基于FNN的非线性形变植物叶片病斑识别与特征计算技术研究
|
摘要
本文对植物叶片非线性形变的病害图像的病斑识别与特征计算技术进行研究,利用图像处理、神经网络及植物病理学知识相融合,实现了对非线性失真的植物叶片的数字图像进行校正,病害区域识别,病斑区域特征的提取和计算。
针对植物叶片图像的非线性失真形式,提出双线性映射方程来恢复失真图像原来的空间关系,利用最近邻插值法进行图像的灰度插值,完成对失真图像的校正。利用植物病斑区域识别分割的技术,提出了在输出层采用线性清晰化方式的五层的模糊神经网络模糊推理系统。采用梯度下降的误差反向传播法进行参数辨识,针对BP算法学习收敛速度慢且易陷入局部极小的不足,提出一种遗传算法和梯度下降的误差反向传播法相融合技术的学习算法,充分利用了遗传算法的全局搜索最优性和梯度下降的误差反向传播局部搜索最优性有机结合一种较优秀的网络学习算法。依据植物病害智能诊断的条件因素,利用图像平滑技术的滤波方法对病斑图像完成预处理后,能够实现对几何、颜色、纹理诊断依据的特征提取和计算。针对其特征矢量处于特征空间,提出隐含层的量子神经元为反正切函数的三层量子神经网络的植物病害诊断模型,样本数据中的不确定性在给定梯度下降学习算法的训练过程中被自适应的确定。本研究的植物病害无损智能诊断关键技术在马铃薯早疫病的诊断中取得了显著效果。
This paper studies the crucial technologies about intellectual diagnosis of diseases of plants and realizes correction of digital images, recognition of diseased area, the extraction and calculation of diseased area’s features,according to image processing, neural net and plant pathology.
Considering the nonlinear distortion of images of leaves, bilinear map equation is proposed to restore distorted images by utilizing interpolation, so that the correction of distorted images is obtained. Meanwhile, the five-layer fuzzy inference system is given in output layer by the partition of diseased area. Because BP algorithm has a slow convergence and usually is trapped into the local minimum, a new algorithm is proposed, which is a more excellent one that is combining two algorithms: genetic algorithm and BP. The extraction and calculation of features in geometry, color and texture are achieved after the pre-processing of the image with scabs by utilizing smoothing technique according to the factors of intellectual diagnosis for diseased plants. Besides these above, a model is designed that is a three-layer quantum neural network model, whose hidden layer is arctangent function. By the improved model, uncertainty of sample data can be determined during the training process in the given gradient descent algorithm. The results of stimulation indicate that the crucial technology proposed in the paper can achieve remarkable recognition and judgment in diagnosis of potatos’early blight.
针对植物叶片图像的非线性失真形式,提出双线性映射方程来恢复失真图像原来的空间关系,利用最近邻插值法进行图像的灰度插值,完成对失真图像的校正。利用植物病斑区域识别分割的技术,提出了在输出层采用线性清晰化方式的五层的模糊神经网络模糊推理系统。采用梯度下降的误差反向传播法进行参数辨识,针对BP算法学习收敛速度慢且易陷入局部极小的不足,提出一种遗传算法和梯度下降的误差反向传播法相融合技术的学习算法,充分利用了遗传算法的全局搜索最优性和梯度下降的误差反向传播局部搜索最优性有机结合一种较优秀的网络学习算法。依据植物病害智能诊断的条件因素,利用图像平滑技术的滤波方法对病斑图像完成预处理后,能够实现对几何、颜色、纹理诊断依据的特征提取和计算。针对其特征矢量处于特征空间,提出隐含层的量子神经元为反正切函数的三层量子神经网络的植物病害诊断模型,样本数据中的不确定性在给定梯度下降学习算法的训练过程中被自适应的确定。本研究的植物病害无损智能诊断关键技术在马铃薯早疫病的诊断中取得了显著效果。
This paper studies the crucial technologies about intellectual diagnosis of diseases of plants and realizes correction of digital images, recognition of diseased area, the extraction and calculation of diseased area’s features,according to image processing, neural net and plant pathology.
