基于高光谱成像技术的小黄瓜水分无损检测

利用近红外高光谱成像技术对小黄瓜的水分进行无损检测研究。采用多元散射校正和 Savitzky-Golay 卷积平滑对900~1700 nm波段范围内的原始光谱进行预处理，选取最优的预处理方法；运用偏最小二乘回归系数选择特征波长，建立全波段和特征波长下的偏最小二乘水分预测模型。结果表明，经过Savitzky-Golay卷积平滑处理后的光谱建模效果最好，且利用特征波长建立的小黄瓜水分校正和验证模型的相关系数和均方根误差分别为0.86，0.90 和0.111，0.156，优于全波段建立的模型。研究表明，采用高光谱成像技术对小黄瓜水分的无损检测是可行的。

Non-destructive detection of moisture content in gherkin using hyperspectral imaging

near-infrared hyperspectral imaging technique was investigated for non-destructive determination of moisture content in gherkin. Multiplicative scatter correction and Savitzky-Golay smoothing were used to acquire the best pretreatment method in the spectral region between 900 nm and 1 700 nm. Optimal wavelengths were selected by regression coefficients of partial least-squares models. Prediction models were developed based on partial least squares method in the full wavelengths and optimal wavelengths. The results show that the best predictions are obtained with Savitzky-Golay smoothing spectral. Models of optimal wavelengths are better than models of full wavelengths for predicting the moisture content in gherkin, and the correlation coefficient and root mean square error of calibration and validation models are 0.86, 0.90 and 0.111, 0.156, respectively. Therefore, it's feasible to determinate the moisture content of gherkin using hyperspectral imaging technique.