基于近红外高光谱成像技术的鸡蛋污染过程中菌落总数可视化研究
|
摘要
[目的]为探讨鸡蛋污染过程中微生物总量无损预测的可行性,本文研究了一种基于近红外高光谱成像技术可视化鸡蛋中菌落总数的无损预测方法。[方法]将鸡蛋样本在接种大肠杆菌和铜绿假单胞菌的混合菌悬液后储存,采集并统计不同污染程度鸡蛋样本的原始高光谱信息和菌落总数信息;在完成最佳预处理方法筛选后,结合连续投影算法(SPA)分别建立了基于全波段和特征波段光谱信息下的偏最小二乘法(PLS)和支持向量机(SVM)菌落总数预测模型;优选出相对最佳预测模型后进一步实现对鸡蛋内部污染程度的可视化研究。[结果]二阶导数预处理效果相对最佳,其中交叉验证集相关系数R_(CV)为0.88,交叉验证集均方根误差为0.82 lg(CFU·g~(-1));鸡蛋中菌落总数的相对最佳预测模型为基于特征波段下SVM模型,其中建模集相关系数R_C为0.88,预测集相关系数R_P为0.84,建模集和预测集均方根误差分别为0.86和0.97 lg(CFU·g~(-1));根据鸡蛋内部污染程度及光谱特性的差异,建立了鸡蛋内部污染程度伪彩色图像。[结论]近红外高光谱成像技术结合化学计量学及图像处理方法,可实现对鸡蛋内部菌落总数的无损预测及污染程度的可视化,该技术可以为鸡蛋的安全性在线检测提供参考。
[Objectives]To discuss the possibility of the non-destructive prediction of the total viable count of bacteria in the polluted eggs,this paper explored a non-destructive method that using near infrared hyperspectral imaging to predict and visualize the total viable count of bacteria in eggs. [Methods]Egg samples were inoculated with the mixture solution of Escherichia coli and Pseudomonas aeruginosa,then the original hyperspectral information and the total viable count of bacteria of eggs in different pollution levels during storage were collected. After selecting the best pretreatment method in this experiment,the predicting model by partial least squares(PLS)and support vector machine(SVM)model were developed based on full wavelengths and the feature wavelengths via the successive projections algorithm(SPA). Finally,the relative best prediction model of the viable count of bacteria was selected and the visualization study of the bacteria was realized in eggs. [Results]The second derivative method was the relative best pretreatment method,the correlation index of cross validation(R_(CV))was 0.88,and the root mean square error of cross validation was 0.82 lg(CFU·g~(-1)). The relative best prediction model was the SVM model which was based on the feature wavelengths,the correlation index of calibration(R_C)and prediction(R_P)was 0.88 and 0.84,and the root mean square error of calibration and prediction was 0.86 and 0.97 lg(CFU·g~(-1)),respectively. The visualized images of the polluted levels in eggs were built based on the difference of the pollution levels and spectral characteristics. [Conclusions]The near infrared hyperspectral imaging technology,and multivariate statistical and image processing methods can realize the prediction and visualization of the total viable count of bacteria in eggs,and this technology can also provide the foundation for on-line detection of the egg security.
[Objectives]To discuss the possibility of the non-destructive prediction of the total viable count of bacteria in the polluted eggs,this paper explored a non-destructive method that using near infrared hyperspectral imaging to predict and visualize the total viable count of bacteria in eggs. [Methods]Egg samples were inoculated with the mixture solution of Escherichia coli and Pseudomonas aeruginosa,then the original hyperspectral information and the total viable count of bacteria of eggs in different pollution levels during storage were collected. After selecting the best pretreatment method in this experiment,the predicting model by partial least squares(PLS)and support vector machine(SVM)model were developed based on full wavelengths and the feature wavelengths via the successive projections algorithm(SPA). Finally,the relative best prediction model of the viable count of bacteria was selected and the visualization study of the bacteria was realized in eggs. [Results]The second derivative method was the relative best pretreatment method,the correlation index of cross validation(R_(CV))was 0.88,and the root mean square error of cross validation was 0.82 lg(CFU·g~(-1)). The relative best prediction model was the SVM model which was based on the feature wavelengths,the correlation index of calibration(R_C)and prediction(R_P)was 0.88 and 0.84,and the root mean square error of calibration and prediction was 0.86 and 0.97 lg(CFU·g~(-1)),respectively. The visualized images of the polluted levels in eggs were built based on the difference of the pollution levels and spectral characteristics. [Conclusions]The near infrared hyperspectral imaging technology,and multivariate statistical and image processing methods can realize the prediction and visualization of the total viable count of bacteria in eggs,and this technology can also provide the foundation for on-line detection of the egg security.
引文
[1] 潘磊庆.基于计算机视觉和声学技术融合检测鸡蛋品质的研究[D].南京:南京农业大学,2007.Pan L Q.Egg quality detection based on computer vision and acoustic technology[D].Nanjing:Nanjing Agricultural University,2007(in Chinese with English abstract).
[2] 宾冬梅,钟金凤.蛋壳及禽蛋中微生物的来源与腐败变质[J].上海畜牧兽医通讯,2006(3):45-47.Bin D M,Zhong J F.The source of bacteria and spoilage in egg shell and egg[J].Shanghai Journal of Animal Husbandry and Veterinary Medicine,2006(3):45-47(in Chinese).
[3] Gu X Z,Sun Y,Tu K,et al.Predicting the growth situation of Pseudomonas aeruginosa on agar plates and meat stuffs using gas sensors[J].Scientific Reports,2016,6:38721.
[4] 魏超,代晓航,郭灵安,等.禽肉中铜绿假单胞菌的分离及其耐药性[J].肉类研究,2017,31(7):7-10.Wei C,Dai X H,Guo L A,et al.Isolation and drug resistance of Pseudomonas aeruginosa from poultry meat[J].Meat Research,2017,31(7):7-10(in Chinese with English abstract).
[5] 中华人民共和国卫生部.食品微生物学检验——菌落总数测定:GB 4789.2—2010[S].北京:中国标准出版社,2010.The Ministry of Health of the People’s Republic of China.Food microbiological examination-Aerobic plate count:GB 4789.2-2010[S].Beijing:China Standards Press,2010(in Chinese).
[6] 李殿鑫,戴远威,苏新国.食品中菌落总数测定的稀释度选择和计数结果的探讨[J].农产品加工,2016(9):39-40.Li D X,Dai Y W,Su X G.Discussion on the selection of dilution and counting results in the determination of total bacterial count in food[J].Farm Products Processing,2016(9):39-40(in Chinese with English abstract).
[7] 刘小丹,冯旭萍,刘飞,等.基于近红外高光谱成像技术鉴别杂交稻品系[J].农业工程学报,2017,33(22):189-194.Liu X D,Feng X P,Liu F,et al.Identification of hybrid rice strain based on near-infrared hyperspectral imaging technology[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(22):189-194(in Chinese with English abstract).
[8] 陈欣欣,郭辰彤,张初,等.高光谱成像技术的库尔勒梨早期损伤可视化检测研究[J].光谱学与光谱分析,2017,37(1):150-155.Chen X X,Guo C T,Zhang C,et al.Visual detection study on early bruises of Korla pear based on hyperspectral imaging technology[J].Spectroscopy and Spectral Analysis,2017,37(1):150-155(in Chinese with English abstract).
[9] He H J,Sun D W.Microbial evaluation of raw and processed food products by Visible/Infrared,Raman and Fluorescence spectroscope[J].Trends in Food Science & Technology,2015,46(2):199-210.
[10] He H J,Sun D W,Wu D.Rapid and real-time prediction of lactic acid bacteria(LAB)in farmed salmon flesh using near-infrared(NIR)hyperspectral imaging combined with chemometric analysis[J].Food Research International,2014,62:476-483.
[11] Feng Y Z,Elmasry G,Sun D W,et al.Near-infrared hyperspectral imaging and partial least squares regression for rapid and reagentless determination of Enterobacteriaceae on chicken fillets[J].Food Chemistry,2013,138(2/3):1829-1836.
[12] Barbin D F,Elmasry G,Sun D W,et al.Non-destructive assessment of microbial contamination in porcine meat using NIR hyperspectral imaging[J].Innovative Food Science and Emerging Technologies,2013,17:180-191.
[13] Tao F F,Peng Y K L,Gomes C,et al.A comparative study for improving prediction of total viable count in beef based on hyperspectral scattering characteristics[J].Journal of Food Engineering,2015,162:38-47.
[14] 丁佳兴,吴龙国,何建国,等.高光谱成像技术对灵武长枣果皮强度的无损检测[J].食品工业科技,2016,37(24):58-63.Ding J X,Wu L G,He J G,et al.Non-destructive determination of pericarp break force of Lingwu long jujube by hyperspectral imaging technology[J].Science and Technology of Food Industry,2016,37(24):58-63(in Chinese with English abstract).
[15] 岳学军,全东平,洪添胜,等.柑桔叶片叶绿素含量高光谱无损检测模型[J].农业工程学报,2015,31(1):294-302.Yue X J,Quan D P,Hong T S,et al.Non-destructive hyperspectral measurement model of chlorophyll content for citrus leaves[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(1):294-302(in Chinese with English abstract).