Considering the nonlinear distortion of images of leaves, bilinear map equation is proposed to restore distorted images by utilizing interpolation, so that the correction of distorted images is obtained. Meanwhile, the five-layer fuzzy inference system is given in output layer by the partition of diseased area. Because BP algorithm has a slow convergence and usually is trapped into the local minimum, a new algorithm is proposed, which is a more excellent one that is combining two algorithms: genetic algorithm and BP. The extraction and calculation of features in geometry, color and texture are achieved after the pre-processing of the image with scabs by utilizing smoothing technique according to the factors of intellectual diagnosis for diseased plants. Besides these above, a model is designed that is a three-layer quantum neural network model, whose hidden layer is arctangent function. By the improved model, uncertainty of sample data can be determined during the training process in the given gradient descent algorithm. The results of stimulation indicate that the crucial technology proposed in the paper can achieve remarkable recognition and judgment in diagnosis of potatos’early blight.
引文
[1] V.NVapnik,S.Golowich,A.J.Smola.Support vector method for function approximation regression and signal proeessing[C].in:NIPS9,San,1997,119-123.
[2] J.Y Deng and F.Lai,Reccgnition-based template deformation and masking foreye-feature extraction and description ,Pattem Recog.30,1997,403-419.
[3]尚翊.世界农药市场展望[J].农药工业译丛.1979(1):13-19.
[4]曾希柏,陈同斌.农用化学品对农业生态环境的影响及其防治[J].科技导报,2000(4):52-54
[5]劳丽.模糊集理论在图像分割中的应用综述[J]中国体视学与图像分析, 2006(3): 200-203.
[6]朴太范.信息融合神经网络—模糊推理理论与应用[M].北京:国防工业出版社2002,7.
[7] T.Darrell,G.Gordon,M.Harville,and J.Woodfill,Integrated person tracking using stereo,eolor , and pattem deteetion,in IEEE Proe.of Int.Conf On ComPuter Vision and Pattem .Reeognition,1998(2):223-227.
[8]田有文,李成华.支持向量机在植物病斑形状识别中的应用研究[D].沈阳:沈阳农业大学,2004.7.
[9] Yutaka Sasakoi,Tsuguo Okamoto,etal.Generating of Distlnetion Parameterfor Automatic Diagnosis of Plant Diseaseby[J].农业机械学会志,1999,61(6):78-80.
[10]陈佳娟基于图像处理和人工智能的植物病害自动诊断技术的研究[D].长春:吉林工业大学,2001.7.
[11]王克如.基于图像识别的作物病虫草害诊断研究[D].北京:中国农业科学院. 2005.7.
[12]穗波信雄.图像处理在植物生长信息提取中的应用[R].农业机械学会关西支部研究会资料(日),1992.
[13] Yutaka Sasakoi,Tsuguo Okamoto.Automatic Diagnosis of Plant Disease recognition Between Healthy and Healthy and Diseased Leaf.农业机械学会志.1999, 61(2)119-126.
[14]徐贵力.基于计算机视觉技术的无土栽培番茄缺素智能识别研究[D]江苏大学,2001.
[15]徐贵力,毛罕平,李萍萍.差分百分率直方图法提取缺素叶片纹理特征[J].农业机械学报,2003,34(2):76-79.
[16]毛罕平,徐贵力,李萍萍.番茄缺素叶片的图像特征提取和优化选择研究[J].农业工程学报,2003,19(2):133-136.
[17]毛罕平,徐贵力,李萍萍.基于计算机视觉的番茄营养元素亏缺的识别[J].农业机械学报,2003,34(2):73-75.
[18]吴雪梅.计算机视觉描述缺素番茄叶片颜色变化的研究[J].农机化研究,2004(5):87-90.
[19] Panigrahi S. Background Segmentation and dimensional measurement of corn germpasm.Transactions of the ASAE,1995,38(1):291-297
[20]田有文.基于纹理特征和支持向量机的玉米病害的识别[J].沈阳农业大学学报,2005,(06):63-69.
[21]田有文、李成华.基于支持向量机和色度矩的植物病害识别研究[J].农业机械学报,2004 (03):37-41.
[22] I.Craw,H.Elks,and J.R.Lishman ,Automatic extraction of face-feature,PattemRecog.Lett.Feb.1987,183-187.
[23]何新贵,许少华.过程神经元网络[M]北京:科学出版社2007,6.
