田间杂草的图像识别技术研究
摘要
本文主要研究了田间杂草的图像识别技术，设计了田间杂草图像识别系统。
系统包括麦田图像数据的采集，实现对图像的预处理；绿色植物与土壤背景的分割包括图像的灰度化与格式转换和图像的二值化；作物与杂草的分割包括作物中心行的识别和作物行的滤除，在滤除作物行的过程中确定边界阈值时本文提出了先计算标定的作物行宽度与计算机自动检测的作物行宽度之间的相对误差，然后选定合适的对应最小误差的作物行边界阈值的方法。
识别杂草位置时分别采用了模板匹配和神经网络识别的方法。
其中模板匹配识别杂草的具体方法是：从图像中选择一株草的特征数据作为模板，将模板一个象素一个象素的在图像中移动，即拿已知的模板和原图像中同样大小的一块区域去匹配，在搜索区域里寻找匹配点，以搜索窗口与目标物体形态特征的匹配度作为判据来实现目标检测与跟踪。本文提出采用计算模板象素与原图像中模板运行位置的象素之间的欧氏距离来验证它们之间的匹配度的方法，欧式距离越接近0，说明匹配程度越高。寻找到图像中与模板匹配度最高的点，识别为杂草，将其象素值标记为1，图像中显示为白色；在图像中以白色斑点的状态表示出来，其它象素作为背景标记为0，图像中显示为黑色。计算出白色斑点的坐标位置，即杂草的坐标位置，从而达到了寻找到杂草位置的目的。
使用神经网络识别杂草的具体方法是：将使用3层完全结合方式的BP神经网络分类器对杂草图像进行分割，输入的特征量为每个象素的H,Cb,Cr值，所以输入层的神经元个数设计为3，输出层的神经元个数为1，输出0～1的信号，如果输出的信号大于0.9，相应的输入信号象素为杂草，将此象素标记为1，图像中显示为白色；如果输出信号小于0.1，相应的输入信号象素为土壤背景，将此象素标记为0，图像中显示为黑色。通过训练使网络达到稳定，最终使用MATLAB工具箱将图像分割，则图像中显示的白色斑点的位置即为杂草的位置。
系统全程使用MATLAB语言编程。系统最终目的是根据杂草和作物分布的位置特征滤除作物行，识别出杂草，并计算出杂草的识别率。
The identification technology of weed images in wheat fields was studied in this paper and a software system of weed images identification has been designed.
The major content includes collecting images using digital camera; pretreating images; partitioning the green plants and the soil which includes again transforming the color images into grey images, and transforming the images' formats, and transforming the grey images into binary images; partitioning the crop and the weed which includes again the identification of the center line of the crop and filtering of the crop line; finally obtaining the weed images. In order to compute the boundary of crop line, this paper choose different thresholds to compute the relative error between the automatically detected crop line width and the manually defined crop line width, and finally choose the appropriate threshold that minimum error.
The template matching and the neural network recognition method are separately used to identify the position of weed.
Template matching identification method is: Choosing a grass from the image to take the characteristic data of the template, moving a template picture from one element to another element in the image, Namely searching the region of the original map like the template and seek the match spots, and searching the window and characteristics of the goal object shape to realize the goal's examination and the track as the criterion. computing Euclidean distance between the elements of template picture and the elements of the operating position of template in the original picture. If the Euclidean distance is closer 0, the match degree is higher. searching the highest matched degree spots. Weeds'pictures are composed by them. In the image its demonstrates white, and it express in the image by the white spots, and the pictures are composed by other elements. In the image its demonstrates black. If the weeds' coordinated positions are computed, thus had achieved intention of seeking the weed position goal.
The neural network identification method is: It use the BP neural network sorter of 3 tiers to car divide up for the weed image completely. The level unifies the way completely the BP neural network division sickness spot image. Input characteristics are each picture's elements: H, Cb, Cr value, therefore the number of neuron center of input level is 3; the number of neuron center of Output level is 1. Then output signal from 0 to 1. If the output signal is bigger than 0.9, the image is weed. In the image it is demonstrated white; If the output signal is smaller than 0.1, the corresponding input signal picture element is the soil background, in the image it is demonstrated black. Enables the network through the training to achieve stably, finally uses the MATLAB toolbox to divide the image, then the image demonstrates white spots' positions namely for weeds' positions.
This system was programmed by MATLAB language. So the system can successfully filter out the crop lines and identify the weeds' positions.
系统包括麦田图像数据的采集，实现对图像的预处理；绿色植物与土壤背景的分割包括图像的灰度化与格式转换和图像的二值化；作物与杂草的分割包括作物中心行的识别和作物行的滤除，在滤除作物行的过程中确定边界阈值时本文提出了先计算标定的作物行宽度与计算机自动检测的作物行宽度之间的相对误差，然后选定合适的对应最小误差的作物行边界阈值的方法。
识别杂草位置时分别采用了模板匹配和神经网络识别的方法。
其中模板匹配识别杂草的具体方法是：从图像中选择一株草的特征数据作为模板，将模板一个象素一个象素的在图像中移动，即拿已知的模板和原图像中同样大小的一块区域去匹配，在搜索区域里寻找匹配点，以搜索窗口与目标物体形态特征的匹配度作为判据来实现目标检测与跟踪。本文提出采用计算模板象素与原图像中模板运行位置的象素之间的欧氏距离来验证它们之间的匹配度的方法，欧式距离越接近0，说明匹配程度越高。寻找到图像中与模板匹配度最高的点，识别为杂草，将其象素值标记为1，图像中显示为白色；在图像中以白色斑点的状态表示出来，其它象素作为背景标记为0，图像中显示为黑色。计算出白色斑点的坐标位置，即杂草的坐标位置，从而达到了寻找到杂草位置的目的。
使用神经网络识别杂草的具体方法是：将使用3层完全结合方式的BP神经网络分类器对杂草图像进行分割，输入的特征量为每个象素的H,Cb,Cr值，所以输入层的神经元个数设计为3，输出层的神经元个数为1，输出0～1的信号，如果输出的信号大于0.9，相应的输入信号象素为杂草，将此象素标记为1，图像中显示为白色；如果输出信号小于0.1，相应的输入信号象素为土壤背景，将此象素标记为0，图像中显示为黑色。通过训练使网络达到稳定，最终使用MATLAB工具箱将图像分割，则图像中显示的白色斑点的位置即为杂草的位置。
系统全程使用MATLAB语言编程。系统最终目的是根据杂草和作物分布的位置特征滤除作物行，识别出杂草，并计算出杂草的识别率。
The identification technology of weed images in wheat fields was studied in this paper and a software system of weed images identification has been designed.
The major content includes collecting images using digital camera; pretreating images; partitioning the green plants and the soil which includes again transforming the color images into grey images, and transforming the images' formats, and transforming the grey images into binary images; partitioning the crop and the weed which includes again the identification of the center line of the crop and filtering of the crop line; finally obtaining the weed images. In order to compute the boundary of crop line, this paper choose different thresholds to compute the relative error between the automatically detected crop line width and the manually defined crop line width, and finally choose the appropriate threshold that minimum error.
The template matching and the neural network recognition method are separately used to identify the position of weed.
Template matching identification method is: Choosing a grass from the image to take the characteristic data of the template, moving a template picture from one element to another element in the image, Namely searching the region of the original map like the template and seek the match spots, and searching the window and characteristics of the goal object shape to realize the goal's examination and the track as the criterion. computing Euclidean distance between the elements of template picture and the elements of the operating position of template in the original picture. If the Euclidean distance is closer 0, the match degree is higher. searching the highest matched degree spots. Weeds'pictures are composed by them. In the image its demonstrates white, and it express in the image by the white spots, and the pictures are composed by other elements. In the image its demonstrates black. If the weeds' coordinated positions are computed, thus had achieved intention of seeking the weed position goal.
The neural network identification method is: It use the BP neural network sorter of 3 tiers to car divide up for the weed image completely. The level unifies the way completely the BP neural network division sickness spot image. Input characteristics are each picture's elements: H, Cb, Cr value, therefore the number of neuron center of input level is 3; the number of neuron center of Output level is 1. Then output signal from 0 to 1. If the output signal is bigger than 0.9, the image is weed. In the image it is demonstrated white; If the output signal is smaller than 0.1, the corresponding input signal picture element is the soil background, in the image it is demonstrated black. Enables the network through the training to achieve stably, finally uses the MATLAB toolbox to divide the image, then the image demonstrates white spots' positions namely for weeds' positions.
This system was programmed by MATLAB language. So the system can successfully filter out the crop lines and identify the weeds' positions.
引文
[1] 徐鹤岭．五大作物农田杂草群落种群演替研究[M]．面向21世纪中国农田杂草可持续治理，中国植物学会杂草学分会．南宁：广西民族出版社，1999
[2] 苏少泉，宋祖顺．中国农田杂草化学防治[M]．北京：中国农业出版社．1996
[3] 陈在平，杜太行．控制系统计算机仿真与CAD—MATLAB语言应用[M]．天津：天津大学出版社，2001
[4] Guyer D. E.,Miles G.E., Schreiber M.M., et al. Machine vision and image processing for plant identification. Transaction of the ASAE, 1986, 29(6): 1500～1507
[5] Franz E, Gebhardt M R, Unldesbay K.B. Shape description of completely visible and partially occluded leaves for identifying plants in digital images.Transaction of the ASAE, 1991, 34 (2) : 673～681
[6] Woebbecke D.M., Meyer G.E., Von Bargen K, et al. Shape features for identifying young weeds using image analysis. Transactions of the ASAE, 1995, 38(1): 271～281
[7] Yonekawa S, Sakai N, Kitani O. Identification of idealized leaf types using simple dimensionless shape factors by image analysis. Transaction of the ASAE, 1996, 39 (4): 1525～1533
[8] Shearer S.A., Holmes R.G. Plant identification using color co-occurrence matrices. Transactions of the A}SAE, 1990, 33(6): 2037～2044
[9] Tang L, Tian F, Steward B.L, et al. Texture based weed classification using gabor wavelets and neural network for real-time selective herbicide application. ASAE, 1997, 32 (4): 1484～1490
[10] Meyer G. E., Mehta T, Kocher M.F., et al. Textural imaging and discriminant analysis for distinguishing weeds for spot spraying. Transaction of the ASAE, 1998, 41(4):1189～1197
[11] Burks T.F., Shearer S.A., Gates R.S. Backpropagation neural network design and evaluation for classifying weed species using color image texture. Transactions of the ASAE, 2000, 43 (4): 1029～1037
[12] Visser R.A., Timmermans J.M. WEED-IT: Proceedings of SPIE, Optics in Agriculture, Ⅱ 2907[C]. 1996, 120～129
[13] Biller R.H. Reduced input of herbicides byof Agricultural Engineering Research, 1998. A new selective weed control system.Forestry, and Biological Processinguse of optoelectronie sensors. Journal 71:357～362
[14] Borregaard T, Nielsen H, Norgaard L, et al. imaging spectroscopy. Journal of Agricultural 75 (4): 389～400
[15] Cardina J.D, Sparrow D.H, Mcoy E.L. Analysis of spatial distribution lambsquarters in no-till soybean. Weed Sci.,1995, 43 (2): 258～268
[16] Woebbecke D M, Meyer G E, Von Bargen K, et al. Color indices for weedand lighting conditions. identification under various soil, residue, Transaction of the ASAE, 1995, 38 (1):259～269
[17] Tian L, Slaughter D.C., Morris R.F. Outdoor field machine vision identification of tomato seedlings for automated weed control. Tx'ansaction of the ASAE, 1997
[18] Benlloch J.V, field condition.RodasIn proeA. Dynamic model to detect weeds in cereals under actual SPIE. 1998
[19] 相阿荣．利用色度法识别杂草和土壤背景物[J]．中国农业大学学报，2000，Vol．5，No．04
[20] 纪寿文，王荣本，陈佳娟，赵学笃．应用计算机图像处理技术识别玉米苗期田间杂草的研究，[J]．农业工程学报，2001，Vol．17，No．02
[21] 刘振恒，张长利，房俊龙．应用机器视觉技术识别田间杂草的研究[J]．农机化研究，2004，No．2
[22] 毛文华，王一鸣，张小超，王月青．基于机器视觉韵苗期杂草实时分割算法[J]．农业机械学报，2005，Vol．36，No．1
[23] 隋美丽，刘俊峰，陈丽．温室大棚中杂草识别系统的应用研究[J]．农机化研究，2005，No．3．
[24] 贾云德，《机器视觉》[M]，科学出版社出版，2000
[25] Rafael C．Gonzalez，Richard E．Woods著．阮秋琦，阮宇智等译．数字图像处理(第二版)[M]．北京：电子工业出版社．2003，40 (6)：1761～1768
[26] Steve Rimmer著，木杉等译，Windows图像处理实用技术和范例，学苑出版社，1994
[27] 陈纯．计算机图像处理技术与算法[M]．北京：清华大学出版社，2003：75～89
[28] David C．Kay等著，柏东等译，图形图像文件格式大全，学苑出版社，1994
[29] 叶晓东，朱兆达．中值滤波的快速算法[J]．信号处理，1997，13(3)：227～230．
[30] 李刚，范瑞霞一种改进的图像中值滤波算法[J]．北京理工大学学报，2002，22(3)：376～378
[31] 飞思科技产品研发中心．MATLAB 6.5辅助图像处理[M]．北京：电子工业出版社，2003．1
[32] Rafael C. Gonzalez, Richard E. Woods, Steven L Eddins. Digital Image Processing Using MATLAB.北京：电子工业出版社，2004
[33] H Yan. Skew correction of document images using interline cross-correlation. Computer Vision Graphics Image Process: Graphical Models and Image Process[J], 1993,55 (6): 538-543
[34] 谷口庆志著．朱虹，廖学成，乐静译．数字图像处理．北京：科学出版社，2001
[35] K R．Castleman，《数字图像处理》[M]，朱志钢等译，电子工业出版社，1998
[36] 毛文华．基于机器视觉的田间杂草识别技术研究[D]．北京：中国农业大学，2004．5
[37] httpa/phot.epfl.ch/workshop/wks96/art_3_1.html
[38] B. Zitova, J. Flusser. Image Registration methods: a survey. Image and Vision Computing, 2003, (21): 977～1000
[39] 王红梅，张科，李言俊．图像匹配研究进展[J]．计算机工程与应用，2004，19：42～44
[40] 马艳．基于颜色与模板匹配的人脸检测方法[D]．辽宁：大连理工大学，2006．11
[41] B. Zitova, J. Flusser. Image Registration methods: a survey. Image and Vision Computing, 2003, (21): 977～1000
[42] 姜凯，陈海霞，刘立峰等，基于模板抽样的快速图像匹配算法，光学精密工程(Optics and Precision Engineering).2004,12 (3): 311～315
[43] 王汇源一种快速模板匹配法及其在运动估计中的应用数据通信，1999，2，18
[44] 章为川．基于神经网络的车牌识别系统的研究与设计[D]．四川：西南交通大学，2006．5
[45] 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．吉林大学博士学位论文．2001，9：42～54
[46] 章毓晋，《图像分割》[M]，北京：科学出版社，2001
[47] 郑南宁，《计算机视觉与模式识别》[M]，国防工业出版社，1998．3
[48] 李介谷等．计算机模式识别技术[M]．上海：上海交通大学出版社．
[49] 边肇祺，张学工等．模式识别[M]．北京：清华大学出版社，2000
[50] 杨建刚．人工神经网络实用教程[M]．浙江：浙江大学出版社，2003．7．
[51] 飞思科技产品研发中心MATLAB 6.5辅助神经网络分析与设计[M]．北京：电子工业出版社，2003，4：64～69
[52] Neural Network Toolbox. MathWorks, 2004
[53] 黄庆明，张田文，潘少静．基于色彩学习的彩色图像分割方法．计算机研究与发展，1995，32(9)：60～64
[54] .Lescure P, Yedid V M, Dupoisot H, et al .Color segmentation on biological microscope images.
[57] 孟章荣．各种颜色模型选用需求分析[J]．中国图像图形学报，1996，1(3)：238～241
[58] 孙家广，杨长贵．计算机图形学．北京：清华大学出版社，1997
[59] 杨建刚．人工神经网络实用教程[M]．浙江：浙江大学出版社，2003．7
[60] 飞思科技产品研发中心．MATLAB 6.5辅助神经网络分析与设计[M]．北京：电子工业出版社，2003，4：64～69
[61] Neural Network Toolbox. MathWorks, 2004
[62] 胡守仁等．丰申经网络导论[M]．长沙：国防科技大学出版社，1993
[63] Bennedsen Bent S, Christensen Lene K, Pedersen Anders, Jensen Lars S, Nielsen Niels E. Remote sensing mapping of soil and plants as basis for a variable rate nutrient application system .Proceedings of SPIE—The International Society for Optical Engineering. v 5271, Monitoring Food Safety, Agriculture, and Plant Health. 2004:212～217
[64] Sammouda R, Sammouda M. Improving the performance of Hopfield neural network to segment pathological liver color images. International Congress Series,2003,12:232～239
[65] 焦李成．神经网络系统理论[M]．西安：西安电子科技大学出版社，1990
[66] 李士勇．模糊控制、神经网络和智能控制论[M]．哈尔滨：哈尔滨工业大学出版社，1996
[67] 孙增忻．智能控制理论与技术．北京：清华大学出版社，1997
[68] 黄庆明，张田文，潘少静．基于色彩学习的彩色图像分割方法．计算机研究与发展，1995，32(9)：60～64
[69] 石俊生，杨卫平，自凤翔等．彩色图像分割与颜色特征选择[J]．云南师范大学学报，1999，19(6)：53～56
[70] Lescure P, Yedid V M, Dupoisot H, et al .Color segmentation on biological microscope images. Proceeding of SPIE, Application of Artificial Neural Networks in Image Processing Ⅳ. San Jose, California, USA, 1999: 182～193
[2] 苏少泉，宋祖顺．中国农田杂草化学防治[M]．北京：中国农业出版社．1996
[3] 陈在平，杜太行．控制系统计算机仿真与CAD—MATLAB语言应用[M]．天津：天津大学出版社，2001
[4] Guyer D. E.,Miles G.E., Schreiber M.M., et al. Machine vision and image processing for plant identification. Transaction of the ASAE, 1986, 29(6): 1500～1507
[5] Franz E, Gebhardt M R, Unldesbay K.B. Shape description of completely visible and partially occluded leaves for identifying plants in digital images.Transaction of the ASAE, 1991, 34 (2) : 673～681
[6] Woebbecke D.M., Meyer G.E., Von Bargen K, et al. Shape features for identifying young weeds using image analysis. Transactions of the ASAE, 1995, 38(1): 271～281
[7] Yonekawa S, Sakai N, Kitani O. Identification of idealized leaf types using simple dimensionless shape factors by image analysis. Transaction of the ASAE, 1996, 39 (4): 1525～1533
[8] Shearer S.A., Holmes R.G. Plant identification using color co-occurrence matrices. Transactions of the A}SAE, 1990, 33(6): 2037～2044
[9] Tang L, Tian F, Steward B.L, et al. Texture based weed classification using gabor wavelets and neural network for real-time selective herbicide application. ASAE, 1997, 32 (4): 1484～1490
[10] Meyer G. E., Mehta T, Kocher M.F., et al. Textural imaging and discriminant analysis for distinguishing weeds for spot spraying. Transaction of the ASAE, 1998, 41(4):1189～1197
[11] Burks T.F., Shearer S.A., Gates R.S. Backpropagation neural network design and evaluation for classifying weed species using color image texture. Transactions of the ASAE, 2000, 43 (4): 1029～1037
[12] Visser R.A., Timmermans J.M. WEED-IT: Proceedings of SPIE, Optics in Agriculture, Ⅱ 2907[C]. 1996, 120～129
[13] Biller R.H. Reduced input of herbicides byof Agricultural Engineering Research, 1998. A new selective weed control system.Forestry, and Biological Processinguse of optoelectronie sensors. Journal 71:357～362
[14] Borregaard T, Nielsen H, Norgaard L, et al. imaging spectroscopy. Journal of Agricultural 75 (4): 389～400
[15] Cardina J.D, Sparrow D.H, Mcoy E.L. Analysis of spatial distribution lambsquarters in no-till soybean. Weed Sci.,1995, 43 (2): 258～268
[16] Woebbecke D M, Meyer G E, Von Bargen K, et al. Color indices for weedand lighting conditions. identification under various soil, residue, Transaction of the ASAE, 1995, 38 (1):259～269
[17] Tian L, Slaughter D.C., Morris R.F. Outdoor field machine vision identification of tomato seedlings for automated weed control. Tx'ansaction of the ASAE, 1997
[18] Benlloch J.V, field condition.RodasIn proeA. Dynamic model to detect weeds in cereals under actual SPIE. 1998
[19] 相阿荣．利用色度法识别杂草和土壤背景物[J]．中国农业大学学报，2000，Vol．5，No．04
[20] 纪寿文，王荣本，陈佳娟，赵学笃．应用计算机图像处理技术识别玉米苗期田间杂草的研究，[J]．农业工程学报，2001，Vol．17，No．02
[21] 刘振恒，张长利，房俊龙．应用机器视觉技术识别田间杂草的研究[J]．农机化研究，2004，No．2
[22] 毛文华，王一鸣，张小超，王月青．基于机器视觉韵苗期杂草实时分割算法[J]．农业机械学报，2005，Vol．36，No．1
[23] 隋美丽，刘俊峰，陈丽．温室大棚中杂草识别系统的应用研究[J]．农机化研究，2005，No．3．
[24] 贾云德，《机器视觉》[M]，科学出版社出版，2000
[25] Rafael C．Gonzalez，Richard E．Woods著．阮秋琦，阮宇智等译．数字图像处理(第二版)[M]．北京：电子工业出版社．2003，40 (6)：1761～1768
[26] Steve Rimmer著，木杉等译，Windows图像处理实用技术和范例，学苑出版社，1994
[27] 陈纯．计算机图像处理技术与算法[M]．北京：清华大学出版社，2003：75～89
[28] David C．Kay等著，柏东等译，图形图像文件格式大全，学苑出版社，1994
[29] 叶晓东，朱兆达．中值滤波的快速算法[J]．信号处理，1997，13(3)：227～230．
[30] 李刚，范瑞霞一种改进的图像中值滤波算法[J]．北京理工大学学报，2002，22(3)：376～378
[31] 飞思科技产品研发中心．MATLAB 6.5辅助图像处理[M]．北京：电子工业出版社，2003．1
[32] Rafael C. Gonzalez, Richard E. Woods, Steven L Eddins. Digital Image Processing Using MATLAB.北京：电子工业出版社，2004
[33] H Yan. Skew correction of document images using interline cross-correlation. Computer Vision Graphics Image Process: Graphical Models and Image Process[J], 1993,55 (6): 538-543
[34] 谷口庆志著．朱虹，廖学成，乐静译．数字图像处理．北京：科学出版社，2001
