基于机器视觉的武夷岩茶做青程度识别研究
|
摘要
[目的]尝试利用机器视觉技术分析武夷岩茶做青过程中萎凋叶的颜色变化情况和做青程度之间的关系。[方法]试验通过图像采集系统获得做青过程的茶叶彩色图像,采用RGB和HSI这2种颜色参数模型观察图像颜色变化,结合自组织竞争人工神经网络技术对不同程度的做青叶进行分类。[结果]140个样本以RGB分量值和HSI分量值表示的训练集和测试集分类的正确率分别为81.64%、78.6%和76.5%、73.8%,显著性检验概率P<0.05,决定系数R~2最小为0.879,颜色分量和做青程度高度相关。[结论]试验构建的自组织竞争人工神经网络模型可以作为武夷岩茶做青程度的预测模型,也可为今后利用机器视觉来监测乌龙茶做青过程提供参考。
[Objective] The objective of this study was to analyze the correlation between the color change of tea leaves after sun withered and the degree of green processing using machinery vision technology. [Methods] Color images were captured by an image acquisition system in green processing phase, and the color change of tea leaves was monitored by RGB and HSI models combined with self-organized artificial neural network technology to classify different degrees of leave green processing. [Results] The classification accuracy rates of training set and testing set of 140 samples expressed by RGB component and HSI component were 81.64%,78.6% and 76.5%,73.8%, respectively. The probability(P)of significance testwas less than 0.05, and the coefficient of determination R~2 was equal or greater than 0.879. The color component was highly correlated to the degree of green processing.[Conclusion] The self-organized artificial neural competition network model can be used to predict the degree of Wuyi Rock Tea green processing,and to provide a reference for monitoring the process of Oolong tea green processing by machinery vision in the future.
[Objective] The objective of this study was to analyze the correlation between the color change of tea leaves after sun withered and the degree of green processing using machinery vision technology. [Methods] Color images were captured by an image acquisition system in green processing phase, and the color change of tea leaves was monitored by RGB and HSI models combined with self-organized artificial neural network technology to classify different degrees of leave green processing. [Results] The classification accuracy rates of training set and testing set of 140 samples expressed by RGB component and HSI component were 81.64%,78.6% and 76.5%,73.8%, respectively. The probability(P)of significance testwas less than 0.05, and the coefficient of determination R~2 was equal or greater than 0.879. The color component was highly correlated to the degree of green processing.[Conclusion] The self-organized artificial neural competition network model can be used to predict the degree of Wuyi Rock Tea green processing,and to provide a reference for monitoring the process of Oolong tea green processing by machinery vision in the future.
引文
[1]刘宝顺,占仕权,刘欣,等. 武夷岩茶制茶环境与品质[J]. 农产品加工,2016(21): 54-56.
[2]刘宝顺,戈佩贞,陈德华,等. 漫话武夷岩茶——兼论岩茶优质机理[J]. 福建茶叶,2014,36(6): 5-8.
[3]郝志龙,林宏政,金心怡,等. 乌龙茶振动做青气流和摊叶厚度对青叶做青物理特性的影响 [J]. 福建农林大学学报(自然科学版),2017,46(2):147-153.
[4]江和金. 武夷岩茶制作工艺[J]. 现代农业科技,2012(3): 337-338,340.
[5]刘宝顺,潘玉华. 武夷岩茶烘焙技术[J]. 福建茶叶,2014(1):29-31.
[6]黄意生. 武夷岩茶现代做青技术研究[J]. 福建茶叶,2015,37(1):11-14.
[7]俞露婷,袁海波,王伟伟,等. 光照强度对发酵叶主要生化成分动态变化的影响[J]. 茶叶科学,2016,36(2):149-159.
[8]刘晓东,刘玉芳,甘春萍,等. 工夫红茶发酵过程中发酵叶茶汤吸光值变化的研究[J]. 茶叶科学,2011(4):300-304.
[9]Gill G S, Kumar A, Agarwal R. Monitoring and grading of tea by computer vision-A review[J]. Journal of Food Engineering, 2011, 106(1): 13-19.
[10]Singh G, Kamal N. Machine vision system for tea quality determination-Tea Quality Index (TQI)[J]. IOSR Journal of Engineering, 2013, 3(7): 46-50.
[11]Laddi A, Sharma S, Kumar A, et al. Classification of tea grains based upon image texture feature analysis under different illumination conditions[J]. Journal of Food Engineering, 2013, 115(2): 226-231.
[12]Wang S, Phillips P, Liu A, et al. Tea category identification using computer vision and generalized eigenvalue proximal svm[J]. Fundamenta Informaticae, 2017, 151(1-4): 325-339.
[13]Tang Z, Su Y, Er M J, et al. A local binary pattern based texture descriptors for classification of tea leaves[J]. Neurocomputing, 2015, 168: 1011-1023.
[14]Zhu H, Ye Y, He H, et al. Evaluation of green tea sensory quality via process characteristics and image information[J]. Food and Bioproducts Processing, 2017, 102: 116-122.
[15]Wang S, Yang X, Zhang Y, et al. Identification of green, oolong and black teas in China via wavelet packet entropy and fuzzy support vector machine[J]. Entropy, 2015, 17(10): 6663-6682.
