基于机器视觉的新疆库尔勒香梨颜色及轻微碰伤无损检测关键技术研究
|
摘要
库尔勒香梨是新疆在海内外最负盛名的果品之一,也是新疆出口创汇的重要产业之一。目前香梨分级主要是依靠人工分级,由于分级人员长期大量依靠目测分级,容易产生视觉疲劳和情绪波动,而且每个人对颜色的标准等感官不一,难免产生误差,造成同一个香梨有不同检测结果,这不仅影响了香梨的果品价值,也不利于保证水果质量和提高消费满意度。在很多同类水果中,着色好且均匀一致的水果商品价值较高。颜色也在一定程度上间接反映了水果的糖度、酸度及口感等。同时,香梨表面的轻微碰伤由于颜色和正常区域相近,容易被忽视。因此,香梨按颜色分级和轻微碰伤的检测也是香梨自动化检测中的两项重要内容。本文提出了基于机器视觉技术对库尔勒香梨的颜色和轻微碰伤进行无损检测,主要方法及内容如下：
通过对香梨进行自动化分级的必要性和国内外在水果智能检测领域的研究现状进行分析,提出了利用机器视觉技术对香梨进行颜色分级和碰伤检测的方法,并针对香梨颜色和轻微碰伤检测的研究内容确定了研究方法。
根据研究内容设计相关实验系统,并对系统的构成和各部件选取进行了分析和优化,概述了实验所用的实验仪器和软件系统。利用机器视觉技术对香梨颜色进行分级的方法进行了研究,找到了对香梨背景分割的方法：利用HSI模式下的H分量作为香梨分割的模板,再进行闽值分割和二值化,得到香梨和背景的分割图,利用该分割图与原香梨图像进行融合,得到去除背景的香梨图像,并对其表面像素和平均值做统计,将统计结果作为人工神经网络的输入,颜色信息作为输出,分别比较了基于BP人工神经网络和RBF人工神经网络的香梨颜色分级,两种方法的分级准确率均为95%。
同时,针对香梨碰伤特点,设计了香梨的碰伤实验装置,对香梨进行人工碰伤。利用机器视觉技术和高光谱图像技术对香梨碰伤进行研究,使用了主成分分析法和独立分量分析法,分别利用主成分分析法和独立分量分析法对获取的高光谱图像数据处理分析,发现香梨第四主成分包含碰伤的主要信息,直接对该主成分进行图像处理和分析,碰伤提取的准确率为81.0%,通过提取特征向量发现其的主要贡献波段分别为528nm,662nm和740nm,利用光谱图像融合技术对主要贡献波段进行融合并处理分析,检测准确率为70.9%。利用独立分量分析可以检测到在第四分量下的香梨碰伤区域,对该分量进行图像处理,提取碰伤区域,检测准确率为82.5%。
最后,归纳了本文的主要结论和有待于进一步研究的内容。
Kurle fragrant pear is one of the most popular fruits in abroad producted by Xinjiang. It's a very important local Economic fruit. Right now, main grading method is by manpower. For a long time working, the works would too busy to keep precision, and everyone would have different result for the same pear. Different standards not only influence the value of fragrant pear, but also influence the quality of fragrant pears and customs' contentment. Some same kind of fruits will have a good price when they have the same color. Color reflects the mature degree of fruits. The bruising of fragrant offen has the same color with normal area, they were easy to neglect. So the color grading and bruising inspection are two important targets of fragrant pears automatic grading. The paper provides a new algorithm of the Kurle fragrant pears' color and bruising non-destructive based on machine vision. The contents of each chapter are described as follows:
A method for color grading and druises detection was introduced. The research status of automated classification and the need for domestic and foreign intelligence testing was analyzed.
According to the study the experimental systems was desined and optimized. The equipment and software system was introduced. The method of pear grading based on machine vision was researched:H component of HSI was used to be the template of image segmentation. The image of pear apart from background was gain after thresholding and binaryzation. The statistics of average and mean square deviation of surface pixels was as the import of ANN, the color information was as the output.The rate of accuracy were both 95% by two methods.
According to the characteristics of pear bruising, the bruising equipment was designed and used to simulate bruise. The machine vision technology and hyperspectral imaging technology were used to detect the slight bruisings of pear. PCA and ICA was used to analysis the dates. PCA4 was found with mainly information of bruising. The rate of accuracy was 81.0% by directly processing PCA 4. The rate of accuracy was 70.9% by processing the image which fused by 528 nm,662 nm and 740 nm. The rate of accuracy was 82.5% by processing ICA 4.
At least part discusses the main achievements and conclusions and some problems for further study.
通过对香梨进行自动化分级的必要性和国内外在水果智能检测领域的研究现状进行分析,提出了利用机器视觉技术对香梨进行颜色分级和碰伤检测的方法,并针对香梨颜色和轻微碰伤检测的研究内容确定了研究方法。
根据研究内容设计相关实验系统,并对系统的构成和各部件选取进行了分析和优化,概述了实验所用的实验仪器和软件系统。利用机器视觉技术对香梨颜色进行分级的方法进行了研究,找到了对香梨背景分割的方法：利用HSI模式下的H分量作为香梨分割的模板,再进行闽值分割和二值化,得到香梨和背景的分割图,利用该分割图与原香梨图像进行融合,得到去除背景的香梨图像,并对其表面像素和平均值做统计,将统计结果作为人工神经网络的输入,颜色信息作为输出,分别比较了基于BP人工神经网络和RBF人工神经网络的香梨颜色分级,两种方法的分级准确率均为95%。
同时,针对香梨碰伤特点,设计了香梨的碰伤实验装置,对香梨进行人工碰伤。利用机器视觉技术和高光谱图像技术对香梨碰伤进行研究,使用了主成分分析法和独立分量分析法,分别利用主成分分析法和独立分量分析法对获取的高光谱图像数据处理分析,发现香梨第四主成分包含碰伤的主要信息,直接对该主成分进行图像处理和分析,碰伤提取的准确率为81.0%,通过提取特征向量发现其的主要贡献波段分别为528nm,662nm和740nm,利用光谱图像融合技术对主要贡献波段进行融合并处理分析,检测准确率为70.9%。利用独立分量分析可以检测到在第四分量下的香梨碰伤区域,对该分量进行图像处理,提取碰伤区域,检测准确率为82.5%。
最后,归纳了本文的主要结论和有待于进一步研究的内容。
Kurle fragrant pear is one of the most popular fruits in abroad producted by Xinjiang. It's a very important local Economic fruit. Right now, main grading method is by manpower. For a long time working, the works would too busy to keep precision, and everyone would have different result for the same pear. Different standards not only influence the value of fragrant pear, but also influence the quality of fragrant pears and customs' contentment. Some same kind of fruits will have a good price when they have the same color. Color reflects the mature degree of fruits. The bruising of fragrant offen has the same color with normal area, they were easy to neglect. So the color grading and bruising inspection are two important targets of fragrant pears automatic grading. The paper provides a new algorithm of the Kurle fragrant pears' color and bruising non-destructive based on machine vision. The contents of each chapter are described as follows:
A method for color grading and druises detection was introduced. The research status of automated classification and the need for domestic and foreign intelligence testing was analyzed.
According to the study the experimental systems was desined and optimized. The equipment and software system was introduced. The method of pear grading based on machine vision was researched:H component of HSI was used to be the template of image segmentation. The image of pear apart from background was gain after thresholding and binaryzation. The statistics of average and mean square deviation of surface pixels was as the import of ANN, the color information was as the output.The rate of accuracy were both 95% by two methods.
According to the characteristics of pear bruising, the bruising equipment was designed and used to simulate bruise. The machine vision technology and hyperspectral imaging technology were used to detect the slight bruisings of pear. PCA and ICA was used to analysis the dates. PCA4 was found with mainly information of bruising. The rate of accuracy was 81.0% by directly processing PCA 4. The rate of accuracy was 70.9% by processing the image which fused by 528 nm,662 nm and 740 nm. The rate of accuracy was 82.5% by processing ICA 4.
At least part discusses the main achievements and conclusions and some problems for further study.
引文
[1]刘玮.库尔勒香梨研究进展[J].安徽农学通报,2009,15(11)：163-164.
[2]夏光,黄文先,百科ROBOT等.香梨http://baike.baidu.com/view/388865.htm,2010-06-27.
[3]于强.库尔勒香梨产业技术发展报告http://www.xibznv.gov.cn/.2009-8-14.
[4]饶秀勤.基于机器视觉的水果品质实时检测与分级生产线的关键技术研究[D].杭州：浙江大学,2007.
[5]赵茂成,侯文军.我国基于机器视觉技术的水果自动分级技术及研究进展[J].包装与食品机械,2007,(5)：5-8.
[6]齐晓娜.鸭梨品质检测与分级计算机视觉系统的研究[D].保定：河北农业大学,2005.
[7]白菲.基于机器视觉的柑橘水果外形识别方法研究[D].北京：中国农业大学,2005.
[8]白菲,孟超英.水果自动分级技术的现状与发展[J].食品科学,2005,26：145-148.
[9]Zhao Jiewen, Chen Quansheng, Saritporn Vittayapadung, etc. Determination of apple firmness using hyperspectral imaging technique and multivariate calibrations [J].Transactions of the CSAE,2009,25(11):226-231.
[10]Nakano.K. Application of neural networks to the color grading of apples[J]. Computers and Electronics in Agriculture,1997(18):105-116.
[11]V.Leemans, H.Magein,M.-F.Destain,Defects segmentation on'Golden Delicious'apples by colour machine vision[J].Computers and electronics in agriculture 1998,117-130.
[12]Dah-Jye Lee, Color Space Conversion for Linear Color Grading[C],SPIE 2000,358-366.
[13]M.Z.ABDULLAH, L.C.GUAN and B.M.N.MOHD AZEMI, STEPWISE DISCRIMINANT ANALYSIS FOR COLOUR GRADING OF OIL PALM USING MACHINE VISION SYSTEM[J], Institution of Chemical Engineers 2001,223-231.
[14]C.Fernandez, J.Suardiaz, C.Jimenez, etc.On-line Quality control assessment of the production process of presserved orange segments[C],IEEE 2002,2635-2639.
[15]B.S.Bennedsen; D.L,Peterson, Performance of a System for Apple Surface Defect Identification in Near-infrared Images[J],Biosystems Engineering 2005,419-431.
[16]Naoshi Kondo, Usman Ahmad, Mitsuji Monta,Haruhiko Murase, Machine Vision based quality evaluation of Iyokan orange fruit using neural networks[J],Computers and Electronics in Agriculture 2000,135-147.
[17]Kavdir I, LU R, Ariana D, et al. Postharvest Biology and Technology,2007,42(2):165.
[18]Devrim Unay, Bernard Gosselin, Artificial Neural Network-Based Segmentation and Apple Grading by Machine Vision[C], IEEE 2005.
[19]Juan Xing, Cedric Bravo, Pal T Jancsok, et al. Dectecting Bruises on'Golden Delicious' apples using hyperspectral imaging with multiple wavebands [J]. Biosystems Engineering,2005,90(1):27-36.
[20]L.Yang, J.Dickinson, Q.M.J.Wu, S.Lang, A Fruit Recognition Method for Automatic Harvesting[C], IEEE 2000,152-157.
[21]D.J.Lee, James K. Archibald and Christopher G.Greco, Color Quantization and Image Analysis for Automated Fruit Quality Evaluation[C], IEEE 2008,194-199.
[22]Kim M S, Chen Y R, P Mehl M. Hyperspectral reflectance and fluorescence imaging system for food quality and safety [J]. Transactions of the ASAE,2001,44(3):721-729.
[23]Alan M, Lefcout, Moon S. Kim. Technique for normalizing intensity histograms of images when approximate size of the target is know:Detection of feces on apples using fluorescence imaging [J]. Computers and Electronics in Agriculture,2006,50:135-147.
[24]Juan Xing, Josse De Baerdemaeker. Bruise detection on 'Jonagold' apples using hyperspectral imaging [J].Postharvest Biology and Technology,2005,37:152-162.
[25]Lu Renfu, Peng Yankun. Hyperspectral scattering for assessing peach fruit firmness [J]. Biosystems Engineering,2006,93(2):161-171.
[26]Jong-Hyun, Park Ryutaro, Tateishi, et al. Multisensor data fusion using multiresolusion analysis[J]. Holand:ISPRS,2000
[27]Gamal Elmasry, Ning Wang, Adel Elsayed, et al..Hyperspectral imaging for nondestructive determination of some quality attributes for strawberry[J].Food Engineering,2007,81(1):98' 107
[28]Masateru Nagata, Jasper G Tallada, Taiichi Kobayashi,et al. Predicting maturity quality parameters of strawber-ries using hyperspectral imaging [C].Paper Number:043033.2004 ASAE Annual International Meeting,Ontario, Canada,1-4 August,2004.
[29]Masateru Nagata, Jasper G Tallada, Taiichi Kobayashi,et al. NIR hyperspectral imaging for measurement of internal quality in strawberries [C]. Paper Number:053131.2005:ASAE Annual International Meeting,Tampa, Florida,17-20 July,2005.
[30]林妙玲.基于机器视觉的虾体位姿和特征点识别[D].浙江：浙江大学,2007.6.
[31]黎静,刘木华,薛龙.基于高光谱图像技术的大米垩白检测[J].南方农机,2009,1：27-29.
[32]宋亚杰.基于机器视觉的作物水分无损检测及评判模型研究[D].重庆：西南大学,2008.4.
[33]陈坤杰,孙鑫,陆秋琰.基于计算机视觉和神经网络的牛肉颜色自动分级[J].农业机械学报.2009,40(4)：173-178.
[34]成芳,应义斌.基于轮廓特征的稻种芽谷检测方法[J].农业工程学报.2004：20(5)：178-181.
[35]成芳,应义斌.基于颜色特征的稻种霉变检测算法[J].农业机械学报.2004：35(4)：102-105.
[36]应义斌,付峰.水果品质机器视觉检测中的图像颜色变换模型[J].农业机械学报.2004,35(1)：85-89.
[37]赵杰文,刘少鹏,邹小波,等.基于支持向量机的缺陷红枣机器视觉识别[J].农业机械学报.2008,39(3)：113-115.
[38]Ying Yibin, Wang Jianping, Jiang Huanyu. Inspecting Diameter and Defect Area of Fruit With Machine Vision[J]农业工程学报.2002,18(5)：216-220.
[39]李光梅,魏新华,李法德,等.水果机器视觉质量综合分选机的设计[J].农机化研究.2008：124-126.
[40]应义斌,饶秀勤,马俊福.柑橘成熟度机器视觉无损检测方法研究[J].农业工程学报2004,20(2)：144-148.
[41]王津京,赵德安,姬伟,等.基于BP神经网络的苹果图像分割算法[J].农机化研究.2008,11：19-21.
[42]赵金英,张铁中,杨丽.西红柿采摘机器人视觉系统的目标提取[J].农业机械学报.2006,37(10)：200-203.
[43]应义斌,饶秀勤,黄永林,等.运动水果图像的实时采集方法与系统研究[J].农业机械学报.2004,35(3)：179-183.
[44]赵杰文,刘少鹏,邹小波.基于机器视觉和支持向量机的缺陷枣识别研究[A].中国机械学会2006年学术年会论文集[C].1338-1341.
[45]饶秀勤,应义斌.基于机器视觉的水果尺寸检测误差分析[J].农业工程学报.2003,19(1)：141-144.
[46]谭峰,马晓丹.基于神经网络的植物图像分割算法的研究[J].黑龙江八一农垦大学学报,2009,21(1)：63-65.
[47]彭中军,肖新棉,赵会珍.计算机视觉和人工神经网络技术在花生仁外观检测中的应用[J].现代农业装备.2008,3：36-40.
[48]孙莎,洪英,邓继忠,等.计算机视觉在种子品质检测和分级中的应用[J].农机化研究.2008,7：175-178.
[49]张立华.基于计算机视觉的芒果表面缺陷检测方法研究[D].南宁：广西大学2006.6
[50]孙树亮.基于计算机视觉的芒果分类[D].南宁：广西大学.2006.6
[51]侯文军.基于机器视觉的苹果自动分级方法研究[D].南京：南京林业大学.2006
[52]张云鹤,乔晓军,张云辉,等.采用CCD摄像和图像分析技术的作物叶面积测量仪的开发[J].仪器仪表学报,2006,26(4)：345-347.
[53]黄勇平,章程辉,刘静.应用计算机视觉对芒果表面缺陷的判别研究[J].福建热作科技.2008,33(1)：4-6.