[35] K R．Castleman，《数字图像处理》[M]，朱志钢等译，电子工业出版社，1998
[36] 毛文华．基于机器视觉的田间杂草识别技术研究[D]．北京：中国农业大学，2004．5
[37] httpa/phot.epfl.ch/workshop/wks96/art_3_1.html
[38] B. Zitova, J. Flusser. Image Registration methods: a survey. Image and Vision Computing, 2003, (21): 977～1000
[39] 王红梅，张科，李言俊．图像匹配研究进展[J]．计算机工程与应用，2004，19：42～44
[40] 马艳．基于颜色与模板匹配的人脸检测方法[D]．辽宁：大连理工大学，2006．11
[41] B. Zitova, J. Flusser. Image Registration methods: a survey. Image and Vision Computing, 2003, (21): 977～1000
[42] 姜凯，陈海霞，刘立峰等，基于模板抽样的快速图像匹配算法，光学精密工程(Optics and Precision Engineering).2004,12 (3): 311～315
[43] 王汇源一种快速模板匹配法及其在运动估计中的应用数据通信，1999，2，18
[44] 章为川．基于神经网络的车牌识别系统的研究与设计[D]．四川：西南交通大学，2006．5
[45] 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．吉林大学博士学位论文．2001，9：42～54
[46] 章毓晋，《图像分割》[M]，北京：科学出版社，2001
[47] 郑南宁，《计算机视觉与模式识别》[M]，国防工业出版社，1998．3
[48] 李介谷等．计算机模式识别技术[M]．上海：上海交通大学出版社．
[49] 边肇祺，张学工等．模式识别[M]．北京：清华大学出版社，2000
[50] 杨建刚．人工神经网络实用教程[M]．浙江：浙江大学出版社，2003．7．
[51] 飞思科技产品研发中心MATLAB 6.5辅助神经网络分析与设计[M]．北京：电子工业出版社，2003，4：64～69
[52] Neural Network Toolbox. MathWorks, 2004
[53] 黄庆明，张田文，潘少静．基于色彩学习的彩色图像分割方法．计算机研究与发展，1995，32(9)：60～64
[54] .Lescure P, Yedid V M, Dupoisot H, et al .Color segmentation on biological microscope images.
[57] 孟章荣．各种颜色模型选用需求分析[J]．中国图像图形学报，1996，1(3)：238～241
[58] 孙家广，杨长贵．计算机图形学．北京：清华大学出版社，1997
[59] 杨建刚．人工神经网络实用教程[M]．浙江：浙江大学出版社，2003．7
[60] 飞思科技产品研发中心．MATLAB 6.5辅助神经网络分析与设计[M]．北京：电子工业出版社，2003，4：64～69
[61] Neural Network Toolbox. MathWorks, 2004
[62] 胡守仁等．丰申经网络导论[M]．长沙：国防科技大学出版社，1993
[63] Bennedsen Bent S, Christensen Lene K, Pedersen Anders, Jensen Lars S, Nielsen Niels E. Remote sensing mapping of soil and plants as basis for a variable rate nutrient application system .Proceedings of SPIE—The International Society for Optical Engineering. v 5271, Monitoring Food Safety, Agriculture, and Plant Health. 2004:212～217
[64] Sammouda R, Sammouda M. Improving the performance of Hopfield neural network to segment pathological liver color images. International Congress Series,2003,12:232～239
[65] 焦李成．神经网络系统理论[M]．西安：西安电子科技大学出版社，1990
[66] 李士勇．模糊控制、神经网络和智能控制论[M]．哈尔滨：哈尔滨工业大学出版社，1996
[67] 孙增忻．智能控制理论与技术．北京：清华大学出版社，1997
[68] 黄庆明，张田文，潘少静．基于色彩学习的彩色图像分割方法．计算机研究与发展，1995，32(9)：60～64
[69] 石俊生，杨卫平，自凤翔等．彩色图像分割与颜色特征选择[J]．云南师范大学学报，1999，19(6)：53～56
[70] Lescure P, Yedid V M, Dupoisot H, et al .Color segmentation on biological microscope images. Proceeding of SPIE, Application of Artificial Neural Networks in Image Processing Ⅳ. San Jose, California, USA, 1999: 182～193