[16] 仝其根,唐巍巍,宋美娜.鲜鸡蛋中溶菌酶的活性分布[J].食品科学,2011,32(9):18-21.Tong Q G,Tang W W,Song M N.Distribution of lysozyme activity in fresh eggs[J].Food Science,2011,32(9):18-21(in Chinese with English abstract).
[17] Suktanarak S,Teerachaichayurt S.Non-destructive quality assessment of hens’ eggs using hyperspectral images[J].Journal of Food Engineering,2017,215:97-103.
[18] 范金波,王瑞环,周素珍,等.不同杀菌方法对蛋清物化性质的影响[J].食品工业科技,2014,35(11):143-151.Fan J B,Wang R H,Zhou S Z,et al.The effect of different sterilization methods on the physical and chemical properties of egg white liquid[J].Science and Technology of Food Industry,2014,35(11):143-151(in Chinese with English abstract).
[19] 何柳.禽蛋不同结构部分的抗菌特性研究[D].武汉:华中农业大学,2012:26-42.He L.Study on the anti-microbial properties of different structure in egg[J].Wuhan:Huazhong Agricultural University,2012:26-42(in Chinese with English abstract).
[20] Liu Q,Zhao N,Zhou D D,et al.Discrimination and growth tracking of fungi contamination in peaches using electronic nose[J].Food Chemistry,2018,262:226-234.
[21] Hao L,Zhao J W,Sun L,et al.Freshness measurement of eggs using near infrared(NIR)spectroscopy and multivariate data analysis[J].Innovative Food Science and Emerging Technologies,2011,12:182-186.
[22] Li J L,Zhu S S,Jiang S,et al.Predictive of egg storage time and yolk index based on electronic nose combined with chemometric methods[J].LWT-Food Science and Technology,2017,82:369-376.
[23] 郑丽敏,杨旭,徐桂云,等.基于计算机视觉的鸡蛋新鲜度无损检测[J].农业工程学报,2009,25(增刊2):335-339.Zheng L M,Yang X,Xu G Y,et al.Non destructive detection of egg freshness based on computer vision[J].Transactions of the Chinese Society of Agricultural Engineering,2009,25(Suppl 2):335-339(in Chinese with English abstract).
[24] Araujo M C U,Saldanha T C B,Galvao R K H,et al.The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J].Chemometrics and Intelligent Laboratory Systems,2001,57:65-73.
[25] Laura L V,Sandra E K,Philip E K.Near-infrared reflectance model for the rapid prediction of total fat in cereal foods[J].Journal of Agriculture and Food Chemistry,2005,53:1550-1555.
[2] 宾冬梅,钟金凤.蛋壳及禽蛋中微生物的来源与腐败变质[J].上海畜牧兽医通讯,2006(3):45-47.Bin D M,Zhong J F.The source of bacteria and spoilage in egg shell and egg[J].Shanghai Journal of Animal Husbandry and Veterinary Medicine,2006(3):45-47(in Chinese).
[3] Gu X Z,Sun Y,Tu K,et al.Predicting the growth situation of Pseudomonas aeruginosa on agar plates and meat stuffs using gas sensors[J].Scientific Reports,2016,6:38721.
[4] 魏超,代晓航,郭灵安,等.禽肉中铜绿假单胞菌的分离及其耐药性[J].肉类研究,2017,31(7):7-10.Wei C,Dai X H,Guo L A,et al.Isolation and drug resistance of Pseudomonas aeruginosa from poultry meat[J].Meat Research,2017,31(7):7-10(in Chinese with English abstract).
[5] 中华人民共和国卫生部.食品微生物学检验——菌落总数测定:GB 4789.2—2010[S].北京:中国标准出版社,2010.The Ministry of Health of the People’s Republic of China.Food microbiological examination-Aerobic plate count:GB 4789.2-2010[S].Beijing:China Standards Press,2010(in Chinese).
[6] 李殿鑫,戴远威,苏新国.食品中菌落总数测定的稀释度选择和计数结果的探讨[J].农产品加工,2016(9):39-40.Li D X,Dai Y W,Su X G.Discussion on the selection of dilution and counting results in the determination of total bacterial count in food[J].Farm Products Processing,2016(9):39-40(in Chinese with English abstract).
[7] 刘小丹,冯旭萍,刘飞,等.基于近红外高光谱成像技术鉴别杂交稻品系[J].农业工程学报,2017,33(22):189-194.Liu X D,Feng X P,Liu F,et al.Identification of hybrid rice strain based on near-infrared hyperspectral imaging technology[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(22):189-194(in Chinese with English abstract).
[8] 陈欣欣,郭辰彤,张初,等.高光谱成像技术的库尔勒梨早期损伤可视化检测研究[J].光谱学与光谱分析,2017,37(1):150-155.Chen X X,Guo C T,Zhang C,et al.Visual detection study on early bruises of Korla pear based on hyperspectral imaging technology[J].Spectroscopy and Spectral Analysis,2017,37(1):150-155(in Chinese with English abstract).