[54]李甦,谭永龙,杨美英,等.水果分级与表面缺陷检测研究[J].计算机工程与设计.2008,29(15)：3954-3957.
[55]冯斌,汪懋华.基于颜色分形的水果计算机视觉分级技术[J].农业工程学报.2002,18(2)：141144.
[56]赵茂程,侯文军.基于神经网络的苹果自动分级方法[J].南京林业大学学报：自然科学版.2009,33(2)：136-138.
[57]安爱琴,余泽通,王宏强.基于机器视觉的苹果大小自动分级方法[J].农机化研究.2008,(4)：163-166.
[58]游家训,陈超,郭创新.径向基神经网络在水果颜色分级机中的应用[J].轻工机械.2008,26(3)：24-26.
[59]曹乐平,黄中培,林继元.基于计算机视觉的柑橘糖度检测[J].食品科技.2008,6：186-188.
[60]洪添胜,乔军,Ning Wang,等.基于高光谱图像技术的雪花梨品质无损检测[J].农业工程学报.2007,23(2)：151-155.
[61]赵杰文,刘剑华,陈全胜,等.利用高光谱图像技术检测水果轻微损伤[J].农业机械学报.2008,39(1)：106-109.
[62]郭恩有,刘木华,赵杰文,等.脐橙糖度的高光谱图像无损检测技术[J].农业机械学报.2008,39(5)：91-93.
[63]刘剑华.基于高光谱图像技术苹果轻微损伤检测的研究[D].镇江：江苏大学.2008.6
[64]蔡建荣,王建黑,黄星奕,等.高光谱图像技术检测柑橘果锈[J].光电工程,2009,36(6)：26-30.
[65]石吉勇,邹小波,赵杰文.等基于GA-ICA和高光谱图像技术的黄瓜叶叶绿素检测[J].江苏大学学报(自然科学版).2011,32(2)：134-139
[66]李江波,饶秀琴,应义斌,等.基于高光谱成像技术检测脐橙溃疡[J].农业工程学报.2010,26(8)：222-228.
[67]郑秀莲.基于计算机视觉的柑橘无损检测和分级技术研究[硕D].杭州：浙江工业大学.2004.12
[68]成芳.稻种质量的机器视觉无损检测研究[D].杭州：浙江大学.2004.5
[69]谢锋云.葡萄干颜色分选机的研究[D].长春：长春理工大学.2002.12
[70]章程辉.红毛丹品质的机器视觉检测技术研究[D].北京：中国农业大学.2005.10
[71]曹乐平,何建湖,黄忠培,等.基于计算机视觉的图像采集对水果分级准确率的影响[J].西北农业学报.2008,17(1)：282-285
[72]谢凤英,赵丹培.Visual C++数字图像处理[M].北京：电子工业出版社,2008：284.
[73]尹建军,王新忠,毛罕平,等.RGB于HSI颜色空间下番茄图像分割的对比研究[J].农机化研究.2006,11：171-174.
[74]余成波.数字图像处理及MATLAB实现[M].重庆：重庆大学出版社,2003.
[75]Rafael C. Gonzalez, Richard E. Woods, Steven L.Eddins著,阮秋奇,等译.数字图像处理(MATLAB版)[M].北京：电子工业出版社,2008.
[76]张德丰MATLAB神经网络仿真与应用[M].北京：电子工业出版社,2009.
[77]吴强,王行愚.基于独立分量分析的图像融合算法[J].计算机工程,2007,33(10)：220-224。
[78]王天亮.独立分量分析及其在通信信号处理中的应用[J].企业科技与发展.2009.16：45-47
[79]寻丽娜,方勇华.独立分量分析在高光谱图像舰船检测中的应用[J].计算机仿真.2008.25(9)：196-197.299
[80]黄北京,顾济华,陶智.基于DWT-SVD域的自适应独立分量分析数字图像水印[J].图像处理.2010.26(3-2)：195-196
[81]郑茂,粘永健,郑林华.基于独立分量分析的高光谱图像目标检测算法[J].信号处理.2009.25(12)：1912-1916
[82]苏令华,衣同胜,万建伟.基于独立分量分析的高光谱图像压缩[J].光子学报.2008.37(5).973-976
[2]夏光,黄文先,百科ROBOT等.香梨http://baike.baidu.com/view/388865.htm,2010-06-27.
