基于机器视觉和近红外光谱的水果品质分级研究
|
摘要
本文以苹果为对象,研究了基于机器视觉和近红外光谱技术的水果品质分级。建立了苹果静态漫透射近红外光谱糖度预测模型;研究了结合DSP机器视觉系统的苹果近红外光谱动态检测方法;研究了苹果外部特征与糖度的分级模型,以及基于信息融合技术的分级模型。
首先对静态漫透射近红外光谱进行分析,研究了不同的预处理方法对预测模型的影响,选定合适的预处理方法;采用反向间隔偏最小二乘法对光谱变量区间进行初步定位,减少建模变量空间;采用量子进化算法对经过初步筛选的变量进一步进行优选,并与遗传算法优选效果进行了比较,最终建立了静态漫透射近红外光谱与苹果糖度的预测模型。
其次,在现有的水果分级设备上,搭建了动态漫透射近红外光谱检测平台,并与DSP机器视觉系统结合,采集苹果动态近红外光谱,研究动态光谱糖度预测模型;将近红外检测功能应用在DSP水果分级系统中,编写分级软件,使系统能够同时检测水果的外部品质和内部品质,从而对水果综合品质分级。
然后,采用图像处理算法,从苹果样品图像中提取出水果的大小、颜色、果形、纹理等特征,并对这些特征进行选择,建立外部特征与苹果糖度的神经网络分级模型和支持向量机分级模型;实验结果表明,采用支持向量机建立的分级模型分级准确率高于神经网络分级模型。
最后,从苹果样品的近红外光谱信息中提取出光谱数据的主成分特征,做为近红外信息特征,然后采用支持向量机融合水果的外部特征和近红外主成分特征,建立了基于机器视觉和近红外信息融合的糖度分级模型,实验结果表明,采用信息融合技术建立的分级模型准确率,高于采用单一DSP图像处理系统或单一近红外检测系统所建立的糖度分级模型正确率。
The thesis choses the apple as research object, studies the apple’s quality assessment based on machine vision and near infrared spectrophotometer (NIRS) technologys. This research establishes the predication model of apples’suguar based on the static diffuse transimission NIR spectrophotometer, studies the application of dynamic NIR on fruit sorting system combined machine vision, buildes the sorting model of apples’suguar with outward features and the sorting model based information fusion of outward and internal features.
Firstly, the static diffuse transimission NIR spectrophotometer of apples was analysed.It studied different preprocessing methods and chosed appropriate ones. Spectroscopy’s regions were preselected by using the backward interval partial least squares (BiPLS), and quantum-Inspired evolutionary algorithms(QEA) was applied in the selection of NIR spectroscopy variables for the prediction of apple sugar degree.At the sametime, QEA model was compared to genetic algorithms(GA) model.
Secondly, the detecting platform of dynamic NIR was constructed on the fruit sorting equipment. Dynamic NIR spectrophotometer was acquired with the equipment combined DSP machine vision system, and dynamic prediction model of apples’suguar was studied.The NIR detecting function was added to the sorting equipment, so it can detect outward quality and internal quality.
Then,the outward features of apples including size,colour,shape and texture were extracted.Suituable outward features were chosed to build sorting models of apples’suguar with artificial neural netowrk( ANN) and support vector machines(SVM).Tht SVM model is better than the ANN model.
At last, principal component features were extracted out from the NIR spectrophotometer as apples’interal features.Then outward features and internal features were fused with SVM to constructed sorting model of apples’suguar.The result shows that the sorting model with fusion technology is better than the model with single sensor.
