基于高光谱成像技术的工夫红茶数字化拼配
|
摘要
以祁门红茶5级6孔正子口、5级8孔正子口、6级6孔正子口和6级8孔正子口4种原料拼配成工夫红茶,应用高光谱图像系统获取拼配后茶样的光谱和图像信息。采用连续投影算法筛选光谱特征值;通过对图像做主成分分析,提取5个特征波长,采用灰度共生矩阵法提取5个特征波长下的图像纹理特征值。分别以光谱特征值、纹理特征值以及融合特征值作为模型输入值,结合偏最小二乘、最小二乘支持向量机(least squares-support vectormachine,LS-SVM)和反向传播人工神经网络方法建立茶叶拼配配比定量预测模型,并对模型的结果做比较。结果表明,以光谱特征值与纹理特征值融合后的值为输入参数,结合LS-SVM方法建立的模型,配比预测正确率达到了94.5%,预测结果较好。研究结果为出口茶叶数字化拼配的可行性提供理论依据。
Both?spatial?and?spectral?information?of?Congou?black?tea?blends?from?superior?fifth-grade?and?sixth-grade?raw?Keemun black tea leaves winnowed through 6 and 8 pores per inch were acquired by hyperspectral imaging technology.Spectral features were selected by successive projections algorithm(SPA), and all the obtained hyperspectral images were analyzed by principal component analysis(PCA). According to the weight coefficient, five dominant wavelengths were extracted?for?the?collection?of?textual?features?by?gray?level?co-occurrence?matrix(GLCM).?Subsequently,?partial?least?squares(PLS),?least?squares-support?vector?machine(LS-SVM)?and?back?propagation-artificial?neural?network(BP-ANN)?classification?models?for?prediction?of?the?optimal?blend?ratio?of?raw?tea?leaves?were?developed?based?on?the?spectral?features,?textural features and data fusion, respectively and they were comparatively evaluated. It was indicated that the discrimination accuracy?of?the?LS-SVM?model?based?on?data?infusion?was?up?to?94.5%.?Our?results?may?provide?a?theoretical?basis?for?the?digitization and standardized production of tea blends.
Both?spatial?and?spectral?information?of?Congou?black?tea?blends?from?superior?fifth-grade?and?sixth-grade?raw?Keemun black tea leaves winnowed through 6 and 8 pores per inch were acquired by hyperspectral imaging technology.Spectral features were selected by successive projections algorithm(SPA), and all the obtained hyperspectral images were analyzed by principal component analysis(PCA). According to the weight coefficient, five dominant wavelengths were extracted?for?the?collection?of?textual?features?by?gray?level?co-occurrence?matrix(GLCM).?Subsequently,?partial?least?squares(PLS),?least?squares-support?vector?machine(LS-SVM)?and?back?propagation-artificial?neural?network(BP-ANN)?classification?models?for?prediction?of?the?optimal?blend?ratio?of?raw?tea?leaves?were?developed?based?on?the?spectral?features,?textural features and data fusion, respectively and they were comparatively evaluated. It was indicated that the discrimination accuracy?of?the?LS-SVM?model?based?on?data?infusion?was?up?to?94.5%.?Our?results?may?provide?a?theoretical?basis?for?the?digitization and standardized production of tea blends.
引文
[1]韩余,肖宏儒,秦广明,等.红茶加工工艺及机械设备研究进展[J].中国农机化学报,2013 34(2):20-25.DOI:10.3969/j.issn.2095-5553.2013.02.006.
[2]DJOKAM M,SANDASI M,CHEN W,et al.Hyperspectral imaging as a rapid quality control method for herbal tea blends[J].Applied Sciences,2017,7(3):268.DOI:10.3390/app7030268.
[3]杨选民,惠康杰,黄凤琴.浅谈绿茶拼配技术[J].茶叶学报,2012(1):18-21.DOI:10.3969/j.issn.1007-4872.2012.01.008.
[4]吴步畅.无性系良种径山茶品质特征暨多品种拼配研究[J].茶叶,2014,40(4):187-193.DOI:10.3969/j.issn.0577-8921.2014.04.001.
[5]童华荣,龚正礼.茶叶拼配的混料设计研究[J].茶叶科学,2004,24(3):207-211.DOI:10.3969/j.issn.1000-369X.2004.03.011.
[6]VERMAAK I,VILJOEN A,LINDSTROM S W.Hyperspectral imaging in the quality control of herbal medicines-the case of neurotoxic Japanese star anise[J].Journal of Pharmaceutical&Biomedical Analysis,2013,75:207-213.DOI:10.1016/j.jpba.2012.11.039.
[7]SANDASI M,VERMAAK I,CHEN W,et al.Hyperspectral imaging and chemometric modeling of echinacea:a novel approach in the quality control of herbal medicines[J].Molecules,2014,19(9):13104.DOI:10.3390/molecules190913104.
[8]KELMAN T,REN J,MARSHALL S.Effective classification of Chinese tea samples in hyperspectral imaging[J].Artificial Intelligence Research,2013,2(4):87-92.DOI:10.5430/air.v2n4p87.
[9]余克强,赵艳茹,李晓丽,等.高光谱成像技术的不同叶位尖椒叶片氮素分布可视化研究[J].光谱学与光谱分析,2015(3):746-750.DOI:10.3964/j.issn.1000-0593(2015)03-0746-05.
[10]梁琨,杜莹莹,卢伟,等.基于高光谱成像技术的小麦籽粒赤霉病识别[J].农业机械学报,2016,47(2):309-315.DOI:10.6041/j.issn.1000-1298.2016.02.041.
[11]孙俊,武小红,张晓东,等.基于高光谱图像的生菜叶片水分预测研究[J].光谱学与光谱分析,2013,33(2):522-526.DOI:10.3964/j.is sn.1000-0593(2013)02-0522-05.
[12]胡鹏程,孙晔,吴海伦,等.高光谱图像对白萝卜糠心的无损检测[J].食品科学,2015,36(12):171-176.DOI:10.7506/spkx1002-6630-201512032.
[13]刘红玉,毛罕平,朱文静,等.基于高光谱的番茄氮磷钾营养水平快速诊断[J].农业工程学报,2015(增刊l):212-220.DOI:10.3969/j.issn.1002-6819.2015.z1.025.
[14]蔡健荣,韩智义.碧螺春茶叶的真伪鉴别技术:基于漫反射式高光谱成像技术[J].农机化研究,2013,35(4):140-143.DOI:10.3969/j.issn.1003-188X.2013.04.033.
[15]艾施荣,吴瑞梅,吴彦红,等.利用高光谱图像技术鉴别庐山云雾茶产地[J].江西农业大学学报,2014(2):428-433.DOI:10.13836/j.jjau.2014070.
[16]于英杰,王琼琼,王冰玉,等.基于高光谱技术的铁观音茶叶等级判别[J].食品科学,2014,35(22):159-163.DOI:10.7506/spkx1002-6630-201422030.
[17]赵杰文,王开亮,欧阳琴,等.高光谱技术分析茶树叶片中叶绿素含量及分布[J].光谱学与光谱分析,2011,31(2):512-515.DOI:10.3964/j.issn.1000-0593(2011)02-0512-04.
[18]王晓庆,冉烈,彭萍,等.炭疽病胁迫下的茶树叶片高光谱特征分析[J].植物保护,2014,40(6):13-17.DOI:10.3969/j.issn.0529-1542.2014.06.003.
[19]熊俊飞.茶叶中农药残留的光谱快速检测研究[D].南昌:江西农业大学,2016.
[20]李浬.基于高光谱图像纹理分析的龙井茶含水率预测的研究[D].杭州:浙江大学,2014.
[21]丁俊之.茶叶拼配加工与品牌营销的新思路[J].广东茶业,2010(5):9-11.DOI:10.3969/j.issn.1672-7398.2010.05.002.
[22]陈晓东,郭培源.基于主成分分析法提取高光谱图像特征检测香肠亚硝酸盐含量[J].肉类研究,2016,30(12):22-27.DOI:10.15922/j.cnki.rlyj.2016.12.005.
[23]吴龙国,王松磊,康宁波,等.基于高光谱成像技术的灵武长枣缺陷识别[J].农业工程学报,2015,31(20):281-286.DOI:10.11975/j.issn.1002-6819.2015.20.039.
