浏览全部资源
扫码关注微信
1.广东药科大学中药学院/国家中医药管理局中药数字化质量评价技术重点研究室/广东高校(省)中药质量工程技术研究中心,广州 510006
2.广东药科大学信息工程学院,广州 510006
Published:30 November 2022,
Received:25 May 2022,
Revised:13 September 2022,
扫 描 看 全 文
张一凡,周苏娟,孟江等.基于机器视觉系统的姜炭炮制程度判别及颜色-成分相关性分析 Δ[J].中国药房,2022,33(22):2712-2718.
ZHANG Yifan,ZHOU Sujuan,MENG Jiang,et al.Discrimination of processing degree of Zingiber officinale charcoal and analysis of the correlation between color and component based on machine vision system[J].ZHONGGUO YAOFANG,2022,33(22):2712-2718.
张一凡,周苏娟,孟江等.基于机器视觉系统的姜炭炮制程度判别及颜色-成分相关性分析 Δ[J].中国药房,2022,33(22):2712-2718. DOI: 10.6039/j.issn.1001-0408.2022.22.05.
ZHANG Yifan,ZHOU Sujuan,MENG Jiang,et al.Discrimination of processing degree of Zingiber officinale charcoal and analysis of the correlation between color and component based on machine vision system[J].ZHONGGUO YAOFANG,2022,33(22):2712-2718. DOI: 10.6039/j.issn.1001-0408.2022.22.05.
目的
2
基于机器视觉系统探讨姜炭炮制程度判别及颜色-成分含量相关性,为姜炭炮制程度控制和质量评价提供参考。
方法
2
采用高效液相色谱法测定干姜及其不同炮制程度姜炭饮片中6-姜酚、8-姜酚、10-姜酚、6-姜烯酚、姜酮5种成分的含量;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,采用机器学习,如主成分分析(PCA)、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)等方法对姜炭不同炮制程度姜炭建立定性判别模型,将颜色特征值与测得的5种成分含量进行相关性分析,建立颜色-成分的定量预测模型。
结果
2
随着炮制程度的加深,姜酮在炮制后产生且含量先增加后降低,标炭饮片中含量最高;6-姜酚、8-姜酚和10-姜酚的含量逐渐降低;6-姜烯酚含量先增加后降低。基于饮片图像颜色客观量化结合有监督判别模式识别方法的LDA和SVM建立的定性判别模型,其交叉验证训练预测准确率达到100%,外部验证准确率达到95.83%。基于饮片图像颜色客观量化结合SVM建立5种成分含量预测模型,RPD值均大于2,各成分的
R
2
P
与
R
2
C
值中姜酮为0.633 9与0.683 3,其他成分值均大于0.75,说明SVM对除姜酮以外的4种成分均有较好的预测能力。
结论
2
基于机器视觉系统对姜炭炮制程度的判别和含量预测模型效果良好,可为姜炭饮片的质量控制和炮制程度的判断提供参考。
OBJECTIVE
2
To explore the discrimination of processing degree of
Zingiber officinale
charcoal and the correlation between color and component content based on machine vision system, and provide reference for quality evaluation and processing degree control of
Z. officinale
charcoal.
METHODS
2
High-performance liquid chromatography method was used to determine the contents of 5 components in
Z. officinale
charcoal and its different processed products, such as 6-gingerol, 8-gingerol, 10-gingerol, 6-shogaol, gingerone. 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 principal component analysis (PCA), linear discriminant analysis (LDA), partial least squares-discriminant analysis (PLS-DA) and support vector machine (SVM), were used to establish qualitative identification model for
Z. officinale
charcoal processed products of different processing degree. The correlation between the color eigenvalues and the contents of measured 5 components were analyzed, and the color-component content prediction model was established.
RESULTS
2
With the deepening of processing, gingerone was produced after processing and the content firstly increased and then decreased, and the content of gingerone in standard carbon was the highest; the contents of 6-gingerol, 8-gingerol and 10-gingerol decreased gradually; the content of 6-shogaol increased firstly and then decreased. The prediction accuracy of qualitative discriminant model, which was established on the basis of objective quantization of image and color combined with LDA and SVM of supervised discriminant pattern recognition method, reached 100% in cross-validation training and 95.83% in the external validation. Content prediction model of 5 components was established on the basis of objective quantization of image and color combined with SVM, the RPD values were all greater than 2, the
R
2
P
and
R
2
C
values of gingerone were 0.633 9 and 0.683 3, and the values of other components were all greater than 0.75, indicating SVM had good prediction ability for the contents of 4 components except for gingerone.
CONCLUSIONS
2
The machine vision system is excellent for the discrimination of the processing degree of
Z. officinale
charcoal and the content prediction, which can provide a reference for the quality control of
Z. officinale
charcoal decoction pieces and the judgment of the processing degree.
姜炭机器视觉机器学习质量评价炮制程度
machine visionmachine learningquality evaluationprocessing degree
国家药典委员会.中华人民共和国药典:一部[S]. 2020年版.北京:中国医药科技出版社,2020:15.
LEEMANS V,DESTAIN M F. A real-time grading method of apples based on features extracted from defects[J]. J Food Eng,2004,61(1):83-89.
段峰,王耀南,雷晓峰,等. 机器视觉技术及其应用综述[J]. 自动化博览,2002,(3):59-61.
田恬. 英国皇家学会发布新的调研项目:机器学习[J]. 科技导报,2016,34(3):93.
解达帅,刘玉杰,杨诗龙,等. 基于“内外结合”分析马钱子的炮制火候[J]. 中国实验方剂学杂志,2016,22(8):1-5.
张银萍,徐燕,朱双杰,等. 基于机器视觉的金丝皇菊智能分级系统研究[J]. 食品工业科技,2022,43(5):13-20.
陶兴宝,卢一,解达帅,等. 基于机器视觉及电子鼻技术的藤椒产地区分研究[J]. 中国调味品,2016,41(4):122-125.
郭超,焦淑珍,徐超,等. 基于机器视觉技术的苦豆子颗粒外观质量评价研究[J]. 中国兽药杂志,2021,55(4):27-38.
蒋苏贞,宓穗卿,王宁生. 姜酚心血管药理作用研究进展[J]. 时珍国医国药,2007,18(1):219-221.
吴英智,傅强,严全能,等.姜酚在心血管疾病中的药理作用研究进展[J].中国临床药理学杂志,2017,33(18):1824-1827.
陈琛,耿剑亮,匡海学,等. UHPLC-Oribtrap/HRMS技术分析干姜中非挥发性化学成分在炮制前后的变化[J]. 南京中医药大学学报,2020,36(3):387-395.
李田叶,刘卫华,梁娜,等.评估生姜及其不同炮制品中姜辣素和其抗氧化活性[J].食品工业,2016,37(12):180-183.
孟江,许舒娅,陈磊,等. 干姜“炒炭存性”质量标准初探[J]. 中国中药杂志,2012,37(4):453-456.
牛秋月,李晓蓓,王晓鹏. 基于Lab颜色模型的聚类舌图像分割[J]. 电脑编程技巧与维护,2021,(1):142-144.
徐曼菲,吴志生,刘晓娜,等. 从辨色论质谈中药质量评价方法[J]. 中国中药杂志,2016,41(2):177-181.
FAN W X, XU Q, WANG L, et al. Prediction of chemical component contents of the fruit of Xanthium strumarium L. during processing based on a computer vision system combined with a support vector machine[J]. Anal Methods, 2019,11(25):3260-3268.
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution