肉品挥发性盐基氮的高光谱无损快速检测

Rapid non-destructive detection of total volatile basic nitrogen in pork using hyperspectral technique

中文关键词:  挥发性盐基氮  高光谱成像技术  洛伦兹函数  偏最小二乘回归  多元线性回归  无损检测

英文关键词:total volatile basic nitrogen  hyperspectral imaging technology  Lorentzian distribution  partial least square regression  multiple linear regression  non-destructive detection

中文摘要:

      建立利用高光谱成像技术对生鲜猪肉的挥发性盐基氮含量进行快速无损伤检测的方法。方法 利用400~1100 nm光谱范围的高光谱成像系统, 获取猪肉表面的高光谱图像信息, 通过洛伦兹函数对其表面的扩散信息进行拟合, 结合偏最小二乘回归和多元线性回归两种方法, 分别建立预测猪肉TVB-N含量的预测模型。结果 利用洛伦兹三参数组合[abc]结合MLR方法建立预测猪肉TVB-N含量的模型效果优于PLSR模型, 预测相关系数达到0.90, 标准差为4.67。结论 高光谱成像技术可以快速无损伤检测肉品挥发性盐基氮。

英文摘要:

      Objective To develop a rapid non-destructive method to predict total volatile basic nitrogen (TVB-N) in pork by hyperspectral imaging technology. Methods Hyperspectral scattering images were collected from the pork surface at the range of 400~1100 nm. The spectral scattering profiles at individual wavelength were fitted accurately by Lorentzian distribution (LD) function. The partial least square regression (PLSR) and multiple linear regression (MLR) methods were used to establish the prediction models. Results The MLR model based on combinations of LD “parameter spectra”[abc] was better than PLSR model. The correlation coefficients of validation (RV) for prediction of TVB-N was 0.90, and the standard error of prediction (SEP) was 4.67. Conclusion The hyperspectral imaging technique can be a valid tool to predict TVB-N in pork.