[24]许少华.一种时变输入输出过程神经元网络及学习算法研究[J]控制与决策2007,12 1425-1428.
[25] He Xin-gui,,Liang Jiu-zhen . Process Neural Networks In:World Computer Congress 2000,Proceedings of Conference on Intelligent Information Processing.Bejing:Tsinghua University Press,2003,143-146.
[24]He Xin-gui.Fuzzy Computational Reasoning and Neural Networks.Proceedings of The Second International Conference on Tools for Artifical Intelligence.Herndon;VA.2000.706-711
[27]李盼池一种量子神经网络模型学习算法及应用[J]控制理论与应用, 2009(5): 531-533.
[28]李世勇.模糊控制神经网络控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,2006.
[29]张吉利.模糊-神经模糊控制原理与工程应用[M].哈尔滨工业大学出版社,2004.
[30]胡宝清.模糊理论基础[M].武汉:武汉大学出版社,2004.
[31] Jang J R.Self learning fuzzy logic controllers based on temporal back-propagation.IEEE Trans.Neural Networks,1992(5):2399-2402.
[32] Li W,Mendel J M.Generating fuzzy rules by learning from examples.IEEE Trans.Neural Net works,1991 (12):345-349.
[33] Buckley J J,Hayashi Y . Fuzzy neural networks : a survey . Fuzzy Sets and Systems,1994(66):188-192.
[34] Jang J R.ANFIS:Adaptive-network-based fuzzy inference system.IEEE Transactions on Systems,Man,and Cybernetics,1993 (3):544-549.
[35] Nurnberger A,Nauck D,Kruse R.Neuro-fuzzy control based on the NEFCONⅣIodel:recent developments.Soft Computing,1999 (4):207-212.
[36] Haoi L T,Osowski S.Neuro-fuzzy TSK network for approximation of static and dynamic functions.Control and Cybernetics,2002(2):988-994.
[37] Nauck D,Kruse R.Neuro-Fuzzy systems for function approximation.Fuzzy Sets and Systems,1999(3):663-669.
[38] Sanchez E.Genetic algorithms,neural networks and fuzzy logic systems.Proc.SecondInternational Conference on Fuzzy Logic and Neural Networks,Iizuka,1992.
[39] Machado R J , Rocha A F . Evolutive fuzzy neural networks . Proc . First IEEE.International Confer ence On Fuzzy Systems(FUZZ-IEEE792),San Diego,1992.
[40] Buckley J J,Reilly K D,Penmetcha K V.Backpropagation and genetic algorithms for training fuzzy neural nets.Herrera F. and Verdegay J.(eds)Genetic Algorithms and Soft Computing,Heidburg Physics Verlag,1996.
[41]王士同.神经模糊系统及其应用[D].北京:北京航空航天大学出版社,1998.
[42]武妍,施鸿宝.模糊规则自动获取及其性能的分析[J].人工智能及应用,1999,25(10):532-535.
[43]李聪超,周铁军人工神经网络在农业中的应用[J]《农业网络信息》2008,1:35-36
[44]丰文义,刘斌.基于独立性参数的无导师图像变形校正[J].复旦学报(自然科学版), 1995.34(3):338-342.
[45] Mersercau K.Morris GM.Scale,rotation,and shift invariant image recognition.Appl Opt,1986,25(14):2338-2342.
[46] Psa,tis D Casasent D.Deformation Invariant optical processors using coordinate transformations Appl Opt,1977,16(8):2288-2292.
[47]刘斌.源于盲分离思想的线性变形图像校正[J].复旦学报(自然科学版),1995.34(2):185-190.
[48] Tang YY,Suen CY. Image transformation approach to nonlinear shape restoration. IEEE Transaction on Systems. Man and Cybernetics. 1993,23(1):155-171
[49] Gersho A. On the structure of vector quantizer. IEEE.1982(5):157-166
[50] Rosenfeld A. Image analysis and computer vision.CVIU,1995,62:90-143.
[51] Rosenfeld A,Torre P. Histogram concavity analysis as an aid in threshold selection.IEEE SMC,1983,13:231-235.
[52] Zimmer Y,Tepper R,Akselrod S. An improved method to compute the convex hull of a shape in a binary image.PR,1997(30):397-402.
[53] Haralick R M, Shapiro L G. Computer and Robot Vision,Addison-Weslet,1992(1):45-49.
[54]章毓晋,徐寅.计算机辅助《图像处理与分析》教学软件的研制与应用.计算机用于教育国际会议论文集[C],1995(3):212-217
[55]洛根.《有限元方法基础教程》第三版[M].北京:高等教育出版社,2003.
[56]伍义生译.有限元方法基础教程[M].北京:电子工业出版社,2003.8
[57] (美)著,欧阳宇等译.有限元分析: ANSYS理论与应用[M].北京:电子工业出版社,2003.6
[58]阮秋琦.数字图像处理学[M].北京:电子工业出版社,2001.
[69]蔡珉琦.一种基于插值算法符号同步的硬件设计[J].电子技术应用,2005(9):37-39.
[60] Keys L D,Schmidt N J,Phillips B E.A prototype example of sensor fusion used for a siting analysis.ACSM-ASPRS Annual Convention,Image Processing and RemoteSensing,1990(4):238-249.
[61]桑金歌基于模糊属性和BP神经网络的彩色图像分割方法[J].计算机教育,2008(4) :114-115.
[62]孙炜王耀南基于模糊小波神经网络的磁共振图像分割方法[J].中国生物医学工程学报,2006(6): 265-268.
[63]冯登超等基于改进型PCNN的不规则图像自适应分割算法研究[J].计算机应用2008(3):80-82.
[64]程起才.基于灰度共生矩阵的模糊神经网络FuCMAC在图像分割中的应用[J] .江南大学学报(自然科学版), 2007(12): 842-845.
[65]王耀.一种神经网络的快速学习算法及其在图像边缘检测中的应用[J],计算机发展与应用,1997(5): 376-381.
[66]雷英杰.遗传算法工具箱及应用[J].西安电子科技大学出版社,2005(5):23-25.
[67]刘沐宇,袁卫国.基于模糊神经网络的大跨度钢管混凝土拱桥安全性评价方法研究.[J]中国公路学报,2004,17(4) 45-47.
[68]王丰元,周一鸣.种子形状参数检测的计算机图像处理技术[J].农业机械学报,1995,26(2):52-57
[69] Rigney M P,BrusewitzGH,Kranzler G A.Asparagus defect inspection with machine vision.Trans of the ASAE[J].1992,35(6):1873-1878.
[70]荣士杰,孙正兴.计算机图形学[M].北京:电子工业出版社,1997.
[71]张毅军,吴雪青,夏正良.二维熵图像值分割的快速退递算法[J].模式识别与人工智能.1997,10(3):798-802.
[72]席庆,张春林.Visual C++ 6.0实用编程技术[M].北京:国际工业出版社,1983.
[73]刘树文.基于模糊神经网络的葡萄病害诊断系统研究[J].农业工程学报,2006(9): 144-147.
[74]关海鸥.马晓丹.石莉莉大豆叶片特征参数测定方法的研究[J].农机化研究, 2008(2): 59-61.
[75] Masaharu Okado,et al . Measurement of the color of leaves by color image processing (part 3). Japanese Society of Agricultural Engineering,1997,59(6): 134-139.
[76]宫小玉.用群集方法进行颜色选择[J].计算机世界.1994(1):76-81.
[77]冯玉才.地图自动识别系统中按颜色分层的算法及实现[J].软件学报,1995,6(7): 38-44.
[78]赵锋,赵荣椿.纹理分割及特征提取方法综述[J].中国体视学与图像分析.1988.3(4): 238-245.
[79] Xu Jianhua. Liang Jingyi.Digital Fourier Transform Texture Analysis Technique for Ocean-Wave Image[C].IEEE Internationnal Conference on Image Processing,1989:5-8.
[80] A.J.Lewis.Geologic Evaluation of Radar Imagery from Darien Province.GRES Techn .Report.1991:182-200.
[81] Karayiannis NB,Purnshothaman G.Fuzzy pattern classifieation using feed forward neural networks with multilevel hidden neurons[J].IEEE International on Neural Networks.1994,Vol.5(2):127-132.
[82] Gopathy P,Nicolaos B,Karayiannis NB.Quantum neural networks:Inherently fuzzy feed forward neural networks[J].IEEE Transactions On Neural Networks,1997,VO1.8(3):679-693.
