基于高光谱成像技术快速检测茶叶茶多酚含量

Rapid detection of tea polyphenols in tea based on hyperspectral imaging technology

中文关键词:  高光谱成像技术  波段筛选  二维相关光谱法  茶叶  茶多酚

英文关键词:hyperspectral imager  variable selection  two-dimensional correlation spectroscopy  tea  tea polyphenol

中文摘要:

      目的 建立一种精确、高效的多元校正模型, 实现快速、无损检测茶叶中茶多酚含量。方法 首先利用高光谱成像技术采集单纵茶叶的光谱数据, 其次通过二维相关光谱(two-dimensional correlation spectroscopy techniques, 2D-COS)波段筛选算法提取特征光谱, 最后结合极限学习机(extreme learning machine, ELM)建立茶多酚的预测模型, 并与全波段模型进行对比。结果 经二维相关光谱算法所提取后的特征波段建立的模型预测效果优于全波段模型。茶多酚模型的决定系数(determination coefficient, R2)从0.89上升到0.94, 预测均方根误差(root mean square error of prediction, RMSEP)也从2.37%下降到2.16%。结论 二维相关光谱波段筛选算法有效地提取茶多酚的特征波段, 适用于茶叶中茶多酚含量的快速、无损预测。

英文摘要:

      Objective To establish an accurate and efficient multivariate calibration model for rapid and nondestructive determination of tea polyphenols in tea. Methods Hyperspectral imager was used to collect the spectral data of Dancong tea, and the characteristic spectrum was extracted by two-dimensional correlation spectroscopy techniques (2D-COS) variable selection algorithm and combine with the prediction model of tea polyphenols which compared with the full-band model established by extreme learning machine (ELM). Results The prediction effects of the model based on the characteristic bands extracted by the 2D-COS algorithm was better than that of the full-band model. The coefficient of determination (R2) of tea polyphenols increased from 0.89 to 0.94, and root mean square error of prediction (RMSEP) decreased from 2.37% to 2.16%. Conclusion The 2D-COS variable selection algorithm can effectively extract the characteristic bands of tea polyphenols, which is suitable for rapid and nondestructive prediction of tea polyphenols content.