考虑直径影响的苹果霉心病透射光谱修正及检测
|
摘要
针对苹果霉心病近红外透射光谱信息受果实直径影响的难题,提出了一种能够修正果实直径对透射光谱影响的方法。基于透射光谱采集平台获取327个红富士苹果的可见/近红外光谱(350～1 100 nm)信息,采用电子游标卡尺获取其直径(光程)信息。以直径为80 mm健康苹果的平均光谱作为参考光谱,将327个苹果的光谱与参考光谱进行比较,结合直径信息利用公式求得透射光在果实内的衰减系数P,用衰减系数P进行透射光谱的修正。修正后光谱建立支持向量机(SVM)模型、误差反向传播神经网络(BP-ANN)模型,并与修正前原始光谱建立模型进行对比。实验结果表明,应用此光谱修正方法能够显著提高模型判别精度,其中应用SVM算法对修正后的光谱建立模型效果最好,对训练集和测试集的判别准确率分别为99. 34%和90. 20%,相对于原始光谱建立的模型判别准确率分别提高了7. 84和5. 89个百分点。基于此方法修正果实直径对于透射光谱的影响是可行的,构建的模型能够实现苹果霉心病的准确判别。
Currently,the near infrared transmission spectrum of moldy core in apples was seriously affected by the size of fruit. In order to solve the problem,a transmission spectrum correction method based on size of fruit was proposed. A spectrum acquisition platform was constructed to acquire the transmission spectra( 350 ～ 1 100 nm) of 327 Fuji apples and their diameters were measured with a vernier caliper. The spectrum of healthy apples with diameter of 80 mm was used as reference.Comparing the spectrum of 327 apples with the reference spectrum,a formula was built. The attenuation index of transmitted light in the fruit can be easily found by using the formula and diameters. Then the transmission spectrum was modified with the help of attenuation index. Error back propagation artificial neural networks( BP-ANN) and support vector machine( SVM) measurement model were established based on corrected spectrum and original spectrum. The results showed that the accuracy of the models based on corrected spectrum was much higher than those of the others,and its recognition accuracy rate reached 99. 34% for the training set and 90. 20% for the test set. The recognition rate of the model was7. 84 and 5. 89 percentage points higher than that of the original spectrum. The results showed that the effect of the size on transmission spectra can be corrected by this method,and the method had high identification accuracy. Meanwhile,the results would provide theoretical basis for the development of online detection of internal quality in apples and provide a new idea for the study of internal disease detection models for different agricultural products.
Currently,the near infrared transmission spectrum of moldy core in apples was seriously affected by the size of fruit. In order to solve the problem,a transmission spectrum correction method based on size of fruit was proposed. A spectrum acquisition platform was constructed to acquire the transmission spectra( 350 ～ 1 100 nm) of 327 Fuji apples and their diameters were measured with a vernier caliper. The spectrum of healthy apples with diameter of 80 mm was used as reference.Comparing the spectrum of 327 apples with the reference spectrum,a formula was built. The attenuation index of transmitted light in the fruit can be easily found by using the formula and diameters. Then the transmission spectrum was modified with the help of attenuation index. Error back propagation artificial neural networks( BP-ANN) and support vector machine( SVM) measurement model were established based on corrected spectrum and original spectrum. The results showed that the accuracy of the models based on corrected spectrum was much higher than those of the others,and its recognition accuracy rate reached 99. 34% for the training set and 90. 20% for the test set. The recognition rate of the model was7. 84 and 5. 89 percentage points higher than that of the original spectrum. The results showed that the effect of the size on transmission spectra can be corrected by this method,and the method had high identification accuracy. Meanwhile,the results would provide theoretical basis for the development of online detection of internal quality in apples and provide a new idea for the study of internal disease detection models for different agricultural products.
引文
[1]刘会香.苹果霉心病的研究现状及展望[J].水土保持研究,2001,8(3):91-92.LIU Huixiang. The studying advance and prospect of apple moldy core[J]. Research of Soil and Water Conservation,2001,8(3):91-92.(in Chinese)
[2]李晓荣,陈小飞,李晓萍.苹果霉心病发生原因及防治措施[J].果农之友,2009(11):26.