[24]孙俊,蒋淑英,毛罕平,等.基于线性判别法的生菜农药残留定性检测模型研究[J].农业机械学报,2016,47(1):234-239.DOI:10.6041/j.issn.1000-1298.2016.01.031.
[25]薛建新,张淑娟,张晶晶.基于高光谱成像技术的沙金杏成熟度判别[J].农业工程学报,2015,31(11):300-307.DOI:10.11975/j.issn.1002-6819.2015.11.043.
[26]王昊鹏,李慧.基于局部二值模式和灰度共生矩阵的籽棉杂质分类识别[J].农业工程学报,2015,31(3):236-241.DOI:10.3969/j.issn.1002-6819.2015.03.031.
[27]王怀宇,李景丽.基于纹理特征的玉米苗期田间杂草识别[J].江苏农业科学,2014,42(7):143-145.DOI:10.3969/j.issn.1002-1302.2014.07.048.
[28]陆治荣.探索性数据分析及其在流程业的应用[M].北京:中国石化出版社,2013.
[29]张筱蕾,刘飞,聂鹏程,等.高光谱成像技术的油菜叶片氮含量及分布快速检测[J].光谱学与光谱分析,2014(9):2513-2518.DOI:10.3964/j.issn.1000-0593(2014)09-2513-06.
[30]宁井铭,孙京京,朱小元,等.基于图像和光谱信息融合的红茶萎凋程度量化判别[J].农业工程学报,2016,32(24):303-308.DOI:10.11975/j.issn.1002-6819.2016.24.041.
[31]HUANG L,ZHAO J W,CHEN Q S,et al.Rapid detection of total viable count(TVC)in pork meat by hyperspectral imaging[J].Food Research International,2013,54:821-828.DOI:10.1016/j.foodres.2013.08.011.
[2]DJOKAM M,SANDASI M,CHEN W,et al.Hyperspectral imaging as a rapid quality control method for herbal tea blends[J].Applied Sciences,2017,7(3):268.DOI:10.3390/app7030268.
[3]杨选民,惠康杰,黄凤琴.浅谈绿茶拼配技术[J].茶叶学报,2012(1):18-21.DOI:10.3969/j.issn.1007-4872.2012.01.008.
[4]吴步畅.无性系良种径山茶品质特征暨多品种拼配研究[J].茶叶,2014,40(4):187-193.DOI:10.3969/j.issn.0577-8921.2014.04.001.
[5]童华荣,龚正礼.茶叶拼配的混料设计研究[J].茶叶科学,2004,24(3):207-211.DOI:10.3969/j.issn.1000-369X.2004.03.011.
[6]VERMAAK I,VILJOEN A,LINDSTROM S W.Hyperspectral imaging in the quality control of herbal medicines-the case of neurotoxic Japanese star anise[J].Journal of Pharmaceutical&Biomedical Analysis,2013,75:207-213.DOI:10.1016/j.jpba.2012.11.039.
[7]SANDASI M,VERMAAK I,CHEN W,et al.Hyperspectral imaging and chemometric modeling of echinacea:a novel approach in the quality control of herbal medicines[J].Molecules,2014,19(9):13104.DOI:10.3390/molecules190913104.
[8]KELMAN T,REN J,MARSHALL S.Effective classification of Chinese tea samples in hyperspectral imaging[J].Artificial Intelligence Research,2013,2(4):87-92.DOI:10.5430/air.v2n4p87.
[9]余克强,赵艳茹,李晓丽,等.高光谱成像技术的不同叶位尖椒叶片氮素分布可视化研究[J].光谱学与光谱分析,2015(3):746-750.DOI:10.3964/j.issn.1000-0593(2015)03-0746-05.
[10]梁琨,杜莹莹,卢伟,等.基于高光谱成像技术的小麦籽粒赤霉病识别[J].农业机械学报,2016,47(2):309-315.DOI:10.6041/j.issn.1000-1298.2016.02.041.
[11]孙俊,武小红,张晓东,等.基于高光谱图像的生菜叶片水分预测研究[J].光谱学与光谱分析,2013,33(2):522-526.DOI:10.3964/j.is sn.1000-0593(2013)02-0522-05.
