单粒玉米种子成熟度快速判别方法
|
摘要
为快速无损检测单粒种子成熟度,推进现代良种单粒播种技术,采用近红外光谱技术结合化学计量学方法建立了单粒玉米种子成熟度快速鉴别模型。采集200份单粒玉米种子样本近红外光谱,采用多种光谱预处理方法消除单粒种子采集过程中由于颗粒形态、杂散光等引入的干扰信息,分别采用分段谱区、连续投影算法筛选特征波长,优化建立种子成熟度判别模型。经SG5_1预处理后,在5 500～4 000 cm~(-1)谱区建立的基于支持向量机的单粒玉米种子成熟度判别模型的分类准确率可达92%。实验结果表明,近红外光谱技术可以快速无损判别单粒玉米种子成熟度。
Seed maturity is an important factor affecting seed quality and crop yield. Therefore,rapid non-destructive testing of single seed maturity is an important basic technical guarantee for promoting modern single seed sowing technology for improved seeds. A rapid identification model of single corn seed maturity was established by combining near-infrared spectroscopy and chemometrics. The experiment collected the near infrared spectrum of 200 single corn seed samples. Interference information was reduced by particle morphology,stray light,etc. during single seed collection. The segmentation spectral region was used respectively,and the continuous projection algorithm was used to screen the feature wavelength optimization to establish a seed maturity determination model. The experiments showed that the recognition accuracy of the SVM based single corn seed maturity discrimination model established in the 5 500 ～ 4 000 cm~(-1) spectral region could reach 92% after the Savitzky-Golay 5-point convolution first derivative pretreatment. The results showed that NIR had a bright application prospect in the rapid and non-destructive discrimination of single corn seed maturity.
Seed maturity is an important factor affecting seed quality and crop yield. Therefore,rapid non-destructive testing of single seed maturity is an important basic technical guarantee for promoting modern single seed sowing technology for improved seeds. A rapid identification model of single corn seed maturity was established by combining near-infrared spectroscopy and chemometrics. The experiment collected the near infrared spectrum of 200 single corn seed samples. Interference information was reduced by particle morphology,stray light,etc. during single seed collection. The segmentation spectral region was used respectively,and the continuous projection algorithm was used to screen the feature wavelength optimization to establish a seed maturity determination model. The experiments showed that the recognition accuracy of the SVM based single corn seed maturity discrimination model established in the 5 500 ～ 4 000 cm~(-1) spectral region could reach 92% after the Savitzky-Golay 5-point convolution first derivative pretreatment. The results showed that NIR had a bright application prospect in the rapid and non-destructive discrimination of single corn seed maturity.
引文
[1]刘国梁,赵亚丽,王秀玲,等.玉米种子成熟度对其活力及F_1产量的影响[J].中国农业科学,2016,49(22):4342-4351.LIU Guoliang,ZHAO Yali,WANG Xiuling,et al.Effects of seed maturity on maize hybrid seed vigor and F_1 yield[J].Scientia Agricultura Sinica,2016,49(22):4342-4351.(in Chinese)
[2]陈龙江,MICHAEL R R.种子质量对中国玉米产出的影响[J].华南农业大学学报(社会科学版),2016,15(3):19-27.CHEN Longjiang,MICHAEI R R.The effect of seeds quality improvement on maize yield[J].Journal of South China Agricultural University(Social Science Edition),2016,15(3):19-27.(in Chinese)
[3]卢德成.中国玉米生产成本优化研究[D].北京:中国农业科学院,2018.LU Decheng.Research on optimization of maize production cost in China[D].Beijing:Chinese Academy of Agricultural Sciences,2018.(in Chinese)
[4]戴立新.玉米单粒播种高产技术推广优势和存在的问题[J].农业与技术,2017,37(18):55.DAI Lixin.The advantages and problems of high yield technology of single seed sowing in maize[J].Agriculture and Technology,2017,37(18):55.(in Chinese)
[5]KAWASAKI M,KAWAMURA S,TSUKAHARA M,et al.Near-infrared spectroscopic sensing system for on-line milk quality assessment in a milking robot[J].Computers and Electronics in Agriculture,2008,63(1):22-27.