[3]苏东,张海辉,陈克涛,等.基于透射光谱的苹果霉心病多因子无损检测[J].食品科学,2016,37(8):207-211.SU Dong,ZHANG Haihui,CHEN Ketao,et al. Multiple-factor nondestructive detection of moldy core in apples based on transmission spectra[J]. Food Science,2016,37(8):207-211.(in Chinese)
[4] LAMMERTYN J,DRESSELAERS T,HECKEB P V,et al. MRI and X-ray CT study of spatial distribution of core breakdown in‘Conference’pears[J]. Magnetic Resonance Imaging,2003,21(7):805-815.
[5] LU Y,LU R. Non-destructive defect detection of apples by spectroscopic and imaging technologies:a review[J]. Transactions of the ASABE,2017,60(5):1765-1790.
[6] POREP J U,KAMMERER D R,CARLE R. On-line application of near infrared(NIR)spectroscopy in food production[J].Trends in Food Science&Technology,2015,46(2):211-230.
[7]李芳,蔡骋,马惠玲,等.基于生物阻抗特性分析的苹果霉心病无损检测[J].食品科学,2013,34(18):197-202.LI Fang,CAI Cheng,MA Huiling,et al. Nondestructive detection of apple mouldy core based on bioimpedance properties[J].Food Science,2013,34(18):197-202.(in Chinese)
[8]杨亮亮.基于机器视觉和X射线的苹果霉心病检测方法研究[D].杨凌:西北农林科技大学,2009.YANG Liangliang. Research of the detection of mould core apple based on machine vision and X-ray[D]. Yangling:Northwest A&F University,2009.(in Chinese)
[9] MCGLONE V A,MARTINSEN P J,CLARK C J,et al. On-line detection of brownheart in Braeburn apples using near infrared transmission measurements[J]. Postharvest Biology and Technology,2005,37(2):142-151.
[10] CLARK C J,MCGLONE V A,JORDAN R B. Detection of Brownheart in‘Braeburn’apple by transmission NIR spectroscopy[J]. Postharvest Biology and Technology,2003,28(1):87-96.
[11] SHENDEREY C,SHMULEVICH I,ALCHANATIS V,et al. NIRS detection of moldy core in apples[J]. Food and Bioprocess Technology,2010,3(1):79-86.
[12]韩东海,刘新鑫,鲁超,等.苹果内部褐变的光学无损伤检测研究[J].农业机械学报,2006,37(6):86-93.HAN Donghai,LIU Xinxin,LU Chao,et al. Study on optical-nondestructive detection of breakdown apples[J]. Transactions of the Chinese Society for Agricultural Machinery,2006,37(6):86-93.(in Chinese)
[13]雷雨,何东键,周兆永,等.苹果霉心病可见/近红外透射能量光谱识别方法[J/OL].农业机械学报,2016,47(4):193-200. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20160426&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2016. 04. 026.LEI Yu,HE Dongjian,ZHOU Zhaoyong,et al. Detection of moldy core of apples based on visible/near infrared transmission energy spectroscopy[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2016,47(4):193-200.(in Chinese)
[14]李顺峰,张丽华,刘兴华,等.基于主成分分析的苹果霉心病近红外漫反射光谱判别[J].农业机械学报,2011,42(10):158-161.LI Shunfeng,ZHANG Lihua,LIU Xinghua,et al. Discriminant analysis of apple moldy core using near infrared diffuse reflectance spectroscopy based on principal component analysis[J]. Transactions of the Chinese Society for Agricultural Machinery,2011,42(10):158-161.(in Chinese)
[15]张海辉,陈克涛,苏东,等.基于特征光谱的苹果霉心病无损检测设备设计[J].农业工程学报,2016,32(18):255-262.ZHANG Haihui,CHEN Ketao,SU Dong,et al. Design of nondestructive detection device for moldy core in apples based on characteristic spectrum[J]. Transactions of the CSAE,2016,32(18):255-262.(in Chinese)
[16]河野澄夫.近赤外分光法による果実糖度の測定[J].食粮_その科学と技術,2005,43:69-86.
[17] QIN J,LU R. Monte Carlo simulation for quantification of light transport features in apples[J]. Computers and Electronics in Agriculture,2009,68(1):44-51.
[18]刘燕德.水果糖度和酸度的近红外光谱无损检测研究[D].杭州:浙江大学,2006.LIU Yande. Study on methods of nondestructive measurement of sugar content and acidity in fruits using near-infrared spectroscopy[D]. Hangzhou:Zhejiang University,2006.(in Chinese)
[19] CEN H,LU R,MENDOZA F,et al. Relationship of the optical absorption and scattering properties with mechanical and structural properties of apple tissue[J]. Postharvest Biology and Technology,2013,85:30-38.
[20] BEERS R V,AERNOUTS B,WATTE R,et al. Effect of maturation on the bulk optical properties of apple skin and cortex in the 500~1 850 nm wavelength range[J]. Journal of Food Engineering,2017,214:79-89.
[21]闵顺耕,李宁,张明祥.近红外光谱分析中异常值的判别与定量模型优化[J].光谱学与光谱分析,2004,24(10):1205-1209.MIN Shungeng, LI Ning, ZHANG Mingxiang. Outlier diagnosis and calibration model optimization for near infrared spectroscopy analysis[J]. Spectroscopy and Spectral Analysis,2004,24(10):1205-1209.(in Chinese)
[22]陈奕云,赵瑞瑛,齐天赐,等.结合光谱变换和Kennard-Stone算法的水稻土全氮光谱估算模型校正集构建策略研究[J].光谱学与光谱分析,2017,37(7):2133-2139.CHEN Yiyun, ZHAO Ruiying, QI Tianci, et al. Constructing representative calibration dataset based on spectral transformation and Kennard-Stone algorithm for VNIR modeling of soil nitrogen in paddy soil[J]. Spectroscopy and Spectral Analysis,2017,37(7):2133-2139.(in Chinese)
[23]展晓日,朱向荣,史新元,等. SPXY样本划分法及蒙特卡罗交叉验证结合近红外光谱用于橘叶中橙皮苷的含量测定[J].光谱学与光谱分析,2009,29(4):964-968.ZHAN Xiaori, ZHU Xiangrong, SHI Xinyuan, et al. Determination of hesperidin in tangerine leaf by near-infrared Spectroscopy with SPXY algorithm for sample subset partitioning and monte carlo cross validation[J]. Spectroscopy and Spectral Analysis,2009,29(4):964-968.(in Chinese)
[24] KAYA-CELIKER H,MALLIKARJUNAN P K,KAAYA A. Mid-infrared spectroscopy for discrimination and classification of Aspergillus spp. contamination in peanuts[J]. Food Control,2015,52:103-111.
[25]李江波,赵春江,陈立平,等.基于可见/近红外光谱谱区有效波长的梨品种鉴别[J/OL].农业机械学报,2013,44(3):153-157,179. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20130328&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2013. 03. 028.LI Jiangbo,ZHAO Chunjiang,CHEN Liping,et al. Variety identification of pears based on effective wavelengths in vasible/near infrared region[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2013,44(3):153-157,179.(in Chinese)
[26]郭文川,刘大洋.猕猴桃膨大果的近红外漫反射光谱无损识别[J/OL].农业机械学报,2014,45(9):230-235. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20140937&journal_id=jcsam. DOI:10. 6041/j.issn. 1000-1298. 2014. 09. 037.GUO Wenchuan,LIU Dayang. Identification of expanded kiwifruit by near-infrared diffused spectroscopy[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(9):230-235.(in Chinese)
[27]岳学军,全东平,洪添胜,等.柑橘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 Xuejun,QUAN Dongping,HONG Tiansheng,et al. Non-destructive hyperspectral measurement model of chlorophyll content for citrus leaves[J]. Transactions of the CSAE,2015,31(1):294-302.(in Chinese)
[28]栾郭宏,贺凯迅,程辉,等.基于神经网络的近红外光谱辛烷值模型的研究及应用[J].计算机与应用化学,2014,31(1):63-68.LUAN Guohong,HE Kaixun,CHENG Hui,et al. Octane model based on neural network by near-infrared spectroscopy and its application[J]. Computers and Applied Chemistry,2014,31(1):63-68.(in Chinese)
[29] CORTES C,VAPNIK V. Support-vector networks[J]. Machine Learning,1995,20(3):273-297.
[2]李晓荣,陈小飞,李晓萍.苹果霉心病发生原因及防治措施[J].果农之友,2009(11):26.
[3]苏东,张海辉,陈克涛,等.基于透射光谱的苹果霉心病多因子无损检测[J].食品科学,2016,37(8):207-211.SU Dong,ZHANG Haihui,CHEN Ketao,et al. Multiple-factor nondestructive detection of moldy core in apples based on transmission spectra[J]. Food Science,2016,37(8):207-211.(in Chinese)
[4] LAMMERTYN J,DRESSELAERS T,HECKEB P V,et al. MRI and X-ray CT study of spatial distribution of core breakdown in‘Conference’pears[J]. Magnetic Resonance Imaging,2003,21(7):805-815.
[5] LU Y,LU R. Non-destructive defect detection of apples by spectroscopic and imaging technologies:a review[J]. Transactions of the ASABE,2017,60(5):1765-1790.
[6] POREP J U,KAMMERER D R,CARLE R. On-line application of near infrared(NIR)spectroscopy in food production[J].Trends in Food Science&Technology,2015,46(2):211-230.
[7]李芳,蔡骋,马惠玲,等.基于生物阻抗特性分析的苹果霉心病无损检测[J].食品科学,2013,34(18):197-202.LI Fang,CAI Cheng,MA Huiling,et al. Nondestructive detection of apple mouldy core based on bioimpedance properties[J].Food Science,2013,34(18):197-202.(in Chinese)
[8]杨亮亮.基于机器视觉和X射线的苹果霉心病检测方法研究[D].杨凌:西北农林科技大学,2009.YANG Liangliang. Research of the detection of mould core apple based on machine vision and X-ray[D]. Yangling:Northwest A&F University,2009.(in Chinese)
[9] MCGLONE V A,MARTINSEN P J,CLARK C J,et al. On-line detection of brownheart in Braeburn apples using near infrared transmission measurements[J]. Postharvest Biology and Technology,2005,37(2):142-151.
[10] CLARK C J,MCGLONE V A,JORDAN R B. Detection of Brownheart in‘Braeburn’apple by transmission NIR spectroscopy[J]. Postharvest Biology and Technology,2003,28(1):87-96.
[11] SHENDEREY C,SHMULEVICH I,ALCHANATIS V,et al. NIRS detection of moldy core in apples[J]. Food and Bioprocess Technology,2010,3(1):79-86.
[12]韩东海,刘新鑫,鲁超,等.苹果内部褐变的光学无损伤检测研究[J].农业机械学报,2006,37(6):86-93.HAN Donghai,LIU Xinxin,LU Chao,et al. Study on optical-nondestructive detection of breakdown apples[J]. Transactions of the Chinese Society for Agricultural Machinery,2006,37(6):86-93.(in Chinese)
[13]雷雨,何东键,周兆永,等.苹果霉心病可见/近红外透射能量光谱识别方法[J/OL].农业机械学报,2016,47(4):193-200. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20160426&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2016. 04. 026.LEI Yu,HE Dongjian,ZHOU Zhaoyong,et al. Detection of moldy core of apples based on visible/near infrared transmission energy spectroscopy[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2016,47(4):193-200.(in Chinese)
[14]李顺峰,张丽华,刘兴华,等.基于主成分分析的苹果霉心病近红外漫反射光谱判别[J].农业机械学报,2011,42(10):158-161.LI Shunfeng,ZHANG Lihua,LIU Xinghua,et al. Discriminant analysis of apple moldy core using near infrared diffuse reflectance spectroscopy based on principal component analysis[J]. Transactions of the Chinese Society for Agricultural Machinery,2011,42(10):158-161.(in Chinese)
[15]张海辉,陈克涛,苏东,等.基于特征光谱的苹果霉心病无损检测设备设计[J].农业工程学报,2016,32(18):255-262.ZHANG Haihui,CHEN Ketao,SU Dong,et al. Design of nondestructive detection device for moldy core in apples based on characteristic spectrum[J]. Transactions of the CSAE,2016,32(18):255-262.(in Chinese)
[16]河野澄夫.近赤外分光法による果実糖度の測定[J].食粮_その科学と技術,2005,43:69-86.
[17] QIN J,LU R. Monte Carlo simulation for quantification of light transport features in apples[J]. Computers and Electronics in Agriculture,2009,68(1):44-51.
[18]刘燕德.水果糖度和酸度的近红外光谱无损检测研究[D].杭州:浙江大学,2006.LIU Yande. Study on methods of nondestructive measurement of sugar content and acidity in fruits using near-infrared spectroscopy[D]. Hangzhou:Zhejiang University,2006.(in Chinese)
[19] CEN H,LU R,MENDOZA F,et al. Relationship of the optical absorption and scattering properties with mechanical and structural properties of apple tissue[J]. Postharvest Biology and Technology,2013,85:30-38.
[20] BEERS R V,AERNOUTS B,WATTE R,et al. Effect of maturation on the bulk optical properties of apple skin and cortex in the 500~1 850 nm wavelength range[J]. Journal of Food Engineering,2017,214:79-89.
[21]闵顺耕,李宁,张明祥.近红外光谱分析中异常值的判别与定量模型优化[J].光谱学与光谱分析,2004,24(10):1205-1209.MIN Shungeng, LI Ning, ZHANG Mingxiang. Outlier diagnosis and calibration model optimization for near infrared spectroscopy analysis[J]. Spectroscopy and Spectral Analysis,2004,24(10):1205-1209.(in Chinese)
[22]陈奕云,赵瑞瑛,齐天赐,等.结合光谱变换和Kennard-Stone算法的水稻土全氮光谱估算模型校正集构建策略研究[J].光谱学与光谱分析,2017,37(7):2133-2139.CHEN Yiyun, ZHAO Ruiying, QI Tianci, et al. Constructing representative calibration dataset based on spectral transformation and Kennard-Stone algorithm for VNIR modeling of soil nitrogen in paddy soil[J]. Spectroscopy and Spectral Analysis,2017,37(7):2133-2139.(in Chinese)
[23]展晓日,朱向荣,史新元,等. SPXY样本划分法及蒙特卡罗交叉验证结合近红外光谱用于橘叶中橙皮苷的含量测定[J].光谱学与光谱分析,2009,29(4):964-968.ZHAN Xiaori, ZHU Xiangrong, SHI Xinyuan, et al. Determination of hesperidin in tangerine leaf by near-infrared Spectroscopy with SPXY algorithm for sample subset partitioning and monte carlo cross validation[J]. Spectroscopy and Spectral Analysis,2009,29(4):964-968.(in Chinese)
[24] KAYA-CELIKER H,MALLIKARJUNAN P K,KAAYA A. Mid-infrared spectroscopy for discrimination and classification of Aspergillus spp. contamination in peanuts[J]. Food Control,2015,52:103-111.
[25]李江波,赵春江,陈立平,等.基于可见/近红外光谱谱区有效波长的梨品种鉴别[J/OL].农业机械学报,2013,44(3):153-157,179. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20130328&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2013. 03. 028.LI Jiangbo,ZHAO Chunjiang,CHEN Liping,et al. Variety identification of pears based on effective wavelengths in vasible/near infrared region[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2013,44(3):153-157,179.(in Chinese)
[26]郭文川,刘大洋.猕猴桃膨大果的近红外漫反射光谱无损识别[J/OL].农业机械学报,2014,45(9):230-235. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20140937&journal_id=jcsam. DOI:10. 6041/j.issn. 1000-1298. 2014. 09. 037.GUO Wenchuan,LIU Dayang. Identification of expanded kiwifruit by near-infrared diffused spectroscopy[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(9):230-235.(in Chinese)
[27]岳学军,全东平,洪添胜,等.柑橘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 Xuejun,QUAN Dongping,HONG Tiansheng,et al. Non-destructive hyperspectral measurement model of chlorophyll content for citrus leaves[J]. Transactions of the CSAE,2015,31(1):294-302.(in Chinese)
[28]栾郭宏,贺凯迅,程辉,等.基于神经网络的近红外光谱辛烷值模型的研究及应用[J].计算机与应用化学,2014,31(1):63-68.LUAN Guohong,HE Kaixun,CHENG Hui,et al. Octane model based on neural network by near-infrared spectroscopy and its application[J]. Computers and Applied Chemistry,2014,31(1):63-68.(in Chinese)
[29] CORTES C,VAPNIK V. Support-vector networks[J]. Machine Learning,1995,20(3):273-297.