[83]钟洛.人工神经网络及其融合应用技术[M].北京:科学出版社,2007,61-68.
[84] Ji X D, Familoni B O. A Diagonal Recurrent Neural Network-BasedHybrid Direct Adaptive SPSA Control System [J]. IEEE Transactions on Automatic Control, 2003, 44(7): 1469-1473.
[2] J.Y Deng and F.Lai,Reccgnition-based template deformation and masking foreye-feature extraction and description ,Pattem Recog.30,1997,403-419.
[3]尚翊.世界农药市场展望[J].农药工业译丛.1979(1):13-19.
[4]曾希柏,陈同斌.农用化学品对农业生态环境的影响及其防治[J].科技导报,2000(4):52-54
[5]劳丽.模糊集理论在图像分割中的应用综述[J]中国体视学与图像分析, 2006(3): 200-203.
[6]朴太范.信息融合神经网络—模糊推理理论与应用[M].北京:国防工业出版社2002,7.
[7] T.Darrell,G.Gordon,M.Harville,and J.Woodfill,Integrated person tracking using stereo,eolor , and pattem deteetion,in IEEE Proe.of Int.Conf On ComPuter Vision and Pattem .Reeognition,1998(2):223-227.
[8]田有文,李成华.支持向量机在植物病斑形状识别中的应用研究[D].沈阳:沈阳农业大学,2004.7.
[9] Yutaka Sasakoi,Tsuguo Okamoto,etal.Generating of Distlnetion Parameterfor Automatic Diagnosis of Plant Diseaseby[J].农业机械学会志,1999,61(6):78-80.
[10]陈佳娟基于图像处理和人工智能的植物病害自动诊断技术的研究[D].长春:吉林工业大学,2001.7.
[11]王克如.基于图像识别的作物病虫草害诊断研究[D].北京:中国农业科学院. 2005.7.
[12]穗波信雄.图像处理在植物生长信息提取中的应用[R].农业机械学会关西支部研究会资料(日),1992.
[13] Yutaka Sasakoi,Tsuguo Okamoto.Automatic Diagnosis of Plant Disease recognition Between Healthy and Healthy and Diseased Leaf.农业机械学会志.1999, 61(2)119-126.
[14]徐贵力.基于计算机视觉技术的无土栽培番茄缺素智能识别研究[D]江苏大学,2001.
[15]徐贵力,毛罕平,李萍萍.差分百分率直方图法提取缺素叶片纹理特征[J].农业机械学报,2003,34(2):76-79.
[16]毛罕平,徐贵力,李萍萍.番茄缺素叶片的图像特征提取和优化选择研究[J].农业工程学报,2003,19(2):133-136.
[17]毛罕平,徐贵力,李萍萍.基于计算机视觉的番茄营养元素亏缺的识别[J].农业机械学报,2003,34(2):73-75.
[18]吴雪梅.计算机视觉描述缺素番茄叶片颜色变化的研究[J].农机化研究,2004(5):87-90.
[19] Panigrahi S. Background Segmentation and dimensional measurement of corn germpasm.Transactions of the ASAE,1995,38(1):291-297
[20]田有文.基于纹理特征和支持向量机的玉米病害的识别[J].沈阳农业大学学报,2005,(06):63-69.
[21]田有文、李成华.基于支持向量机和色度矩的植物病害识别研究[J].农业机械学报,2004 (03):37-41.
[22] I.Craw,H.Elks,and J.R.Lishman ,Automatic extraction of face-feature,PattemRecog.Lett.Feb.1987,183-187.
[23]何新贵,许少华.过程神经元网络[M]北京:科学出版社2007,6.
[24]许少华.一种时变输入输出过程神经元网络及学习算法研究[J]控制与决策2007,12 1425-1428.
[25] He Xin-gui,,Liang Jiu-zhen . Process Neural Networks In:World Computer Congress 2000,Proceedings of Conference on Intelligent Information Processing.Bejing:Tsinghua University Press,2003,143-146.
[24]He Xin-gui.Fuzzy Computational Reasoning and Neural Networks.Proceedings of The Second International Conference on Tools for Artifical Intelligence.Herndon;VA.2000.706-711
[27]李盼池一种量子神经网络模型学习算法及应用[J]控制理论与应用, 2009(5): 531-533.
[28]李世勇.模糊控制神经网络控制和智能控制论[M].哈尔滨:哈尔滨工业大学出版社,2006.
[29]张吉利.模糊-神经模糊控制原理与工程应用[M].哈尔滨工业大学出版社,2004.
[30]胡宝清.模糊理论基础[M].武汉:武汉大学出版社,2004.
[31] Jang J R.Self learning fuzzy logic controllers based on temporal back-propagation.IEEE Trans.Neural Networks,1992(5):2399-2402.
[32] Li W,Mendel J M.Generating fuzzy rules by learning from examples.IEEE Trans.Neural Net works,1991 (12):345-349.
[33] Buckley J J,Hayashi Y . Fuzzy neural networks : a survey . Fuzzy Sets and Systems,1994(66):188-192.
[34] Jang J R.ANFIS:Adaptive-network-based fuzzy inference system.IEEE Transactions on Systems,Man,and Cybernetics,1993 (3):544-549.
[35] Nurnberger A,Nauck D,Kruse R.Neuro-fuzzy control based on the NEFCONⅣIodel:recent developments.Soft Computing,1999 (4):207-212.
[36] Haoi L T,Osowski S.Neuro-fuzzy TSK network for approximation of static and dynamic functions.Control and Cybernetics,2002(2):988-994.
[37] Nauck D,Kruse R.Neuro-Fuzzy systems for function approximation.Fuzzy Sets and Systems,1999(3):663-669.
[38] Sanchez E.Genetic algorithms,neural networks and fuzzy logic systems.Proc.SecondInternational Conference on Fuzzy Logic and Neural Networks,Iizuka,1992.
[39] Machado R J , Rocha A F . Evolutive fuzzy neural networks . Proc . First IEEE.International Confer ence On Fuzzy Systems(FUZZ-IEEE792),San Diego,1992.
[40] Buckley J J,Reilly K D,Penmetcha K V.Backpropagation and genetic algorithms for training fuzzy neural nets.Herrera F. and Verdegay J.(eds)Genetic Algorithms and Soft Computing,Heidburg Physics Verlag,1996.
[41]王士同.神经模糊系统及其应用[D].北京:北京航空航天大学出版社,1998.
[42]武妍,施鸿宝.模糊规则自动获取及其性能的分析[J].人工智能及应用,1999,25(10):532-535.
[43]李聪超,周铁军人工神经网络在农业中的应用[J]《农业网络信息》2008,1:35-36
[44]丰文义,刘斌.基于独立性参数的无导师图像变形校正[J].复旦学报(自然科学版), 1995.34(3):338-342.
[45] Mersercau K.Morris GM.Scale,rotation,and shift invariant image recognition.Appl Opt,1986,25(14):2338-2342.
[46] Psa,tis D Casasent D.Deformation Invariant optical processors using coordinate transformations Appl Opt,1977,16(8):2288-2292.
[47]刘斌.源于盲分离思想的线性变形图像校正[J].复旦学报(自然科学版),1995.34(2):185-190.
[48] Tang YY,Suen CY. Image transformation approach to nonlinear shape restoration. IEEE Transaction on Systems. Man and Cybernetics. 1993,23(1):155-171
[49] Gersho A. On the structure of vector quantizer. IEEE.1982(5):157-166
[50] Rosenfeld A. Image analysis and computer vision.CVIU,1995,62:90-143.
[51] Rosenfeld A,Torre P. Histogram concavity analysis as an aid in threshold selection.IEEE SMC,1983,13:231-235.
[52] Zimmer Y,Tepper R,Akselrod S. An improved method to compute the convex hull of a shape in a binary image.PR,1997(30):397-402.
[53] Haralick R M, Shapiro L G. Computer and Robot Vision,Addison-Weslet,1992(1):45-49.
[54]章毓晋,徐寅.计算机辅助《图像处理与分析》教学软件的研制与应用.计算机用于教育国际会议论文集[C],1995(3):212-217
[55]洛根.《有限元方法基础教程》第三版[M].北京:高等教育出版社,2003.