[3]于强.库尔勒香梨产业技术发展报告http://www.xibznv.gov.cn/.2009-8-14.
[4]饶秀勤.基于机器视觉的水果品质实时检测与分级生产线的关键技术研究[D].杭州：浙江大学,2007.
[5]赵茂成,侯文军.我国基于机器视觉技术的水果自动分级技术及研究进展[J].包装与食品机械,2007,(5)：5-8.
[6]齐晓娜.鸭梨品质检测与分级计算机视觉系统的研究[D].保定：河北农业大学,2005.
[7]白菲.基于机器视觉的柑橘水果外形识别方法研究[D].北京：中国农业大学,2005.
[8]白菲,孟超英.水果自动分级技术的现状与发展[J].食品科学,2005,26：145-148.
[9]Zhao Jiewen, Chen Quansheng, Saritporn Vittayapadung, etc. Determination of apple firmness using hyperspectral imaging technique and multivariate calibrations [J].Transactions of the CSAE,2009,25(11):226-231.
[10]Nakano.K. Application of neural networks to the color grading of apples[J]. Computers and Electronics in Agriculture,1997(18):105-116.
[11]V.Leemans, H.Magein,M.-F.Destain,Defects segmentation on'Golden Delicious'apples by colour machine vision[J].Computers and electronics in agriculture 1998,117-130.
[12]Dah-Jye Lee, Color Space Conversion for Linear Color Grading[C],SPIE 2000,358-366.
[13]M.Z.ABDULLAH, L.C.GUAN and B.M.N.MOHD AZEMI, STEPWISE DISCRIMINANT ANALYSIS FOR COLOUR GRADING OF OIL PALM USING MACHINE VISION SYSTEM[J], Institution of Chemical Engineers 2001,223-231.
[14]C.Fernandez, J.Suardiaz, C.Jimenez, etc.On-line Quality control assessment of the production process of presserved orange segments[C],IEEE 2002,2635-2639.
[15]B.S.Bennedsen; D.L,Peterson, Performance of a System for Apple Surface Defect Identification in Near-infrared Images[J],Biosystems Engineering 2005,419-431.
[16]Naoshi Kondo, Usman Ahmad, Mitsuji Monta,Haruhiko Murase, Machine Vision based quality evaluation of Iyokan orange fruit using neural networks[J],Computers and Electronics in Agriculture 2000,135-147.
[17]Kavdir I, LU R, Ariana D, et al. Postharvest Biology and Technology,2007,42(2):165.
[18]Devrim Unay, Bernard Gosselin, Artificial Neural Network-Based Segmentation and Apple Grading by Machine Vision[C], IEEE 2005.
[19]Juan Xing, Cedric Bravo, Pal T Jancsok, et al. Dectecting Bruises on'Golden Delicious' apples using hyperspectral imaging with multiple wavebands [J]. Biosystems Engineering,2005,90(1):27-36.
[20]L.Yang, J.Dickinson, Q.M.J.Wu, S.Lang, A Fruit Recognition Method for Automatic Harvesting[C], IEEE 2000,152-157.
[21]D.J.Lee, James K. Archibald and Christopher G.Greco, Color Quantization and Image Analysis for Automated Fruit Quality Evaluation[C], IEEE 2008,194-199.
[22]Kim M S, Chen Y R, P Mehl M. Hyperspectral reflectance and fluorescence imaging system for food quality and safety [J]. Transactions of the ASAE,2001,44(3):721-729.
[23]Alan M, Lefcout, Moon S. Kim. Technique for normalizing intensity histograms of images when approximate size of the target is know:Detection of feces on apples using fluorescence imaging [J]. Computers and Electronics in Agriculture,2006,50:135-147.
[24]Juan Xing, Josse De Baerdemaeker. Bruise detection on 'Jonagold' apples using hyperspectral imaging [J].Postharvest Biology and Technology,2005,37:152-162.
[25]Lu Renfu, Peng Yankun. Hyperspectral scattering for assessing peach fruit firmness [J]. Biosystems Engineering,2006,93(2):161-171.
[26]Jong-Hyun, Park Ryutaro, Tateishi, et al. Multisensor data fusion using multiresolusion analysis[J]. Holand:ISPRS,2000
[27]Gamal Elmasry, Ning Wang, Adel Elsayed, et al..Hyperspectral imaging for nondestructive determination of some quality attributes for strawberry[J].Food Engineering,2007,81(1):98' 107
[28]Masateru Nagata, Jasper G Tallada, Taiichi Kobayashi,et al. Predicting maturity quality parameters of strawber-ries using hyperspectral imaging [C].Paper Number:043033.2004 ASAE Annual International Meeting,Ontario, Canada,1-4 August,2004.
[29]Masateru Nagata, Jasper G Tallada, Taiichi Kobayashi,et al. NIR hyperspectral imaging for measurement of internal quality in strawberries [C]. Paper Number:053131.2005:ASAE Annual International Meeting,Tampa, Florida,17-20 July,2005.
[30]林妙玲.基于机器视觉的虾体位姿和特征点识别[D].浙江：浙江大学,2007.6.
[31]黎静,刘木华,薛龙.基于高光谱图像技术的大米垩白检测[J].南方农机,2009,1：27-29.
[32]宋亚杰.基于机器视觉的作物水分无损检测及评判模型研究[D].重庆：西南大学,2008.4.
[33]陈坤杰,孙鑫,陆秋琰.基于计算机视觉和神经网络的牛肉颜色自动分级[J].农业机械学报.2009,40(4)：173-178.
[34]成芳,应义斌.基于轮廓特征的稻种芽谷检测方法[J].农业工程学报.2004：20(5)：178-181.
[35]成芳,应义斌.基于颜色特征的稻种霉变检测算法[J].农业机械学报.2004：35(4)：102-105.
[36]应义斌,付峰.水果品质机器视觉检测中的图像颜色变换模型[J].农业机械学报.2004,35(1)：85-89.
[37]赵杰文,刘少鹏,邹小波,等.基于支持向量机的缺陷红枣机器视觉识别[J].农业机械学报.2008,39(3)：113-115.
[38]Ying Yibin, Wang Jianping, Jiang Huanyu. Inspecting Diameter and Defect Area of Fruit With Machine Vision[J]农业工程学报.2002,18(5)：216-220.
[39]李光梅,魏新华,李法德,等.水果机器视觉质量综合分选机的设计[J].农机化研究.2008：124-126.
[40]应义斌,饶秀勤,马俊福.柑橘成熟度机器视觉无损检测方法研究[J].农业工程学报2004,20(2)：144-148.
[41]王津京,赵德安,姬伟,等.基于BP神经网络的苹果图像分割算法[J].农机化研究.2008,11：19-21.
[42]赵金英,张铁中,杨丽.西红柿采摘机器人视觉系统的目标提取[J].农业机械学报.2006,37(10)：200-203.
[43]应义斌,饶秀勤,黄永林,等.运动水果图像的实时采集方法与系统研究[J].农业机械学报.2004,35(3)：179-183.
[44]赵杰文,刘少鹏,邹小波.基于机器视觉和支持向量机的缺陷枣识别研究[A].中国机械学会2006年学术年会论文集[C].1338-1341.
[45]饶秀勤,应义斌.基于机器视觉的水果尺寸检测误差分析[J].农业工程学报.2003,19(1)：141-144.
[46]谭峰,马晓丹.基于神经网络的植物图像分割算法的研究[J].黑龙江八一农垦大学学报,2009,21(1)：63-65.
[47]彭中军,肖新棉,赵会珍.计算机视觉和人工神经网络技术在花生仁外观检测中的应用[J].现代农业装备.2008,3：36-40.
[48]孙莎,洪英,邓继忠,等.计算机视觉在种子品质检测和分级中的应用[J].农机化研究.2008,7：175-178.
[49]张立华.基于计算机视觉的芒果表面缺陷检测方法研究[D].南宁：广西大学2006.6
[50]孙树亮.基于计算机视觉的芒果分类[D].南宁：广西大学.2006.6
[51]侯文军.基于机器视觉的苹果自动分级方法研究[D].南京：南京林业大学.2006
[52]张云鹤,乔晓军,张云辉,等.采用CCD摄像和图像分析技术的作物叶面积测量仪的开发[J].仪器仪表学报,2006,26(4)：345-347.
[53]黄勇平,章程辉,刘静.应用计算机视觉对芒果表面缺陷的判别研究[J].福建热作科技.2008,33(1)：4-6.
