高光谱成像技术结合多元数据分析识别热损伤水稻种子

摘要：种子在干燥过程中由于工艺和温度控制不当常常造成热损伤影响种子活力，如何快速无损地识别受热损伤的种子对 农业生产具有关键作用。本研究采用电加热恒温鼓风干燥箱模拟水稻种子的干燥过程，并进行不同时间加热（未处理， 1h/60℃，3h/60℃，5h/60℃，7h/60℃，9h/60℃，11h/60℃），利用866.4–1701.0nm的高光谱成像系统获取不同程度热损 伤的水稻种子的高光谱图像。采用3种预处理方法(Savitzky-Golay一阶导数、标准正态变量和多元散射校正)对原始光谱 数据进行预处理,采用3种特征提取算法(二阶导数、连续投影算法和邻域成分分析)提取特征波长,采用3种分类器模型(k 最近邻、支持向量机和朴素贝叶斯)进行建模分析。经过多元数据分析,多元散射校正-邻域成分分析-朴素贝叶斯模型表现 最好,被选定为最优模型。最后基于对象的方法对验证集的高光谱图像进行可视化,展示直观的分类效果。结果表明,高光 谱成像技术是一种快速识别和可视化不同程度热损伤水稻种子的有效工具。

关键词：热损伤; 高光谱成像技术; 多元数据分析; 对象式; 水稻种子

期刊：SPECTROSCOPY LETTERS

DOI：https://DOI.org/10.1080/00387010.2020.1726402

设备：GaiaField

Hyperspectral imaging technology combined with multivariate data analysis to identify heat damaged rice seeds

Abstract：Seeds in the drying process due to improper control of process and temperature often cause heat damage to affect seed vigor. How to quickly and nondestructively identify seeds that are heat-damaged plays a key role in agricultural production. In this study, the electric heating con stant temperature blast drying oven was used to simulate the drying process of rice seeds and heated for different time (Untreated, 1h/60 C, 3h/60 C, 5h/60 C, 7h/60 C, 9h/60 C, 11h/ 60 C). The hyperspectral images of rice seeds with different degrees of heat damage were obtained by using a hyperspectral imaging system of 866.4–1701.0nm. Three preprocessing methods (Savitzky-Golay first derivative, standard normal variate, and multivariate scatter correc tion) were used to preprocess the original spectral data, three feature extraction algorithms (second derivative, successive projections algorithm, and neighborhood component analysis) were used to extract the feature wavelengths, and three classifier models (k-nearest neighbor, support vector machine, and naive Bayes) were used for modeling analysis. After multivariate data analysis, the multivariate scatter correction- neighborhood component analysis-naive Bayes model performed best and was selected as the best model. Finally, the hyperspectral images of the verification set were visualized based on the object-wise method to show the intuitive classi fication effect. The results show that the hyperspectral imaging technology is an effective tool for quickly identifying and visualizing rice seeds with different degrees of heat damage.

Keywords：Heat damage; hyperspectral imaging technology; multivariate data analysis; object-wise; rice seed