[12]胡鹏程,孙晔,吴海伦,等.高光谱图像对白萝卜糠心的无损检测[J].食品科学,2015,36(12):171-176.DOI:10.7506/spkx1002-6630-201512032.
[13]刘红玉,毛罕平,朱文静,等.基于高光谱的番茄氮磷钾营养水平快速诊断[J].农业工程学报,2015(增刊l):212-220.DOI:10.3969/j.issn.1002-6819.2015.z1.025.
[14]蔡健荣,韩智义.碧螺春茶叶的真伪鉴别技术:基于漫反射式高光谱成像技术[J].农机化研究,2013,35(4):140-143.DOI:10.3969/j.issn.1003-188X.2013.04.033.
[15]艾施荣,吴瑞梅,吴彦红,等.利用高光谱图像技术鉴别庐山云雾茶产地[J].江西农业大学学报,2014(2):428-433.DOI:10.13836/j.jjau.2014070.
[16]于英杰,王琼琼,王冰玉,等.基于高光谱技术的铁观音茶叶等级判别[J].食品科学,2014,35(22):159-163.DOI:10.7506/spkx1002-6630-201422030.
[17]赵杰文,王开亮,欧阳琴,等.高光谱技术分析茶树叶片中叶绿素含量及分布[J].光谱学与光谱分析,2011,31(2):512-515.DOI:10.3964/j.issn.1000-0593(2011)02-0512-04.
[18]王晓庆,冉烈,彭萍,等.炭疽病胁迫下的茶树叶片高光谱特征分析[J].植物保护,2014,40(6):13-17.DOI:10.3969/j.issn.0529-1542.2014.06.003.
[19]熊俊飞.茶叶中农药残留的光谱快速检测研究[D].南昌:江西农业大学,2016.
[20]李浬.基于高光谱图像纹理分析的龙井茶含水率预测的研究[D].杭州:浙江大学,2014.
[21]丁俊之.茶叶拼配加工与品牌营销的新思路[J].广东茶业,2010(5):9-11.DOI:10.3969/j.issn.1672-7398.2010.05.002.
[22]陈晓东,郭培源.基于主成分分析法提取高光谱图像特征检测香肠亚硝酸盐含量[J].肉类研究,2016,30(12):22-27.DOI:10.15922/j.cnki.rlyj.2016.12.005.
[23]吴龙国,王松磊,康宁波,等.基于高光谱成像技术的灵武长枣缺陷识别[J].农业工程学报,2015,31(20):281-286.DOI:10.11975/j.issn.1002-6819.2015.20.039.
[24]孙俊,蒋淑英,毛罕平,等.基于线性判别法的生菜农药残留定性检测模型研究[J].农业机械学报,2016,47(1):234-239.DOI:10.6041/j.issn.1000-1298.2016.01.031.
[25]薛建新,张淑娟,张晶晶.基于高光谱成像技术的沙金杏成熟度判别[J].农业工程学报,2015,31(11):300-307.DOI:10.11975/j.issn.1002-6819.2015.11.043.
[26]王昊鹏,李慧.基于局部二值模式和灰度共生矩阵的籽棉杂质分类识别[J].农业工程学报,2015,31(3):236-241.DOI:10.3969/j.issn.1002-6819.2015.03.031.
[27]王怀宇,李景丽.基于纹理特征的玉米苗期田间杂草识别[J].江苏农业科学,2014,42(7):143-145.DOI:10.3969/j.issn.1002-1302.2014.07.048.
[28]陆治荣.探索性数据分析及其在流程业的应用[M].北京:中国石化出版社,2013.
[29]张筱蕾,刘飞,聂鹏程,等.高光谱成像技术的油菜叶片氮含量及分布快速检测[J].光谱学与光谱分析,2014(9):2513-2518.DOI:10.3964/j.issn.1000-0593(2014)09-2513-06.
[30]宁井铭,孙京京,朱小元,等.基于图像和光谱信息融合的红茶萎凋程度量化判别[J].农业工程学报,2016,32(24):303-308.DOI:10.11975/j.issn.1002-6819.2016.24.041.
[31]HUANG L,ZHAO J W,CHEN Q S,et al.Rapid detection of total viable count(TVC)in pork meat by hyperspectral imaging[J].Food Research International,2013,54:821-828.DOI:10.1016/j.foodres.2013.08.011.