[6]CHEN L,YANG Z,HAN L.A review on the use of near-infrared spectroscopy for analyzing feed protein materials[J].Applied Spectroscopy Reviews,2013,48(7):509-522.
[7]杨泉女,周权驹,蒙高山,等.近红外反射光谱技术测定甜玉米总多糖和淀粉含量的研究[J].吉林农业大学学报,2019,41(1):108-114.YANG Quannü,ZHOU Quanju,MENG Gaoshan,et al.Determination of total polysaccharide and starch content in sweet corn by NIRS[J].Journal of Jilin Agricultural University,2019,41(1):108-114.(in Chinese)
[8]卢德成.中美玉米种植成本比较与分析[J].农业展望,2018,14(3):37-42.LU Decheng.Comparison and analysis of maize planting cost between China and America[J].Agricultural Outlook,2018,14(3):37-42.(in Chinese)
[9]朱占侠.夏玉米单粒播种技术要点[J].种子科技,2018,36(7):44-45.ZHU Zhanxia.Technology of single seed sowing of summer maize[J].Seed Science&Technology,2018,36(7):44-45.(in Chinese)
[10]张鹏,李江阔,冯晓元,等.可见/近红外漫反射光谱预测磨盘柿成熟度[J].食品研究与开发,2013,34(11):91-94.ZHANG Peng,LI Jiangkuo,FENG Xiaoyuan,et al.Prediction of maturity of mopan persimmon using near infrared diffuse reflectance spectroscopy[J].Food Research and Development,2013,34(11):91-94.(in Chinese)
[11]孙静涛.基于光谱和图像信息融合的哈密瓜成熟度无损检测研究[D].石河子:石河子大学,2017.SUN Jingtao.Study on nondestructive dection of hami melon maturity based on information fusion of spectrum and image[D].Shihezi:Shihezi University,2017.(in Chinese)
[12]杨小玲,由昭红,成芳.高光谱成像技术检测玉米种子成熟度[J].光谱学与光谱分析,2016,36(12):4028-4033.YANG Xiaoling,YOU Zhaohong,CHENG Fang.Study on identification of immature corn seed using hyperspectral imaging[J].Spectroscopy and Spectral Analysis,2016,36(12):4028-4033.(in Chinese)
[13]曹晓峰,任惠如,李幸芝,等.高光谱技术结合特征波长/光谱指数对冬枣成熟度可视化判别[J].光谱学与光谱分析,2018,38(7):2175-2182.CAO Xiaofeng,REN Huiru,LI Xingzhi,et al.Discrimination of winter jujube's maturity using hyperspectral technique combined with characteristic wavelength and spectral indices[J].Spectroscopy and Spectral Analysis,2018,38(7):2175-2182.(in Chinese)
[14]GIORGIO M,LORENZO S,ELISABETTA G,et al.Near-infrared calibration transfer for undried whole maize plant between laboratory and on-site spectrometers[J].Italian Journal of Animal Science,2018,17(1):66-72.
[15]刘燕德,徐海,孙旭东,等.西红柿成熟度的近红外漫透射光谱无损检测[J].激光技术,2019,43(1):25-29.LIU Yande,XU Hai,SUN Xudong,et al.Non-destructive measurement of tomato maturity by near-infrared diffuse transmission spectroscopy[J].Laser Technology,2019,43(1):25-29.(in Chinese)
[16]蒋大鹏,张冬妍,李丹丹,等.基于近红外的松子蛋白质品质分类处理[J].计算技术与自动化,2018,37(3):180-184.JIANG Dapeng,ZHANG Dongyan,LI Dandan,et al.Classification of pine nut protein quality based on near infrared[J].Computing Technology and Automation,2018,37(3):180-184.(in Chinese)
[17]高云飞,付霖宇,瞿军,等.基于相似性度量的改进KS算法对近红外光谱分析模型的影响研究[J].电光与控制,2019,26(6):18-21.GAO Yunfei,FU Linyu,QU Jun,et al.Research on influence of improved KS algorithm based on similarity measure on nearinfrared spectroscopy analysis model[J].Electronics Optics&Control,2019,26(6):18-21.(in Chinese)
[18]章海亮,罗微,刘雪梅,等.应用遗传算法结合连续投影算法近红外光谱检测土壤有机质研究[J].光谱学与光谱分析,2017,37(2):584-587.ZHANG Hailiang,LUO Wei,LIU Xuemei,et al.Measurement of soil organic matter with near infrared spectroscopy combined with genetic algorithm and successive projection algorithm[J].Spectroscopy and Spectral Analysis,2017,37(2):584-587.(in Chinese)
[19]孙丽萍,张希萌,何睿,等.基于SVM的近红外黑木耳多糖含量分类[J].电子科技,2019(8):1-7.SUN Liping,ZHANG Ximeng,HE Rui,et al.Near-infrared scanning polysaccharide content classification of auricularia Auricular based on SVM[J].Electronic Science and Technology,2019(8):1-7.(in Chinese)
[20]TEYE E,AMUAH C L Y,MCGRATH T,et al.Innovative and rapid analysis for rice authenticity using handheld NIRspectrometry and chemometrics[J].Spectrochimica Acta.Part A,Molecular and Biomolecular Spectroscopy,2019,217(3):147-154.
[2]陈龙江,MICHAEL R R.种子质量对中国玉米产出的影响[J].华南农业大学学报(社会科学版),2016,15(3):19-27.CHEN Longjiang,MICHAEI R R.The effect of seeds quality improvement on maize yield[J].Journal of South China Agricultural University(Social Science Edition),2016,15(3):19-27.(in Chinese)
[3]卢德成.中国玉米生产成本优化研究[D].北京:中国农业科学院,2018.LU Decheng.Research on optimization of maize production cost in China[D].Beijing:Chinese Academy of Agricultural Sciences,2018.(in Chinese)
[4]戴立新.玉米单粒播种高产技术推广优势和存在的问题[J].农业与技术,2017,37(18):55.DAI Lixin.The advantages and problems of high yield technology of single seed sowing in maize[J].Agriculture and Technology,2017,37(18):55.(in Chinese)
[5]KAWASAKI M,KAWAMURA S,TSUKAHARA M,et al.Near-infrared spectroscopic sensing system for on-line milk quality assessment in a milking robot[J].Computers and Electronics in Agriculture,2008,63(1):22-27.
[6]CHEN L,YANG Z,HAN L.A review on the use of near-infrared spectroscopy for analyzing feed protein materials[J].Applied Spectroscopy Reviews,2013,48(7):509-522.
