temperature Based on Hyperspectral Imaging
XIE Chuan-qi1, 2, SAHO Yong-ni1, GAO Jun-feng1, HE Yong1*
1. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China 2. Agricultural and Biological Engineering Department, University of Florida, Gainesville, Florida 32611, USA
摘要： 提出了利用可见/近红外高光谱成像技术检测高温障碍胁迫下番茄叶片色差的方法。首先采集380~1 023 nm波段范围内60个高温障碍胁迫和60个健康番茄叶片的高光谱图像，同时获取全部叶片的色差值(L*, a*和b*)，然后提取所有样本的高光谱图像中感兴趣区域(region of interest, ROI)的光谱反射率值。基于不同预处理方法建立偏最小二乘(partial least squares, PLS)预测模型，再利用连续投影算法(successive projections algorithm, SPA)提取特征波长并建立SPA-PLS预测模型。最后分别基于全波段和特征波段建立偏最小二乘-判别分析(partial least squares-discriminant analysis, PLS-DA)模型。结果显示，全波段中基于原始光谱信息建立的模型效果最好，3个色差值的预测集决定系数(determination coefficient, R2)分别是0.818，0.109和0.896;基于特征波长建立的模型预测集R2分别是0.591，0.244和0.673;所有模型预测集的总体识别率均大于77.50%。结果表明，可见/近红外高光谱成像技术检测番茄叶片色差值(L*和b*)和识别高温障碍样本是可行的。
关键词：高光谱成像;色差值;高温障碍;偏最小二乘;番茄
Abstract：Determination of color values on tomato leaves stressed by the high temperature using hyperspectral imaging technique was studied in this paper. Hyperspectral images of sixty healthy and sixty unhealthy tomato leaves in the wavelengths of 380～1 023 nm were acquired by the hyperspectral imaging system. Simultaneously, three color parameters (L*, a* and b*) were measured by a colorimeter. Reflectance of all pixels in the region of interest (ROI) was extracted from the corrected hyperspectral image. Partial Least Squares (PLS) models were established based on different preprocessing methods. Successive Projections Algorithm (SPA) was identified to select effective wavelengths. Finally, Partial Least Squares-Discriminant Analysis (PLS-DA) models were built to classify different types of samples. The results showed that the determination coefficient (R2) were 0.818, 0.109 and 0.896 in the prediction sets of PLS modes; 0.591, 0.244 and 0.673 in the prediction sets of SPA-PLS models. The overall classification accuracy in the prediction sets of PLS-DA models were over 77.50%. It demonstrated that it is feasible to measure color values on tomato leaves and identify different types of samples using hyperspectral imaging technique.
Key words：Hyperspectral imaging;Color;Obstacle by a high temperature;Partial Least Squares(PLS);Tomato
谢传奇1, 2，邵咏妮1，高俊峰1，何 勇1* . 高光谱成像技术检测高温障碍胁迫下番茄叶片色差的研究 [J]. 光谱学与光谱分析, 2015, 35(12): 3431-3435.
XIE Chuan-qi1, 2, SAHO Yong-ni1, GAO Jun-feng1, HE Yong1* . Study on the Color Determination of Tomato Leaves Stressed by the High Temperature Based on Hyperspectral Imaging . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2015, 35(12): 3431-3435.
[1] Tigist M, Workneh T S, Woldetsadik K. Journal of Food Science and Technology, 2013, 50: 477. [2] Willcox J K, Catignani G L, Lazarus S. Critical Reviews in Food Science and nutrition, 2003, 43: 1. [3] Xie C Q, Li X L, Nie P C, et al. Transactions of the ASABE, 2013, 56: 1431. [4] Zhang X L, Liu F, He Y, et al. Biosystems Engineering, 2013, 115: 56. [5] Cheng J H, Qu J H, Sun D W, et al. Food Research International, 2014, 56: 190. [6] Wu D, Sun D W, He Y. Innovative Food Science and Emerging Technologies, 2012, 16: 361. [7] ElMasry G, Sun D W, Allen P. Journal of Food Engineering, 2012, 110: 127. [8] Huang M, Wang Q G, Zhang M, et al. Journal of Food Engineering, 2014, 128: 24. [9] Iqbal A, Sun D W, Allen P. Journal of Food Engineering, 2013, 117: 42. [10] Jiang L L, Liu F, He Y. Sensors, 2012, 12: 3498. [11] Zou X B, Shi J Y, Hao L M, et al. Analytic Chimica Acta, 2011, 706: 105. [12] Wei X, Liu F, Qiu Z J, et al. Food and Bioprocess Technology, 2014, 7(5): 1371. [13] Wu D, Shi H, Wang S J, et al. Analytic Chimica Acta, 2012, 726: 57. [14] Liu S B, Fu Y Q, Nian S. Food Chemistry, 2014, 162: 16.
