基于机器视觉的玉米品质检测
|
摘要
机器视觉技术是模拟视觉功能来实现无损检测，利用被测物的图像信息探测目标属性。该技术在谷物无损检测中具有客观、高效、准确的特点，因此其理论研究及应用受到了广泛的关注。特别是随着生活质量的改善，无论是玉米用于食用、工业加工还是作为种子进行农业再生产，人们对品质要求都越来越高，因此采用有效的无损检测技术来保证其品质就显得很有必要。
本文在理论研究和实验分析的基础上，深入研究了玉米品质自动检测的方法，构建了玉米籽粒实时分析系统。围绕如何根据单粒玉米的检测特点，实现多籽粒玉米图像的分割、信息提取及品质识别进行了以下工作：(1)基于图像采集系统，记录平铺的玉米籽粒图像来获取玉米单籽粒的信息，并将图像经过预处理操作，使图像信息增强便于运算。随后研究了主动轮廓模型和分水岭两种不同处理方法，从图像的分割速率和效果上看，分水岭算法更能满足实际应用的要求。在此基础上，本文通过变阈值法来改进分水岭算法，达到逐次分割的目的，提高了图像分割效率，同时维护了图像中单籽粒玉米的外形特征；(2)跟踪单籽粒标记区域，从形状、颜色、纹理等信息中提取能够描述其外观的37个有效特征。但是从识别用途上看，许多不同的特征具有很大的关联性，在进行模式识别时会造成数据冗余的现象。针对这一问题，本文分别采用遗传算法和主分量分析对特征数据进行处理，选择有效的分类特征作为模式识别的输入参数，并对比了两种方法的优缺点。实验结果表明，遗传算法适用范围大，能获得单个特征量的重要性，而主分量分析的方法需要压缩所有数据，直观性不强；(3)探讨了BP神经网络和支持向量机两种不同的模式识别方法，并通过实验对两种方法的识别效率与精确度进行了比较分析。实验表明，BP神经网络更适合于缺陷粒的分类，当优化特征组合方法与神经网络方法结合应用时，网络的误差曲线迅速收敛，获得了很好的分类精度。同时通过质量与图像检测玉米籽粒面积的关系来计算千粒重，并比较了计算与实际千粒重值的偏差。结果表明，可以采用该方法获取千粒重来评价玉米籽粒的品质。
最后，基于Matlab软件平台实现前面叙述的图像处理功能，并在Labview软件平台中调用了Matlab Script节点，实现两个软件的间的程序调用，借助Labview平台开发良好的用户界面，建立了玉米籽粒分析系统。之后，通过样品测试实验，验证了该系统在检测中的准确性并提出进一步的改进措施。
本文的工作可实现无损检测，获得客观、快速、准确的籽粒品质分析，对机器视觉技术应用于玉米品质检测具有一定的指导作用。
Machine vision technology is used to simulate visual function to achievenondestructive testing, through acquiring and processing images of object to be measuredto get properties of the target. Machine vision technology applied in cereal’snon-destructive testing have the significant characteristics of non-subjective, high-speed,and high-precision of detection, so the theoretical research and application of thetechnology have obtained extensive attention. Especially, with the improvement of thequality of people’s life, whether the corn used for edibility, industrial processing or asseeds for agricultural reproduction, the corn quality are highly demanded more and more.In order to ensure the quality of the corn, it is necessary to adopt effectivelynon-destructive testing techniques.
Based on theoretical research and experimental analysis, this article presented athorough study of the automatic detection method of the corn quality and the system ofreal-time analysis of the maize was established. According to test the characteristics ofsingle kernel corn, an approach for inspection of touching corn kernels was developed torealize image segmentation, information extraction and quality evaluation. The maincontents are as follows:(1) Relying on the image acquisition system, the tile corn imageswere collected, so that the information of a single kernel was obtained. After pretreatedoperation of image enhancement, the images were more suitable for calculation.Subsequently, two different methods of image processing including active contour modeland watershed were comparatively studied. Computation speed and segmentation resultsshowed that the watershed algorithm was more suitable for actual application. Then, inorder to achieve successive segmentation and improve the efficiency of imagesegmentation, the alterable threshold method was used to improve the watershed algorithm.At the same time, the improved algorithm preserved the shape of a single grain image.(2) Single grain region was tracked and marked,37feature parameters including shape, colorand texture were extracted to describe the appearance. There was a great connectionbetween the features during pattern recognition which would result in data redundancy. Inorder to avoid this situation, this article adopted genetic algorithms and principalcomponent analysis to deal with the feature data for selecting valid classification featuresas input parameters for pattern recognition algorithm and then compared the advantagesand disadvantages of the two methods. The results showed that genetic algorithms had alarge scope of application and could acquire the importance of individual feature parameter;however, principal component analysis required all data compression and appearedunintuitive.(3) This paper discussed two pattern recognition methods based on SVM modeland BP neural network model and compared the efficiency and precision of the twomethods by actual experiment. The experiment results illustrated that BP neural networkwas more suitable for the identification of defective particles. When optimization algorithmof features and neural network combined, the recognition network had a better convergenceand high identifying accuracy was found. Meanwhile, the thousand-seed weight wascalculated according to the function between corn weight and detected area, the values ofcalculation and actual measurement were compared. The experimental results demonstratedthis method could be used to predict thousand-seed weight for evaluating corn quality.
Eventually, this article realized image processing function described above based onMatlab software and a decision system based on Labview was built to develop a good userinterface and the communication of these softwares was achieved by calling Matlab Scriptnode. Then, the accuracy of the built system in detection of corn quality was verifiedthrough sample experiment and proposed some improved measures
The work in this article can realize objective, rapid and accurate analysis of cornquality and offer some leading effect on applying machine vision technology to detectionof maize quality.
本文在理论研究和实验分析的基础上，深入研究了玉米品质自动检测的方法，构建了玉米籽粒实时分析系统。围绕如何根据单粒玉米的检测特点，实现多籽粒玉米图像的分割、信息提取及品质识别进行了以下工作：(1)基于图像采集系统，记录平铺的玉米籽粒图像来获取玉米单籽粒的信息，并将图像经过预处理操作，使图像信息增强便于运算。随后研究了主动轮廓模型和分水岭两种不同处理方法，从图像的分割速率和效果上看，分水岭算法更能满足实际应用的要求。在此基础上，本文通过变阈值法来改进分水岭算法，达到逐次分割的目的，提高了图像分割效率，同时维护了图像中单籽粒玉米的外形特征；(2)跟踪单籽粒标记区域，从形状、颜色、纹理等信息中提取能够描述其外观的37个有效特征。但是从识别用途上看，许多不同的特征具有很大的关联性，在进行模式识别时会造成数据冗余的现象。针对这一问题，本文分别采用遗传算法和主分量分析对特征数据进行处理，选择有效的分类特征作为模式识别的输入参数，并对比了两种方法的优缺点。实验结果表明，遗传算法适用范围大，能获得单个特征量的重要性，而主分量分析的方法需要压缩所有数据，直观性不强；(3)探讨了BP神经网络和支持向量机两种不同的模式识别方法，并通过实验对两种方法的识别效率与精确度进行了比较分析。实验表明，BP神经网络更适合于缺陷粒的分类，当优化特征组合方法与神经网络方法结合应用时，网络的误差曲线迅速收敛，获得了很好的分类精度。同时通过质量与图像检测玉米籽粒面积的关系来计算千粒重，并比较了计算与实际千粒重值的偏差。结果表明，可以采用该方法获取千粒重来评价玉米籽粒的品质。
最后，基于Matlab软件平台实现前面叙述的图像处理功能，并在Labview软件平台中调用了Matlab Script节点，实现两个软件的间的程序调用，借助Labview平台开发良好的用户界面，建立了玉米籽粒分析系统。之后，通过样品测试实验，验证了该系统在检测中的准确性并提出进一步的改进措施。
本文的工作可实现无损检测，获得客观、快速、准确的籽粒品质分析，对机器视觉技术应用于玉米品质检测具有一定的指导作用。
Machine vision technology is used to simulate visual function to achievenondestructive testing, through acquiring and processing images of object to be measuredto get properties of the target. Machine vision technology applied in cereal’snon-destructive testing have the significant characteristics of non-subjective, high-speed,and high-precision of detection, so the theoretical research and application of thetechnology have obtained extensive attention. Especially, with the improvement of thequality of people’s life, whether the corn used for edibility, industrial processing or asseeds for agricultural reproduction, the corn quality are highly demanded more and more.In order to ensure the quality of the corn, it is necessary to adopt effectivelynon-destructive testing techniques.
Based on theoretical research and experimental analysis, this article presented athorough study of the automatic detection method of the corn quality and the system ofreal-time analysis of the maize was established. According to test the characteristics ofsingle kernel corn, an approach for inspection of touching corn kernels was developed torealize image segmentation, information extraction and quality evaluation. The maincontents are as follows:(1) Relying on the image acquisition system, the tile corn imageswere collected, so that the information of a single kernel was obtained. After pretreatedoperation of image enhancement, the images were more suitable for calculation.Subsequently, two different methods of image processing including active contour modeland watershed were comparatively studied. Computation speed and segmentation resultsshowed that the watershed algorithm was more suitable for actual application. Then, inorder to achieve successive segmentation and improve the efficiency of imagesegmentation, the alterable threshold method was used to improve the watershed algorithm.At the same time, the improved algorithm preserved the shape of a single grain image.(2) Single grain region was tracked and marked,37feature parameters including shape, colorand texture were extracted to describe the appearance. There was a great connectionbetween the features during pattern recognition which would result in data redundancy. Inorder to avoid this situation, this article adopted genetic algorithms and principalcomponent analysis to deal with the feature data for selecting valid classification featuresas input parameters for pattern recognition algorithm and then compared the advantagesand disadvantages of the two methods. The results showed that genetic algorithms had alarge scope of application and could acquire the importance of individual feature parameter;however, principal component analysis required all data compression and appearedunintuitive.(3) This paper discussed two pattern recognition methods based on SVM modeland BP neural network model and compared the efficiency and precision of the twomethods by actual experiment. The experiment results illustrated that BP neural networkwas more suitable for the identification of defective particles. When optimization algorithmof features and neural network combined, the recognition network had a better convergenceand high identifying accuracy was found. Meanwhile, the thousand-seed weight wascalculated according to the function between corn weight and detected area, the values ofcalculation and actual measurement were compared. The experimental results demonstratedthis method could be used to predict thousand-seed weight for evaluating corn quality.
Eventually, this article realized image processing function described above based onMatlab software and a decision system based on Labview was built to develop a good userinterface and the communication of these softwares was achieved by calling Matlab Scriptnode. Then, the accuracy of the built system in detection of corn quality was verifiedthrough sample experiment and proposed some improved measures
The work in this article can realize objective, rapid and accurate analysis of cornquality and offer some leading effect on applying machine vision technology to detectionof maize quality.
引文
[1]应义斌，于海燕.农产品品质无损检测技术研究进展[C].中国农业工程学会2005学术年会论文集，2005,70-80.
[2] Zayas I, Y Pomeranz, and F S Lai. Discrimination between Arthur and Arkan wheatsby image analysis [J]. Cereal Chemistry,1985,62:478.
[3] M Neuman, H D Sapirstein, E Shwedyk, W Bushuk. Discrimination of wheat class andvariety by digital image analysis of whole grain samples [J]. Journal of Cereal Science,1987,6:125-132.
[4] Gunasekaran S, Cooper T M, Berlage A G Evaluating quality factors of corn andsoybean using a computer vision system [J]. Trans of ASAE,1988a,31(4):1264-1271.
[5] T McDonald, Y R Chen. Application of morphological image processing in agriculture[J]. Transactions of the ASABE,1990,33(4):1346-1352.
[6] Zayas I, H Converse, J L Steele. Discrimination of whole from broken corn kemelswith image analysis [J]. Trans of the ASAE,1990,33(5):1642-1646.
[7] K Liao, M R Paulsen, J F Reid, B Ni and E Bonifacio. Corn kernel shape identificationby machine vision using a neural network classifier [J]. Trans of the ASAE,1992,6992-7017.
[8] N Zhang, C Chaisattapagon. Effective criteria for weed identification in wheat fieldsusing machine vision [J], Trans of the ASAE,1995,38(3):965-974.
[9] Zayas, I., Martin, C.R., Steele, J L Katsevich, A.,1996.Wheat classification usingimage analysis and crush-force parameters. Trans of ASAE,39:2199-2204.
[10]B Ni, M R Paulsen, J F Reid. Size grading of corn kernels with machine vision [J].Trans of the ASAE,1998,14(5):567-571.
[11]Zayas I Y, Flinn P W. Detection of insects in bulk wheat samples with machine vision[J]. Trans of the ASAE,1998,41(3):883-888.
[12]Siriluk Sansomboonsuk, Nitin Afzulpurkar. Machine vision for rice quality evaluation
[C]. Technology and Innovation for sustainable development conference,2008,343-346.
[13]W Medina, O Skurtys, J M Aguilera. Study on image analysis application foridentification Quinoa seeds (Chenopodium quinoa Willd) geographical provenance [J].Food Science and Technology,2010,43:238-246.
[14]Piotr Zapotoczny. Discrimination of wheat grain varieties using image analysis andneural networks. Part I. Single kernel texture [J]. Journal of Cereal Science,2011,54:60-80.
[15]Wan Y N, Lin C M, Chiou J F., Adaptive classification method for an automatic grainquality inspection system using machine vision and neural network [C]. ASAE AnnualInternational Meeting,2000,9085-9659.
[16]Wan Y N, Automatic grain quality inspection with learning mechanism [C].Proceedings of the Third Asian Conference for Information Technology in Agricultural,2002,445-449.
[17]G Dalen. Determination of the size distribution and percentage of broken kernels ofrice using flatbed scanning and image analysis [J]. Food Research International,2003,37:51-58.
[18]Kivanc Kilic, Ismail Hakki Boyaci, K Hamit. A classification system for beans usingcomputer vision system and artificial neural networks [J]. Journal of Food Engineering,2007,78:897-904.
[19]刘绍刚，吴守一，高良润.农产品品质的光特性无损检测[J].江苏工学院学报，1991,12(1):1-8.
[20]刘绍刚，吴守一，方如明等.计算机控制的农产品光特性检测系统[J].农业工程学报，1992,8(3):97-103.
[21]方如明.计算机图像处理与米的品质检测[J].农业工程学报，1992,8(3):104-112.
[22]宋韬.应用计算机视觉进行作物籽粒形状识别的研究[D].1995.博士学位论文.北京:北京农业工程大学.
[23]王丰元，周一鸣.种子形状参数检测的计算机图像技术[J].农业机械学报，1995,26(2):52-57
[24]刘禾，汪懋华.用计算机图像技术进行苹果坏损自动检测的研究[J].农业机械学报，1998,(04):81-86.
[25]张书慧，陈晓光，张晓梅，谭台哲.苹果、桃等农副产品品质检测与分级图像处理系统的研究[J].农业工程学报，1999,15(1):201-204.
[26]潘伟.计算机视觉在农产品自动检测与分级中的研究——番茄的自动检测与分级
[D].2000.硕士学位论文.东北农业大学.
[27]周水琴，应义斌.颜色模型在农产品颜色检测与分级中的应用[J].浙江大学学报，2003,29(6):684-688.
[28]闸建文，陈永艳.基于外部特征的玉米品种计算机识别系统[J].农业机械学报，2004,35(6):115-118.
[29]凌云.基于机器视觉的谷物外观品质检测技术研究[D].2004.博士学位论文.北京：中国农业大学.
[30]成芳，应义斌.基于Matlab平台的稻种图像分析系统[J].浙江大学学报，2004,30(5):572-576.
[31]成芳.稻种质量的机器视觉无损检测研究[D].2004.博士学位论文.浙江：浙江大学.
[32]周佳璐.基于机器视觉的小麦质量判别系统的研究[D].2006.硕士学位论文.上海：同济大学.
[33]刘中合.基于计算机视觉的玉米种子特征提取及应用研究[D].2007.硕士学位论文.山东农业大学.
[34]孙亮.谷物图像的快速特征提取及分选算法研究[D].2007.硕士学位论文.天津科技大学.
[35]王瑶.种子分类与检验的图像分割与识别[D].2007.硕士学位论文.长春：吉林大学.
[36]王玉亮.基于机器视觉的玉米种子品种识别与检测研究[D].2008.硕士学位论文.山东农业大学.
[37]郑敏江.基于数字图像处理的玉米种子质量分级方法研究[D].2009,硕士学位论文,武汉理工大学.
[38]宋鹏，张俊雄，荀一，陈晓，李伟.玉米种子自动精选系统开发[J].农业工程学报，2010,26(9):124-127.
[39]赵春燕，闫长青等.图像分割综述[J].中国科技信息.2009,1:42-43.
[40]韩思奇，王蕾.图像分割的阈值法综述[J].系统工程与电子技术.2002,24(6):91-94.
[41]杨家红，刘杰等.结合分水岭与自动种子区域生长的彩色图像分割算法[J].中国图象图形学报.2010,1(15):63-68.
[42]徐建东，蒋野等.基于改进的形态学算子的灰度图像边缘检测[J].佳木斯大学学报.2009,6(27):857-859.
[43]王玉涛，苑玮琦等.基于神经网络的颗粒图像边缘混合检测方法[J].控制与决策.1999,3(14):234-239.
[44]周鲜成，申群太.基于微粒群和最大模糊熵的图像分割[J].计算机仿真.2008,4(25):221-223.
[45]秦斌，左欣.基于小波变换的颗粒图像边缘检测算法研究[J].福建电脑,2009,9:88-89.
[46]巫小蓉，吴效明.基于小波变换和高斯差分冷冻电镜生物大分子图像的自动分割[J].中国组织工程研究与临床康复.2009,48(13):9479-9482.
[47]杨蜀秦，宁纪锋，何东健.一种基于主动轮廓模型的连接米粒图像分割算法[J].农业工程学报.2010,2(26):207-211.
[48]韩峰.一种自适应分水岭数字图像分割技术[D].2007.硕士学位论文.湖南大学.
[49]韩仲志，赵友刚.基于计算机视觉的花生品质分级检测研究.中国农业科学，2010,43(18):3882-3891.
[50]Mehmed Kantardzic. Data Mining Concepts, Models, Methods, and Algorithms [M].IEEE Press.2002.
[51]岳田利，彭帮柱，袁亚宏等.基于主成分分析法的苹果酒香气质量评价模型的构建[J].农业工程学报，2007,23(6):223-227.
[52]曾洁，孙俊良，李光磊等.基于主成分分析和Q型聚类分析的玉米品种特性研究[J].沈阳农业大学学报，2009,40(1):53-57.
[53]熊凯，李向红，李言照等.基于ANN和PCA的玉米品种特征分析与识别研究[J].粮油食品科技，2010,18(4):1-5.
[54]Jack L B, Nandi A K.. Feature selection for ANNs using genetic algorithms incondition monitoring [C]. ESANN’1999Proceeding European Symposium onArtificial Neural Networks.1999:313-318.
[55]郑宇.基于机器视觉的稻谷种子特征提取与品种识别方法研究[D].2009.华中农业大学硕士学位论文.
[56]郝建平，杨锦忠，杜天庆等.基于图像处理的玉米品种的种子形态分析及其分类研究[J].中国农业科学，2008,41(4):994-1002.