[7]杨泉女,周权驹,蒙高山,等.近红外反射光谱技术测定甜玉米总多糖和淀粉含量的研究[J].吉林农业大学学报,2019,41(1):108-114.YANG Quannü,ZHOU Quanju,MENG Gaoshan,et al.Determination of total polysaccharide and starch content in sweet corn by NIRS[J].Journal of Jilin Agricultural University,2019,41(1):108-114.(in Chinese)
[8]卢德成.中美玉米种植成本比较与分析[J].农业展望,2018,14(3):37-42.LU Decheng.Comparison and analysis of maize planting cost between China and America[J].Agricultural Outlook,2018,14(3):37-42.(in Chinese)
[9]朱占侠.夏玉米单粒播种技术要点[J].种子科技,2018,36(7):44-45.ZHU Zhanxia.Technology of single seed sowing of summer maize[J].Seed Science&Technology,2018,36(7):44-45.(in Chinese)
[10]张鹏,李江阔,冯晓元,等.可见/近红外漫反射光谱预测磨盘柿成熟度[J].食品研究与开发,2013,34(11):91-94.ZHANG Peng,LI Jiangkuo,FENG Xiaoyuan,et al.Prediction of maturity of mopan persimmon using near infrared diffuse reflectance spectroscopy[J].Food Research and Development,2013,34(11):91-94.(in Chinese)
[11]孙静涛.基于光谱和图像信息融合的哈密瓜成熟度无损检测研究[D].石河子:石河子大学,2017.SUN Jingtao.Study on nondestructive dection of hami melon maturity based on information fusion of spectrum and image[D].Shihezi:Shihezi University,2017.(in Chinese)
[12]杨小玲,由昭红,成芳.高光谱成像技术检测玉米种子成熟度[J].光谱学与光谱分析,2016,36(12):4028-4033.YANG Xiaoling,YOU Zhaohong,CHENG Fang.Study on identification of immature corn seed using hyperspectral imaging[J].Spectroscopy and Spectral Analysis,2016,36(12):4028-4033.(in Chinese)
[13]曹晓峰,任惠如,李幸芝,等.高光谱技术结合特征波长/光谱指数对冬枣成熟度可视化判别[J].光谱学与光谱分析,2018,38(7):2175-2182.CAO Xiaofeng,REN Huiru,LI Xingzhi,et al.Discrimination of winter jujube's maturity using hyperspectral technique combined with characteristic wavelength and spectral indices[J].Spectroscopy and Spectral Analysis,2018,38(7):2175-2182.(in Chinese)
[14]GIORGIO M,LORENZO S,ELISABETTA G,et al.Near-infrared calibration transfer for undried whole maize plant between laboratory and on-site spectrometers[J].Italian Journal of Animal Science,2018,17(1):66-72.
[15]刘燕德,徐海,孙旭东,等.西红柿成熟度的近红外漫透射光谱无损检测[J].激光技术,2019,43(1):25-29.LIU Yande,XU Hai,SUN Xudong,et al.Non-destructive measurement of tomato maturity by near-infrared diffuse transmission spectroscopy[J].Laser Technology,2019,43(1):25-29.(in Chinese)
[16]蒋大鹏,张冬妍,李丹丹,等.基于近红外的松子蛋白质品质分类处理[J].计算技术与自动化,2018,37(3):180-184.JIANG Dapeng,ZHANG Dongyan,LI Dandan,et al.Classification of pine nut protein quality based on near infrared[J].Computing Technology and Automation,2018,37(3):180-184.(in Chinese)
[17]高云飞,付霖宇,瞿军,等.基于相似性度量的改进KS算法对近红外光谱分析模型的影响研究[J].电光与控制,2019,26(6):18-21.GAO Yunfei,FU Linyu,QU Jun,et al.Research on influence of improved KS algorithm based on similarity measure on nearinfrared spectroscopy analysis model[J].Electronics Optics&Control,2019,26(6):18-21.(in Chinese)
[18]章海亮,罗微,刘雪梅,等.应用遗传算法结合连续投影算法近红外光谱检测土壤有机质研究[J].光谱学与光谱分析,2017,37(2):584-587.ZHANG Hailiang,LUO Wei,LIU Xuemei,et al.Measurement of soil organic matter with near infrared spectroscopy combined with genetic algorithm and successive projection algorithm[J].Spectroscopy and Spectral Analysis,2017,37(2):584-587.(in Chinese)
[19]孙丽萍,张希萌,何睿,等.基于SVM的近红外黑木耳多糖含量分类[J].电子科技,2019(8):1-7.SUN Liping,ZHANG Ximeng,HE Rui,et al.Near-infrared scanning polysaccharide content classification of auricularia Auricular based on SVM[J].Electronic Science and Technology,2019(8):1-7.(in Chinese)
[20]TEYE E,AMUAH C L Y,MCGRATH T,et al.Innovative and rapid analysis for rice authenticity using handheld NIRspectrometry and chemometrics[J].Spectrochimica Acta.Part A,Molecular and Biomolecular Spectroscopy,2019,217(3):147-154.