[56]伍义生译.有限元方法基础教程[M].北京:电子工业出版社,2003.8
[57] (美)著,欧阳宇等译.有限元分析: ANSYS理论与应用[M].北京:电子工业出版社,2003.6
[58]阮秋琦.数字图像处理学[M].北京:电子工业出版社,2001.
[69]蔡珉琦.一种基于插值算法符号同步的硬件设计[J].电子技术应用,2005(9):37-39.
[60] Keys L D,Schmidt N J,Phillips B E.A prototype example of sensor fusion used for a siting analysis.ACSM-ASPRS Annual Convention,Image Processing and RemoteSensing,1990(4):238-249.
[61]桑金歌基于模糊属性和BP神经网络的彩色图像分割方法[J].计算机教育,2008(4) :114-115.
[62]孙炜王耀南基于模糊小波神经网络的磁共振图像分割方法[J].中国生物医学工程学报,2006(6): 265-268.
[63]冯登超等基于改进型PCNN的不规则图像自适应分割算法研究[J].计算机应用2008(3):80-82.
[64]程起才.基于灰度共生矩阵的模糊神经网络FuCMAC在图像分割中的应用[J] .江南大学学报(自然科学版), 2007(12): 842-845.
[65]王耀.一种神经网络的快速学习算法及其在图像边缘检测中的应用[J],计算机发展与应用,1997(5): 376-381.
[66]雷英杰.遗传算法工具箱及应用[J].西安电子科技大学出版社,2005(5):23-25.
[67]刘沐宇,袁卫国.基于模糊神经网络的大跨度钢管混凝土拱桥安全性评价方法研究.[J]中国公路学报,2004,17(4) 45-47.
[68]王丰元,周一鸣.种子形状参数检测的计算机图像处理技术[J].农业机械学报,1995,26(2):52-57
[69] Rigney M P,BrusewitzGH,Kranzler G A.Asparagus defect inspection with machine vision.Trans of the ASAE[J].1992,35(6):1873-1878.
[70]荣士杰,孙正兴.计算机图形学[M].北京:电子工业出版社,1997.
[71]张毅军,吴雪青,夏正良.二维熵图像值分割的快速退递算法[J].模式识别与人工智能.1997,10(3):798-802.
[72]席庆,张春林.Visual C++ 6.0实用编程技术[M].北京:国际工业出版社,1983.
[73]刘树文.基于模糊神经网络的葡萄病害诊断系统研究[J].农业工程学报,2006(9): 144-147.
[74]关海鸥.马晓丹.石莉莉大豆叶片特征参数测定方法的研究[J].农机化研究, 2008(2): 59-61.
[75] Masaharu Okado,et al . Measurement of the color of leaves by color image processing (part 3). Japanese Society of Agricultural Engineering,1997,59(6): 134-139.
[76]宫小玉.用群集方法进行颜色选择[J].计算机世界.1994(1):76-81.
[77]冯玉才.地图自动识别系统中按颜色分层的算法及实现[J].软件学报,1995,6(7): 38-44.
[78]赵锋,赵荣椿.纹理分割及特征提取方法综述[J].中国体视学与图像分析.1988.3(4): 238-245.
[79] Xu Jianhua. Liang Jingyi.Digital Fourier Transform Texture Analysis Technique for Ocean-Wave Image[C].IEEE Internationnal Conference on Image Processing,1989:5-8.
[80] A.J.Lewis.Geologic Evaluation of Radar Imagery from Darien Province.GRES Techn .Report.1991:182-200.
[81] Karayiannis NB,Purnshothaman G.Fuzzy pattern classifieation using feed forward neural networks with multilevel hidden neurons[J].IEEE International on Neural Networks.1994,Vol.5(2):127-132.
[82] Gopathy P,Nicolaos B,Karayiannis NB.Quantum neural networks:Inherently fuzzy feed forward neural networks[J].IEEE Transactions On Neural Networks,1997,VO1.8(3):679-693.
[83]钟洛.人工神经网络及其融合应用技术[M].北京:科学出版社,2007,61-68.
[84] Ji X D, Familoni B O. A Diagonal Recurrent Neural Network-BasedHybrid Direct Adaptive SPSA Control System [J]. IEEE Transactions on Automatic Control, 2003, 44(7): 1469-1473.
© 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 |