[9] He H J,Sun D W.Microbial evaluation of raw and processed food products by Visible/Infrared,Raman and Fluorescence spectroscope[J].Trends in Food Science & Technology,2015,46(2):199-210.
[10] He H J,Sun D W,Wu D.Rapid and real-time prediction of lactic acid bacteria(LAB)in farmed salmon flesh using near-infrared(NIR)hyperspectral imaging combined with chemometric analysis[J].Food Research International,2014,62:476-483.
[11] Feng Y Z,Elmasry G,Sun D W,et al.Near-infrared hyperspectral imaging and partial least squares regression for rapid and reagentless determination of Enterobacteriaceae on chicken fillets[J].Food Chemistry,2013,138(2/3):1829-1836.
[12] Barbin D F,Elmasry G,Sun D W,et al.Non-destructive assessment of microbial contamination in porcine meat using NIR hyperspectral imaging[J].Innovative Food Science and Emerging Technologies,2013,17:180-191.
[13] Tao F F,Peng Y K L,Gomes C,et al.A comparative study for improving prediction of total viable count in beef based on hyperspectral scattering characteristics[J].Journal of Food Engineering,2015,162:38-47.
[14] 丁佳兴,吴龙国,何建国,等.高光谱成像技术对灵武长枣果皮强度的无损检测[J].食品工业科技,2016,37(24):58-63.Ding J X,Wu L G,He J G,et al.Non-destructive determination of pericarp break force of Lingwu long jujube by hyperspectral imaging technology[J].Science and Technology of Food Industry,2016,37(24):58-63(in Chinese with English abstract).
[15] 岳学军,全东平,洪添胜,等.柑桔叶片叶绿素含量高光谱无损检测模型[J].农业工程学报,2015,31(1):294-302.Yue X J,Quan D P,Hong T S,et al.Non-destructive hyperspectral measurement model of chlorophyll content for citrus leaves[J].Transactions of the Chinese Society of Agricultural Engineering,2015,31(1):294-302(in Chinese with English abstract).
[16] 仝其根,唐巍巍,宋美娜.鲜鸡蛋中溶菌酶的活性分布[J].食品科学,2011,32(9):18-21.Tong Q G,Tang W W,Song M N.Distribution of lysozyme activity in fresh eggs[J].Food Science,2011,32(9):18-21(in Chinese with English abstract).
[17] Suktanarak S,Teerachaichayurt S.Non-destructive quality assessment of hens’ eggs using hyperspectral images[J].Journal of Food Engineering,2017,215:97-103.
[18] 范金波,王瑞环,周素珍,等.不同杀菌方法对蛋清物化性质的影响[J].食品工业科技,2014,35(11):143-151.Fan J B,Wang R H,Zhou S Z,et al.The effect of different sterilization methods on the physical and chemical properties of egg white liquid[J].Science and Technology of Food Industry,2014,35(11):143-151(in Chinese with English abstract).
[19] 何柳.禽蛋不同结构部分的抗菌特性研究[D].武汉:华中农业大学,2012:26-42.He L.Study on the anti-microbial properties of different structure in egg[J].Wuhan:Huazhong Agricultural University,2012:26-42(in Chinese with English abstract).
[20] Liu Q,Zhao N,Zhou D D,et al.Discrimination and growth tracking of fungi contamination in peaches using electronic nose[J].Food Chemistry,2018,262:226-234.
[21] Hao L,Zhao J W,Sun L,et al.Freshness measurement of eggs using near infrared(NIR)spectroscopy and multivariate data analysis[J].Innovative Food Science and Emerging Technologies,2011,12:182-186.
[22] Li J L,Zhu S S,Jiang S,et al.Predictive of egg storage time and yolk index based on electronic nose combined with chemometric methods[J].LWT-Food Science and Technology,2017,82:369-376.
[23] 郑丽敏,杨旭,徐桂云,等.基于计算机视觉的鸡蛋新鲜度无损检测[J].农业工程学报,2009,25(增刊2):335-339.Zheng L M,Yang X,Xu G Y,et al.Non destructive detection of egg freshness based on computer vision[J].Transactions of the Chinese Society of Agricultural Engineering,2009,25(Suppl 2):335-339(in Chinese with English abstract).
[24] Araujo M C U,Saldanha T C B,Galvao R K H,et al.The successive projections algorithm for variable selection in spectroscopic multicomponent analysis[J].Chemometrics and Intelligent Laboratory Systems,2001,57:65-73.
[25] Laura L V,Sandra E K,Philip E K.Near-infrared reflectance model for the rapid prediction of total fat in cereal foods[J].Journal of Agriculture and Food Chemistry,2005,53:1550-1555.
© 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 |