[57]石礼娟，文友先等.谷物检测中机器视觉技术应用进展[J].湖北农业科学.2009,6(48):1514-1518.
[58]闸建文，陈永艳.基于外部特征的玉米品种计算机识别系统[J].农业机械学报，2004,35(6):115-118.
[59]G.Van Dalen. Determination of the size distribution and percentage of broken kernelsof rice using flatted scanning and image analysis [J]. Food Research International.2004,37:51-58.
[60]时玉强.基于机器视觉的大豆品质的研究[D].2009.东北农业大学硕士学位论文.
[61]宋凡峰.基于Labview与Matlab的现代光测图像处理系统[D].南京航空航天大学.2007.
[62]马永强，华宇宁.基于Labview/Matlab的人脸识别系统设计与实现[J].工业技术-科技资讯.2007,06:15-16.
[63]成芳，刘兆燕，应义斌.谷物视觉检测系统的硬件环境[J].中国食品学报.2005,5(3):80-85.
[64]Kass M, Witkin A, Terzopoulos D. Snake: active contour models [J]. InternationalJournal of Computer Vision,1987,1(4):321－331.
[65]于殿泓.图像检测与处理技术[M]，2006.西安：西安电子科技大学出版社.
[66]Hu M K. Visual pattern recognition by moment invariants [J], IEEE Transactions onInformation Theory,1962,8(1):179-187.
[67]姚敏.数字图像处理[M]，2006.北京：机械工业出版社.
[68]陈果，邓堰.遗传算法特征选取中的几种适应度函数构造新方法及其应用[J].机械科学与技术.2011,30(1):124-132.
[2] Zayas I, Y Pomeranz, and F S Lai. Discrimination between Arthur and Arkan wheatsby image analysis [J]. Cereal Chemistry,1985,62:478.
[3] M Neuman, H D Sapirstein, E Shwedyk, W Bushuk. Discrimination of wheat class andvariety by digital image analysis of whole grain samples [J]. Journal of Cereal Science,1987,6:125-132.
[4] Gunasekaran S, Cooper T M, Berlage A G Evaluating quality factors of corn andsoybean using a computer vision system [J]. Trans of ASAE,1988a,31(4):1264-1271.
[5] T McDonald, Y R Chen. Application of morphological image processing in agriculture[J]. Transactions of the ASABE,1990,33(4):1346-1352.
[6] Zayas I, H Converse, J L Steele. Discrimination of whole from broken corn kemelswith image analysis [J]. Trans of the ASAE,1990,33(5):1642-1646.
[7] K Liao, M R Paulsen, J F Reid, B Ni and E Bonifacio. Corn kernel shape identificationby machine vision using a neural network classifier [J]. Trans of the ASAE,1992,6992-7017.
[8] N Zhang, C Chaisattapagon. Effective criteria for weed identification in wheat fieldsusing machine vision [J], Trans of the ASAE,1995,38(3):965-974.
[9] Zayas, I., Martin, C.R., Steele, J L Katsevich, A.,1996.Wheat classification usingimage analysis and crush-force parameters. Trans of ASAE,39:2199-2204.
[10]B Ni, M R Paulsen, J F Reid. Size grading of corn kernels with machine vision [J].Trans of the ASAE,1998,14(5):567-571.
[11]Zayas I Y, Flinn P W. Detection of insects in bulk wheat samples with machine vision[J]. Trans of the ASAE,1998,41(3):883-888.
[12]Siriluk Sansomboonsuk, Nitin Afzulpurkar. Machine vision for rice quality evaluation
[C]. Technology and Innovation for sustainable development conference,2008,343-346.
[13]W Medina, O Skurtys, J M Aguilera. Study on image analysis application foridentification Quinoa seeds (Chenopodium quinoa Willd) geographical provenance [J].Food Science and Technology,2010,43:238-246.
[14]Piotr Zapotoczny. Discrimination of wheat grain varieties using image analysis andneural networks. Part I. Single kernel texture [J]. Journal of Cereal Science,2011,54:60-80.
[15]Wan Y N, Lin C M, Chiou J F., Adaptive classification method for an automatic grainquality inspection system using machine vision and neural network [C]. ASAE AnnualInternational Meeting,2000,9085-9659.
[16]Wan Y N, Automatic grain quality inspection with learning mechanism [C].Proceedings of the Third Asian Conference for Information Technology in Agricultural,2002,445-449.
[17]G Dalen. Determination of the size distribution and percentage of broken kernels ofrice using flatbed scanning and image analysis [J]. Food Research International,2003,37:51-58.
[18]Kivanc Kilic, Ismail Hakki Boyaci, K Hamit. A classification system for beans usingcomputer vision system and artificial neural networks [J]. Journal of Food Engineering,2007,78:897-904.
[19]刘绍刚，吴守一，高良润.农产品品质的光特性无损检测[J].江苏工学院学报，1991,12(1):1-8.
[20]刘绍刚，吴守一，方如明等.计算机控制的农产品光特性检测系统[J].农业工程学报，1992,8(3):97-103.
[21]方如明.计算机图像处理与米的品质检测[J].农业工程学报，1992,8(3):104-112.
[22]宋韬.应用计算机视觉进行作物籽粒形状识别的研究[D].1995.博士学位论文.北京:北京农业工程大学.
[23]王丰元，周一鸣.种子形状参数检测的计算机图像技术[J].农业机械学报，1995,26(2):52-57
[24]刘禾，汪懋华.用计算机图像技术进行苹果坏损自动检测的研究[J].农业机械学报，1998,(04):81-86.
[25]张书慧，陈晓光，张晓梅，谭台哲.苹果、桃等农副产品品质检测与分级图像处理系统的研究[J].农业工程学报，1999,15(1):201-204.
[26]潘伟.计算机视觉在农产品自动检测与分级中的研究——番茄的自动检测与分级
[D].2000.硕士学位论文.东北农业大学.
[27]周水琴，应义斌.颜色模型在农产品颜色检测与分级中的应用[J].浙江大学学报，2003,29(6):684-688.
[28]闸建文，陈永艳.基于外部特征的玉米品种计算机识别系统[J].农业机械学报，2004,35(6):115-118.
[29]凌云.基于机器视觉的谷物外观品质检测技术研究[D].2004.博士学位论文.北京：中国农业大学.
[30]成芳，应义斌.基于Matlab平台的稻种图像分析系统[J].浙江大学学报，2004,30(5):572-576.
[31]成芳.稻种质量的机器视觉无损检测研究[D].2004.博士学位论文.浙江：浙江大学.
[32]周佳璐.基于机器视觉的小麦质量判别系统的研究[D].2006.硕士学位论文.上海：同济大学.
[33]刘中合.基于计算机视觉的玉米种子特征提取及应用研究[D].2007.硕士学位论文.山东农业大学.
[34]孙亮.谷物图像的快速特征提取及分选算法研究[D].2007.硕士学位论文.天津科技大学.
[35]王瑶.种子分类与检验的图像分割与识别[D].2007.硕士学位论文.长春：吉林大学.
[36]王玉亮.基于机器视觉的玉米种子品种识别与检测研究[D].2008.硕士学位论文.山东农业大学.
[37]郑敏江.基于数字图像处理的玉米种子质量分级方法研究[D].2009,硕士学位论文,武汉理工大学.
[38]宋鹏，张俊雄，荀一，陈晓，李伟.玉米种子自动精选系统开发[J].农业工程学报，2010,26(9):124-127.
[39]赵春燕，闫长青等.图像分割综述[J].中国科技信息.2009,1:42-43.
[40]韩思奇，王蕾.图像分割的阈值法综述[J].系统工程与电子技术.2002,24(6):91-94.
[41]杨家红，刘杰等.结合分水岭与自动种子区域生长的彩色图像分割算法[J].中国图象图形学报.2010,1(15):63-68.