首先对静态漫透射近红外光谱进行分析,研究了不同的预处理方法对预测模型的影响,选定合适的预处理方法;采用反向间隔偏最小二乘法对光谱变量区间进行初步定位,减少建模变量空间;采用量子进化算法对经过初步筛选的变量进一步进行优选,并与遗传算法优选效果进行了比较,最终建立了静态漫透射近红外光谱与苹果糖度的预测模型。
其次,在现有的水果分级设备上,搭建了动态漫透射近红外光谱检测平台,并与DSP机器视觉系统结合,采集苹果动态近红外光谱,研究动态光谱糖度预测模型;将近红外检测功能应用在DSP水果分级系统中,编写分级软件,使系统能够同时检测水果的外部品质和内部品质,从而对水果综合品质分级。
然后,采用图像处理算法,从苹果样品图像中提取出水果的大小、颜色、果形、纹理等特征,并对这些特征进行选择,建立外部特征与苹果糖度的神经网络分级模型和支持向量机分级模型;实验结果表明,采用支持向量机建立的分级模型分级准确率高于神经网络分级模型。
最后,从苹果样品的近红外光谱信息中提取出光谱数据的主成分特征,做为近红外信息特征,然后采用支持向量机融合水果的外部特征和近红外主成分特征,建立了基于机器视觉和近红外信息融合的糖度分级模型,实验结果表明,采用信息融合技术建立的分级模型准确率,高于采用单一DSP图像处理系统或单一近红外检测系统所建立的糖度分级模型正确率。
The thesis choses the apple as research object, studies the apple’s quality assessment based on machine vision and near infrared spectrophotometer (NIRS) technologys. This research establishes the predication model of apples’suguar based on the static diffuse transimission NIR spectrophotometer, studies the application of dynamic NIR on fruit sorting system combined machine vision, buildes the sorting model of apples’suguar with outward features and the sorting model based information fusion of outward and internal features.
Firstly, the static diffuse transimission NIR spectrophotometer of apples was analysed.It studied different preprocessing methods and chosed appropriate ones. Spectroscopy’s regions were preselected by using the backward interval partial least squares (BiPLS), and quantum-Inspired evolutionary algorithms(QEA) was applied in the selection of NIR spectroscopy variables for the prediction of apple sugar degree.At the sametime, QEA model was compared to genetic algorithms(GA) model.
Secondly, the detecting platform of dynamic NIR was constructed on the fruit sorting equipment. Dynamic NIR spectrophotometer was acquired with the equipment combined DSP machine vision system, and dynamic prediction model of apples’suguar was studied.The NIR detecting function was added to the sorting equipment, so it can detect outward quality and internal quality.
Then,the outward features of apples including size,colour,shape and texture were extracted.Suituable outward features were chosed to build sorting models of apples’suguar with artificial neural netowrk( ANN) and support vector machines(SVM).Tht SVM model is better than the ANN model.
At last, principal component features were extracted out from the NIR spectrophotometer as apples’interal features.Then outward features and internal features were fused with SVM to constructed sorting model of apples’suguar.The result shows that the sorting model with fusion technology is better than the model with single sensor.
引文
[1]白菲,孟超英.水果自动分级技术的现状与发展.食品科学,2005,26:145~148.
[2]韩东海,王加华.2008水果内部品质近红外光谱无损检测研究进展[J].中国激光,35(10):1123~1131.
[3]刘同明,夏祖勋,解洪成.数据融合技术及其应用[M].北京:国防工业出版社,1998.
[4]张永利.基于支持向量机的信息融合技术研究与应用[硕士学位论文].西安,西安科技大学,2008.
[5]鲁敏,王洪坤.计算机视觉技术在农业中的应用.农机化研究,2008,6:240~244.
[6] Wen Z, Tao Y. Building a rule-based machine vision system for defect inspection on apple sorting and packing lines. Expert systems with application, 1999(16):307~313.
[7] Tao Y, Heinemann P H, et al. Machine vision for color inspection of potatoes and apples. Transactions of the ASAE, 1995, 38(5):1555-1561.
[8] Varghese Z, Morrow C T, Heinemann P H. Automated inspection of golden delicious apples using color computer vision. ASAE paper, 1991, No.91-7002
[9] Van De Vooren J G, Polder G, Van Der Heijden W A M. Identification of mushrooms cultivars using image analysis. Transactions of the ASAE, 1992, 35(l):347~350
[10] Leemans V, Magein H, Destain M F. Apple shape Inspection with computer Vision. Proceedings from the sensors for Nondestructive Testing Internationa1Conference, Orlando Florida, 1997,316~327.
[11]刘禾,汪懋华.水果果形判别人工神经网络专家系统的研究.农业工程学报,1996,12(1):171~176.
[12]应义斌,景寒松、马俊福等.机器视觉技术在黄花梨尺寸和果面缺陷检测中的应用.农业工程学报.1999,15(1):197~200.
[13]张书慧,陈晓光,张晓梅等.苹果、桃等农副产品品质检测与分级图像处理系统的研究.农业工程学报,1999,15(1):201:204.
[14]应以斌.水果形状的傅里叶描述子研究.生物数学学报,2001, 16(2):234~240
[15]冯斌.计算机视觉信息处理方法与水果分级检测技术研究[博士学位论文].北京,中国农业大学,2002.
[16] Kawano S., Fujiwara T., Iwamoto, M. Nondestructive determination of mandarin using near infrared (NIR) transmittance [J]. Japan. Soc. Hort. Soc. 1993, 62 (2): 465~470.
[17] Lammertyn J, Nicolai B M, Ooms K, et a1. Non~destructive measurement of acidity, soluble solids and firmness of Jonagold apples using NIR spectroscopy [J]. Trans. of the ASAE, 1998, 41(4): 1089~1094.
[18] McGlone V A, JordanR B, et al. Vis MIR estimation at harvest of pre~ and post~storage quality indices for 'Royal Gala' apple [J]. Postharvest Biology and Technology, 2002, 25 (2): 135~144.
[19] Bennedsen B S, Peterson D L. An optical method for detecting watercore and meatiness in apples[J]. Transactions of ASAE, 2005, 48(5): 1819~1826.
[20]陈世铭,张文宏等.果汁糖度检测模式之研究.农业机械学刊, 1998, 7(3): 41~60.
[21]何东健,前川孝昭等.水果内部品质在线近红外分光检测装置及试验.农业工程学报, 2001,17(1): 146~148.
[22]刘燕德,欧阳爱国,罗吉等.近红外漫反射检测赣南脐橙可溶性固形物的研究.光谱学与光谱分析,2007,27(11):2190~2192.
[23]杜冉,闸建文等.运用近红外透射光谱技术检测苹果内部品质.农机化研究,2008, 9: 139~141.
[24]陆辉山,傅霞萍,应义斌等.可见/近红外光估测完整柑橘水果可溶性固形物含量的研究.光谱学与光谱分析,2007,27(9):1727~1730.
[25]田海清,应义斌,陆辉山等.可见/近红外光谱漫透射技术检测西瓜坚实度的研究.光谱学与光谱分析,2007,27(6):1113~1117.
[26]李鹏飞.梨内部品质可见/近红外光谱无损检测研究[硕士学位论文].北京,中国农业大学,2009.
[27] Fildes J M, Cinar A. Sensor fusion and intelligent control for food processing.ASAE,Food Processing Automation Conference IV, 1995:67~72 .
[28] Shmulevich I, Rachmani D, Edan Y. Quality grading tomatoes by mechanical properties using a neural network system. International Conference on Agricultural Engineering, Milan, Italy, EuragEng Paper,1994,No.94-g-064.
[29] Ozer N, Engel B A, Simon J E. Fusion classification techniques for fruit quality. Transactions of the ASAE, 1995,38(6):1927~1934.
[30] Armstrong P R, Stone M L, Brusewitz G H. Peach firmness determination using two different nondestructive vibrational sensing instruments. Transactions of the ASAE,1997,40(3):699~703.
[31] V.Steinmetz, F.Sevila, V.Bellon-Maurel. A Methodology for Sensor Fusion Design:Application to Fruit Quality Assessment. J.agric.Engng Res,1999,74:21~31.
[32] V. Steinmetz,J. M. Roger,E. MoltoH 2, J. Blasco2. On-line Fusion of Colour Camera and Spectrophotometer for Sugar ContentPrediction of Apples[J]. J. Agric. Engng Res. 1999, 73: 207-216.
[33] Changying Li, Paul Heinemnn, Richard Sherry. Neural network and Bayesian network fusion models to fuse electronic nose and surface acoustic wave sensor data for apple defect detection. Sensors and Actuators,2007,125:301~310.
[34] Zou Xiaobo, Zhao Jiewen. Apple quality assessment by fusion three sensors. IEEE, 2005: 389~392.
[35]杨丽华,程咏梅,赵春晖等.基于决策融合的苹果等级分类算法.电子测量技术,2008,31(1):10~12.
[36]陆辉山.水果内部品质可见/近红外光谱实时无损检测关键技术研究[博士学位论文].浙江,浙江大学,2006.
[37]梁逸曾,俞汝勤.分析化学手册(10)——化学计量学[M],北京:化工出版社, 2001.
[38]杜冉.基于近红外光谱透射技术的苹果内部品质在线检测的研究[硕士学位论文].山东,山东理工大学,2008.
[39]陆婉珍.现代近红外光谱分析技术[M].北京:中国石化出版社, 2006.
[40]刘建学.实用近红外光谱分析技术[M].北京:科学出版社, 2008.
[41]刘蓉.近红外光谱分析中模型优化方法的初步研究[硕士学位论文].天津,天津大学,2003.
[42]李民赞.光谱分析技术及其应用[M].北京:科学出版社,2006.
[43]褚小丽,袁洪福,陆婉珍.近红外光谱分析中光谱预处理及波长选择方法进展与应用.化学进展,2004,16(4):528~541.
[44]李鹏飞,王加华,曹楠宁,韩东海.BiPLS结合GA优选可见/近红外光谱MLR变量.光谱学与光谱分析,2009,29(10):2637-2641.
[45]梁田,郑楠,齐文宗.近红外光谱法快速分析罗红霉素两种主要成分.理化检验――化学分册,2007,43(12):1000~1003.
[46]范胜辉.量子进化算法及其应用研究[硕士学位论文].南京,南京航空航天大学,2010.
[47] Han K H, Kim J H. Quantum-inspired evolutionary algorithm for a class of combinatorial optimization[J]. IEEE Transactions on Evolutionary Computation,2002, 6(6): 580-593.
[48]李俊山,李旭辉.数字图像处理[M].北京:清华大学出版社,2007.
[49]杨文浩.嵌入式机器视觉系统[硕士学位论文].无锡,江南大学,2009.
[50]杨帆等.数字图像处理与分析[M].北京:北京航空航天大学出版社,2007.
[51]刘仰龙.基于DSP机器视觉的水果外形分级技术研究[硕士学位论文].南京,南京航空航天大学,2010.
[52]谢忠红,郭小清,姬长英.基于颜色模型和纹理特征的水果图像分割方法.计算机工程与科学,2010,32(1):64~66.
[53]侯大中,朱伟兴,董国贵.基于图像处理的苹果形状特征的提取研究.信息化纵横,2009,14:54~57.
[54]侯海苗,冀小平.基于灰度共生矩阵的纹理特征.长治学院学报,2008,25(5):31~32.
[55]蒋益女,徐从富.结合纹理分析和SVM苹果梗蒂和缺陷识别方法.计算机工程与应用,2008,44(1):235~237.
[56]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2004.
[57]何勇,李晓丽,邵咏妮.基于主成分分析和神经网络的近红外光谱苹果品种鉴别方法研究.光谱学与光谱分析, 2006,26(5): 850~853.
[58]冯瑞,宋春林等.基于支持向量机与RBF神经网络的软测量模型比较研究[J].上海交通大学学报, 2003. 37(sup): 122~125.
[59]李悦卿.基于神经网络和最小二乘支持向量机的软测量技术应用研究.青岛:青岛科技大学, 2007.
[60] Tsai C F. Training support vector rnachines based on stacked generalization for image classification [J]. Neurocomputing, 2005, 64: 497~503.
[61] Wu D, He Y et a1. Study on infrared spectroscopy technique for fast measurementof protein content in milk powder based on LS~SVM [J]. Journal of Food Engineering, 2008, 84: 124~131.
[62]陈全胜,赵杰文,蔡健荣.基于近红外光谱和机器视觉的多信息融合技术评判茶叶品质.农业工程学报,2008,24(3):5~10.
[2]韩东海,王加华.2008水果内部品质近红外光谱无损检测研究进展[J].中国激光,35(10):1123~1131.
[3]刘同明,夏祖勋,解洪成.数据融合技术及其应用[M].北京:国防工业出版社,1998.
[4]张永利.基于支持向量机的信息融合技术研究与应用[硕士学位论文].西安,西安科技大学,2008.
[5]鲁敏,王洪坤.计算机视觉技术在农业中的应用.农机化研究,2008,6:240~244.
[6] Wen Z, Tao Y. Building a rule-based machine vision system for defect inspection on apple sorting and packing lines. Expert systems with application, 1999(16):307~313.
[7] Tao Y, Heinemann P H, et al. Machine vision for color inspection of potatoes and apples. Transactions of the ASAE, 1995, 38(5):1555-1561.
[8] Varghese Z, Morrow C T, Heinemann P H. Automated inspection of golden delicious apples using color computer vision. ASAE paper, 1991, No.91-7002
[9] Van De Vooren J G, Polder G, Van Der Heijden W A M. Identification of mushrooms cultivars using image analysis. Transactions of the ASAE, 1992, 35(l):347~350
[10] Leemans V, Magein H, Destain M F. Apple shape Inspection with computer Vision. Proceedings from the sensors for Nondestructive Testing Internationa1Conference, Orlando Florida, 1997,316~327.
[11]刘禾,汪懋华.水果果形判别人工神经网络专家系统的研究.农业工程学报,1996,12(1):171~176.
[12]应义斌,景寒松、马俊福等.机器视觉技术在黄花梨尺寸和果面缺陷检测中的应用.农业工程学报.1999,15(1):197~200.
[13]张书慧,陈晓光,张晓梅等.苹果、桃等农副产品品质检测与分级图像处理系统的研究.农业工程学报,1999,15(1):201:204.
[14]应以斌.水果形状的傅里叶描述子研究.生物数学学报,2001, 16(2):234~240
[15]冯斌.计算机视觉信息处理方法与水果分级检测技术研究[博士学位论文].北京,中国农业大学,2002.
[16] Kawano S., Fujiwara T., Iwamoto, M. Nondestructive determination of mandarin using near infrared (NIR) transmittance [J]. Japan. Soc. Hort. Soc. 1993, 62 (2): 465~470.
[17] Lammertyn J, Nicolai B M, Ooms K, et a1. Non~destructive measurement of acidity, soluble solids and firmness of Jonagold apples using NIR spectroscopy [J]. Trans. of the ASAE, 1998, 41(4): 1089~1094.
[18] McGlone V A, JordanR B, et al. Vis MIR estimation at harvest of pre~ and post~storage quality indices for 'Royal Gala' apple [J]. Postharvest Biology and Technology, 2002, 25 (2): 135~144.
[19] Bennedsen B S, Peterson D L. An optical method for detecting watercore and meatiness in apples[J]. Transactions of ASAE, 2005, 48(5): 1819~1826.
[20]陈世铭,张文宏等.果汁糖度检测模式之研究.农业机械学刊, 1998, 7(3): 41~60.
[21]何东健,前川孝昭等.水果内部品质在线近红外分光检测装置及试验.农业工程学报, 2001,17(1): 146~148.
[22]刘燕德,欧阳爱国,罗吉等.近红外漫反射检测赣南脐橙可溶性固形物的研究.光谱学与光谱分析,2007,27(11):2190~2192.
[23]杜冉,闸建文等.运用近红外透射光谱技术检测苹果内部品质.农机化研究,2008, 9: 139~141.
[24]陆辉山,傅霞萍,应义斌等.可见/近红外光估测完整柑橘水果可溶性固形物含量的研究.光谱学与光谱分析,2007,27(9):1727~1730.
[25]田海清,应义斌,陆辉山等.可见/近红外光谱漫透射技术检测西瓜坚实度的研究.光谱学与光谱分析,2007,27(6):1113~1117.
[26]李鹏飞.梨内部品质可见/近红外光谱无损检测研究[硕士学位论文].北京,中国农业大学,2009.
[27] Fildes J M, Cinar A. Sensor fusion and intelligent control for food processing.ASAE,Food Processing Automation Conference IV, 1995:67~72 .
[28] Shmulevich I, Rachmani D, Edan Y. Quality grading tomatoes by mechanical properties using a neural network system. International Conference on Agricultural Engineering, Milan, Italy, EuragEng Paper,1994,No.94-g-064.
[29] Ozer N, Engel B A, Simon J E. Fusion classification techniques for fruit quality. Transactions of the ASAE, 1995,38(6):1927~1934.
[30] Armstrong P R, Stone M L, Brusewitz G H. Peach firmness determination using two different nondestructive vibrational sensing instruments. Transactions of the ASAE,1997,40(3):699~703.
[31] V.Steinmetz, F.Sevila, V.Bellon-Maurel. A Methodology for Sensor Fusion Design:Application to Fruit Quality Assessment. J.agric.Engng Res,1999,74:21~31.
[32] V. Steinmetz,J. M. Roger,E. MoltoH 2, J. Blasco2. On-line Fusion of Colour Camera and Spectrophotometer for Sugar ContentPrediction of Apples[J]. J. Agric. Engng Res. 1999, 73: 207-216.
[33] Changying Li, Paul Heinemnn, Richard Sherry. Neural network and Bayesian network fusion models to fuse electronic nose and surface acoustic wave sensor data for apple defect detection. Sensors and Actuators,2007,125:301~310.
[34] Zou Xiaobo, Zhao Jiewen. Apple quality assessment by fusion three sensors. IEEE, 2005: 389~392.
[35]杨丽华,程咏梅,赵春晖等.基于决策融合的苹果等级分类算法.电子测量技术,2008,31(1):10~12.
[36]陆辉山.水果内部品质可见/近红外光谱实时无损检测关键技术研究[博士学位论文].浙江,浙江大学,2006.
[37]梁逸曾,俞汝勤.分析化学手册(10)——化学计量学[M],北京:化工出版社, 2001.
[38]杜冉.基于近红外光谱透射技术的苹果内部品质在线检测的研究[硕士学位论文].山东,山东理工大学,2008.
[39]陆婉珍.现代近红外光谱分析技术[M].北京:中国石化出版社, 2006.
[40]刘建学.实用近红外光谱分析技术[M].北京:科学出版社, 2008.
[41]刘蓉.近红外光谱分析中模型优化方法的初步研究[硕士学位论文].天津,天津大学,2003.
[42]李民赞.光谱分析技术及其应用[M].北京:科学出版社,2006.
[43]褚小丽,袁洪福,陆婉珍.近红外光谱分析中光谱预处理及波长选择方法进展与应用.化学进展,2004,16(4):528~541.
[44]李鹏飞,王加华,曹楠宁,韩东海.BiPLS结合GA优选可见/近红外光谱MLR变量.光谱学与光谱分析,2009,29(10):2637-2641.
[45]梁田,郑楠,齐文宗.近红外光谱法快速分析罗红霉素两种主要成分.理化检验――化学分册,2007,43(12):1000~1003.
[46]范胜辉.量子进化算法及其应用研究[硕士学位论文].南京,南京航空航天大学,2010.
[47] Han K H, Kim J H. Quantum-inspired evolutionary algorithm for a class of combinatorial optimization[J]. IEEE Transactions on Evolutionary Computation,2002, 6(6): 580-593.
[48]李俊山,李旭辉.数字图像处理[M].北京:清华大学出版社,2007.
[49]杨文浩.嵌入式机器视觉系统[硕士学位论文].无锡,江南大学,2009.
[50]杨帆等.数字图像处理与分析[M].北京:北京航空航天大学出版社,2007.
[51]刘仰龙.基于DSP机器视觉的水果外形分级技术研究[硕士学位论文].南京,南京航空航天大学,2010.
[52]谢忠红,郭小清,姬长英.基于颜色模型和纹理特征的水果图像分割方法.计算机工程与科学,2010,32(1):64~66.
[53]侯大中,朱伟兴,董国贵.基于图像处理的苹果形状特征的提取研究.信息化纵横,2009,14:54~57.
[54]侯海苗,冀小平.基于灰度共生矩阵的纹理特征.长治学院学报,2008,25(5):31~32.
[55]蒋益女,徐从富.结合纹理分析和SVM苹果梗蒂和缺陷识别方法.计算机工程与应用,2008,44(1):235~237.
[56]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2004.
[57]何勇,李晓丽,邵咏妮.基于主成分分析和神经网络的近红外光谱苹果品种鉴别方法研究.光谱学与光谱分析, 2006,26(5): 850~853.
[58]冯瑞,宋春林等.基于支持向量机与RBF神经网络的软测量模型比较研究[J].上海交通大学学报, 2003. 37(sup): 122~125.
[59]李悦卿.基于神经网络和最小二乘支持向量机的软测量技术应用研究.青岛:青岛科技大学, 2007.
[60] Tsai C F. Training support vector rnachines based on stacked generalization for image classification [J]. Neurocomputing, 2005, 64: 497~503.
[61] Wu D, He Y et a1. Study on infrared spectroscopy technique for fast measurementof protein content in milk powder based on LS~SVM [J]. Journal of Food Engineering, 2008, 84: 124~131.
[62]陈全胜,赵杰文,蔡健荣.基于近红外光谱和机器视觉的多信息融合技术评判茶叶品质.农业工程学报,2008,24(3):5~10.