[54]李甦,谭永龙,杨美英,等.水果分级与表面缺陷检测研究[J].计算机工程与设计.2008,29(15)：3954-3957.
[55]冯斌,汪懋华.基于颜色分形的水果计算机视觉分级技术[J].农业工程学报.2002,18(2)：141144.
[56]赵茂程,侯文军.基于神经网络的苹果自动分级方法[J].南京林业大学学报：自然科学版.2009,33(2)：136-138.
[57]安爱琴,余泽通,王宏强.基于机器视觉的苹果大小自动分级方法[J].农机化研究.2008,(4)：163-166.
[58]游家训,陈超,郭创新.径向基神经网络在水果颜色分级机中的应用[J].轻工机械.2008,26(3)：24-26.
[59]曹乐平,黄中培,林继元.基于计算机视觉的柑橘糖度检测[J].食品科技.2008,6：186-188.
[60]洪添胜,乔军,Ning Wang,等.基于高光谱图像技术的雪花梨品质无损检测[J].农业工程学报.2007,23(2)：151-155.
[61]赵杰文,刘剑华,陈全胜,等.利用高光谱图像技术检测水果轻微损伤[J].农业机械学报.2008,39(1)：106-109.
[62]郭恩有,刘木华,赵杰文,等.脐橙糖度的高光谱图像无损检测技术[J].农业机械学报.2008,39(5)：91-93.
[63]刘剑华.基于高光谱图像技术苹果轻微损伤检测的研究[D].镇江：江苏大学.2008.6
[64]蔡建荣,王建黑,黄星奕,等.高光谱图像技术检测柑橘果锈[J].光电工程,2009,36(6)：26-30.
[65]石吉勇,邹小波,赵杰文.等基于GA-ICA和高光谱图像技术的黄瓜叶叶绿素检测[J].江苏大学学报(自然科学版).2011,32(2)：134-139
[66]李江波,饶秀琴,应义斌,等.基于高光谱成像技术检测脐橙溃疡[J].农业工程学报.2010,26(8)：222-228.
[67]郑秀莲.基于计算机视觉的柑橘无损检测和分级技术研究[硕D].杭州：浙江工业大学.2004.12
[68]成芳.稻种质量的机器视觉无损检测研究[D].杭州：浙江大学.2004.5
[69]谢锋云.葡萄干颜色分选机的研究[D].长春：长春理工大学.2002.12
[70]章程辉.红毛丹品质的机器视觉检测技术研究[D].北京：中国农业大学.2005.10
[71]曹乐平,何建湖,黄忠培,等.基于计算机视觉的图像采集对水果分级准确率的影响[J].西北农业学报.2008,17(1)：282-285
[72]谢凤英,赵丹培.Visual C++数字图像处理[M].北京：电子工业出版社,2008：284.
[73]尹建军,王新忠,毛罕平,等.RGB于HSI颜色空间下番茄图像分割的对比研究[J].农机化研究.2006,11：171-174.
[74]余成波.数字图像处理及MATLAB实现[M].重庆：重庆大学出版社,2003.
[75]Rafael C. Gonzalez, Richard E. Woods, Steven L.Eddins著,阮秋奇,等译.数字图像处理(MATLAB版)[M].北京：电子工业出版社,2008.
[76]张德丰MATLAB神经网络仿真与应用[M].北京：电子工业出版社,2009.
[77]吴强,王行愚.基于独立分量分析的图像融合算法[J].计算机工程,2007,33(10)：220-224。
[78]王天亮.独立分量分析及其在通信信号处理中的应用[J].企业科技与发展.2009.16：45-47
[79]寻丽娜,方勇华.独立分量分析在高光谱图像舰船检测中的应用[J].计算机仿真.2008.25(9)：196-197.299
[80]黄北京,顾济华,陶智.基于DWT-SVD域的自适应独立分量分析数字图像水印[J].图像处理.2010.26(3-2)：195-196
[81]郑茂,粘永健,郑林华.基于独立分量分析的高光谱图像目标检测算法[J].信号处理.2009.25(12)：1912-1916
[82]苏令华,衣同胜,万建伟.基于独立分量分析的高光谱图像压缩[J].光子学报.2008.37(5).973-976