[42]徐建东，蒋野等.基于改进的形态学算子的灰度图像边缘检测[J].佳木斯大学学报.2009,6(27):857-859.
[43]王玉涛，苑玮琦等.基于神经网络的颗粒图像边缘混合检测方法[J].控制与决策.1999,3(14):234-239.
[44]周鲜成，申群太.基于微粒群和最大模糊熵的图像分割[J].计算机仿真.2008,4(25):221-223.
[45]秦斌，左欣.基于小波变换的颗粒图像边缘检测算法研究[J].福建电脑,2009,9:88-89.
[46]巫小蓉，吴效明.基于小波变换和高斯差分冷冻电镜生物大分子图像的自动分割[J].中国组织工程研究与临床康复.2009,48(13):9479-9482.
[47]杨蜀秦，宁纪锋，何东健.一种基于主动轮廓模型的连接米粒图像分割算法[J].农业工程学报.2010,2(26):207-211.
[48]韩峰.一种自适应分水岭数字图像分割技术[D].2007.硕士学位论文.湖南大学.
[49]韩仲志，赵友刚.基于计算机视觉的花生品质分级检测研究.中国农业科学，2010,43(18):3882-3891.
[50]Mehmed Kantardzic. Data Mining Concepts, Models, Methods, and Algorithms [M].IEEE Press.2002.
[51]岳田利，彭帮柱，袁亚宏等.基于主成分分析法的苹果酒香气质量评价模型的构建[J].农业工程学报，2007,23(6):223-227.
[52]曾洁，孙俊良，李光磊等.基于主成分分析和Q型聚类分析的玉米品种特性研究[J].沈阳农业大学学报，2009,40(1):53-57.
[53]熊凯，李向红，李言照等.基于ANN和PCA的玉米品种特征分析与识别研究[J].粮油食品科技，2010,18(4):1-5.
[54]Jack L B, Nandi A K.. Feature selection for ANNs using genetic algorithms incondition monitoring [C]. ESANN’1999Proceeding European Symposium onArtificial Neural Networks.1999:313-318.
[55]郑宇.基于机器视觉的稻谷种子特征提取与品种识别方法研究[D].2009.华中农业大学硕士学位论文.
[56]郝建平，杨锦忠，杜天庆等.基于图像处理的玉米品种的种子形态分析及其分类研究[J].中国农业科学，2008,41(4):994-1002.
[57]石礼娟，文友先等.谷物检测中机器视觉技术应用进展[J].湖北农业科学.2009,6(48):1514-1518.
[58]闸建文，陈永艳.基于外部特征的玉米品种计算机识别系统[J].农业机械学报，2004,35(6):115-118.
[59]G.Van Dalen. Determination of the size distribution and percentage of broken kernelsof rice using flatted scanning and image analysis [J]. Food Research International.2004,37:51-58.
[60]时玉强.基于机器视觉的大豆品质的研究[D].2009.东北农业大学硕士学位论文.
[61]宋凡峰.基于Labview与Matlab的现代光测图像处理系统[D].南京航空航天大学.2007.
[62]马永强，华宇宁.基于Labview/Matlab的人脸识别系统设计与实现[J].工业技术-科技资讯.2007,06:15-16.
[63]成芳，刘兆燕，应义斌.谷物视觉检测系统的硬件环境[J].中国食品学报.2005,5(3):80-85.
[64]Kass M, Witkin A, Terzopoulos D. Snake: active contour models [J]. InternationalJournal of Computer Vision,1987,1(4):321－331.
[65]于殿泓.图像检测与处理技术[M]，2006.西安：西安电子科技大学出版社.
[66]Hu M K. Visual pattern recognition by moment invariants [J], IEEE Transactions onInformation Theory,1962,8(1):179-187.
[67]姚敏.数字图像处理[M]，2006.北京：机械工业出版社.
[68]陈果，邓堰.遗传算法特征选取中的几种适应度函数构造新方法及其应用[J].机械科学与技术.2011,30(1):124-132.
© 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 |