基于机器视觉系统佛手炮制前后的判别及颜色-成分相关性分析

Discrimination and color component correlation analysis of Citrus Medica before and after processing based on machine vision system

目的 基于机器视觉系统探讨佛手炮制前后颜色判别及颜色-成分质量分数相关性,为佛手饮片质量控制提供依据。方法 利用高效液相色谱(HPLC)法测定佛手与蒸佛手饮片中橙皮苷、6,7-二甲氧基香豆素、莨菪亭3种成分的质量分数;采用机器视觉技术获得饮片图像并提取饮片RGB、L*a*b*、HSV 3个不同颜色空间的颜色特征,采用线性判别分析(LDA)、偏最小二乘法-判别分析(PLS-DA)和支持向量机(SVM)等机器学习方法对佛手炮制前后建立定性判别模型,利用Pearson相关性分析研究颜色特征值与测得的3种成分质量分数间的相关性。结果LDA、PLS-DA、SVM判别模型分类鉴别具有较高的预测精度和较低的预估错误率;佛手和蒸佛手中成分质量分数与颜色特征值间存在一定的相关性。结论 基于机器视觉系统对佛手炮制前后的判别效果良好,且该方法操作简单、高效准确,可为佛手及其炮制品的质量控制和临床应用提供参考。

Objective To discriminate the different processed products of Citrus Medica and the correlation between color and component content based on machine vision system,and provide reference for quality evaluation and processing control of Citrus Medica.Methods High-performance liquid chromatography method was used to determine the contents of hesperidin,6,7-dimethoxycoumarin,Hyoscytin in Citrus Medica and its processed products.Machine vision system was used to obtain the image of the decoction pieces and extract the color features of the decoction pieces in RGB,L*a*b*and HSV color spaces.Machine learning methods,such as linear discriminant analysis(LDA),partial least squares-discriminant analysis(PLS-DA)and support vector machine(SVM),were used to establish qualitative identification model for the different processed products of Citrus Medica,and analyzed the correlation between the color eigenvalues and the contents of measured 3 components by Pearson correlation analysis.Results LDA,PLS-DA and SVM had higher prediction accuracy and lower prediction error rate.There was a certain correlation between the content of Citrus Medica and its processed product and the color characteristic values.Conclusion Based on the machine vision system,the discrimination effect for different processed products of Citrus Medica is good,and this method is simple,efficient,and accurate,which can provide reference for the quality control and clinical application of Citrus Medica and its processed products.