[16]Leon K,Mery D,Pedreschi F,et al. Color measurement in L/a/b units from RGB digital image[J]. Food Research International, 2006,39(10):1084-1091.
[17]Garrido N C.,Pérez-Marin D,Amigo J M,et al. Grading and color evolution of apples using rgb and hyperspectral imaging vision cameras[J]. Journal of Food Engineering,2012,113(2): 281-288.
[18]Ulrici A, Foca G, Ielo M C, et al. Automated identification and visualization of food defects using RGB imaging: Application to the detection of red skin defect of raw hams[J]. Innovative Food Science and Emerging Technologies, 2012, 16: 417-426.
[19]Aghbashlo,M,Mobli H,Ra?ee S,et al. The use of arti?cial neural network to predict exergetic performance of spray drying process: a preliminary study[J]. Computers and Electronics in Agriculture,2012,88(10): 32-43.
[20]Peng Xu,Shijin Xu,Hongwei Yin. Application of self-organizing competitive neural network in fault diagnosis of suck rod pumping system[J]. Journal of Petroleum Science and Engineering,2006,58(1-2):43-48.
[21]Zhang J, Feng X, Zhou B, et al. An overall-regional competitive self-organizing map neural network for the Euclidean traveling salesman problem[J]. Neurocomputing, 2012, 89(8): 1-11.
[2]刘宝顺,戈佩贞,陈德华,等. 漫话武夷岩茶——兼论岩茶优质机理[J]. 福建茶叶,2014,36(6): 5-8.
[3]郝志龙,林宏政,金心怡,等. 乌龙茶振动做青气流和摊叶厚度对青叶做青物理特性的影响 [J]. 福建农林大学学报(自然科学版),2017,46(2):147-153.
[4]江和金. 武夷岩茶制作工艺[J]. 现代农业科技,2012(3): 337-338,340.
[5]刘宝顺,潘玉华. 武夷岩茶烘焙技术[J]. 福建茶叶,2014(1):29-31.
[6]黄意生. 武夷岩茶现代做青技术研究[J]. 福建茶叶,2015,37(1):11-14.
[7]俞露婷,袁海波,王伟伟,等. 光照强度对发酵叶主要生化成分动态变化的影响[J]. 茶叶科学,2016,36(2):149-159.
[8]刘晓东,刘玉芳,甘春萍,等. 工夫红茶发酵过程中发酵叶茶汤吸光值变化的研究[J]. 茶叶科学,2011(4):300-304.
[9]Gill G S, Kumar A, Agarwal R. Monitoring and grading of tea by computer vision-A review[J]. Journal of Food Engineering, 2011, 106(1): 13-19.
[10]Singh G, Kamal N. Machine vision system for tea quality determination-Tea Quality Index (TQI)[J]. IOSR Journal of Engineering, 2013, 3(7): 46-50.
[11]Laddi A, Sharma S, Kumar A, et al. Classification of tea grains based upon image texture feature analysis under different illumination conditions[J]. Journal of Food Engineering, 2013, 115(2): 226-231.
[12]Wang S, Phillips P, Liu A, et al. Tea category identification using computer vision and generalized eigenvalue proximal svm[J]. Fundamenta Informaticae, 2017, 151(1-4): 325-339.
[13]Tang Z, Su Y, Er M J, et al. A local binary pattern based texture descriptors for classification of tea leaves[J]. Neurocomputing, 2015, 168: 1011-1023.
[14]Zhu H, Ye Y, He H, et al. Evaluation of green tea sensory quality via process characteristics and image information[J]. Food and Bioproducts Processing, 2017, 102: 116-122.
[15]Wang S, Yang X, Zhang Y, et al. Identification of green, oolong and black teas in China via wavelet packet entropy and fuzzy support vector machine[J]. Entropy, 2015, 17(10): 6663-6682.
[16]Leon K,Mery D,Pedreschi F,et al. Color measurement in L/a/b units from RGB digital image[J]. Food Research International, 2006,39(10):1084-1091.
[17]Garrido N C.,Pérez-Marin D,Amigo J M,et al. Grading and color evolution of apples using rgb and hyperspectral imaging vision cameras[J]. Journal of Food Engineering,2012,113(2): 281-288.
[18]Ulrici A, Foca G, Ielo M C, et al. Automated identification and visualization of food defects using RGB imaging: Application to the detection of red skin defect of raw hams[J]. Innovative Food Science and Emerging Technologies, 2012, 16: 417-426.
[19]Aghbashlo,M,Mobli H,Ra?ee S,et al. The use of arti?cial neural network to predict exergetic performance of spray drying process: a preliminary study[J]. Computers and Electronics in Agriculture,2012,88(10): 32-43.
[20]Peng Xu,Shijin Xu,Hongwei Yin. Application of self-organizing competitive neural network in fault diagnosis of suck rod pumping system[J]. Journal of Petroleum Science and Engineering,2006,58(1-2):43-48.
[21]Zhang J, Feng X, Zhou B, et al. An overall-regional competitive self-organizing map neural network for the Euclidean traveling salesman problem[J]. Neurocomputing, 2012, 89(8): 1-11.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |