基于图像分析的植物叶部病害识别方法研究
摘要
基于图像分析的植物叶部病害识别技术研究，对有效防治农作物病害的发生，提高农作物的产量、减少农药对农产品和环境的污染，均具有重要的现实意义。本研究在国内外研究成果的基础上，以提高农作物病害识别准确率和效率为目标，以苹果、黄瓜和辣椒等作物病害为例对植物叶部病害的图像分割、特征提取、病害诊断识别方法等关键技术展开系统研究。论文的主要工作和创新点如下：
（1）针对植物病斑彩色图像噪声大和边缘模糊等特点，提出了一种基于水平集和加权颜色信息的改进C-V模型。借助水平集方法对病斑图像的RGB分量图像颜色信息取加权值，以差分图像能量作为能量函数最终值，以适应不同病害种类。试验结果表明，经过RGB加权的辣椒缺水病斑图像用3R-B图像模型，苹果锈病病斑图像用3R-G图像模型自动分割，比传统C-V模型分割效果好，性能明显提高，抗噪性和可扩展性好。
（2）针对加权颜色信息C-V模型运行时间长及人工选取权重参数难等问题，提出了基于相似度改进C-V模型的植物叶部病斑彩色图像分割方法。通过计算病斑彩色图像R、G、B通道的前景与背景像素均值的比例，作为病斑图像R、G、B通道的能量权值；每次迭代中将符号距离函数中小于外部能量区域符号距离平均值的距离值归零，得收敛分割曲线。试验结果表明，该方法平均准确率分别高于基于加权颜色信息的C-V模型和传统C-V模型0.42和43.55个百分点，且抗噪性好；对于高分辨率彩色图片，平均运行时间不到这二者的1/1000，大大提高了算法效率。
（3）针对颜色矩运行时间长及分类率不高的问题，提出了基于颜色矩和小波变换的加权特征提取方法，该方法分别对H、S和V通道图像进行小波分解根据其1-3阶矩特征得到每个子图的能量系数，将其作为特征的权重。试验显示，用支持向量机多项式核函数，小波基为bior2.4时提取特征的识别正确率最高，花叶病、锈病和斑点落叶病平均识别正确率为89.78%，与基于颜色矩和小波的特征提取方法的识别正确率（25.67%和80.14%）相比，显著提高了识别正确率。
（4）针对小波分解进行特征提取通常仅利用了图像低频子带信息的缺点，提出了基于YUV和小波包的多通道特征提取算法，以全面分析图像纹理特征。该方法对输入图像的Y、U、V通道子图像进行小波包分解，以Y、U、V分量子图像各自小波包能量特征和分量子图像之间的小波包能量特征作为病害图像特征向量。试验结果表明，当小波基为haar，支持向量机为多项式核函数时，花叶病、锈病和斑点落叶病的平均识别正确率为89.10%，比基于小波的特征提取方法识别正确率提高12.16个百分点。
（5）针对SVM模型中参数难以确定的问题，提出了基于遗传算法支持向量机模型（GA-SVM）的苹果叶部病害识别方法。该方法用遗传算法自动获取SVM参数，GA参数用旋转正交方法得到，获得合适的GA-SVM模型后，将基于颜色矩和小波变换的加权特征作为特征向量进行分类。试验结果表明：当粒子数M=50，交叉率Pc=0.7，变异率Pm=0.05，迭代次数G m=100时，花叶病、锈病和斑点落叶病的平均识别正确率为92.39%，比SVM模型提高了5.21%识别正确率。
（6）针对SVM模型中参数难确定及遗传算法复杂问题，提出了基于粒子群算法支持向量机模型（PSO-SVM）的苹果叶部病害识别方法。该方法用粒子群算法确定SVM模型的惩罚因子和核参数的最优数值，得到合适的PSO-SVM模型后，以基于颜色矩和小波的加权特征作为特征向量进行分类。经旋转正交试验探明较优粒子群算法参数为c1=c2=2.05，粒子数m=20时，病害识别正确率较高，苹果花叶病、锈病和斑点落叶病的识别正确率分别为90.24%、87.26%和85.23%，平均运行时间比GA-SVM方法减少10.86个百分点，提高了识别效率。
The image analysis-based research on plant leaf disease diagnosis recognitiontechnology has a great significance to prevente the occurrence of crop disasters effectively,reduce the impact of the crops diseased, increase crop yield and reduce pesticides onagricultural products and environmental pollution. On the basis of adequate summary aboutthe advanced achievements at home and aboard, in this paper systematical research has beenmade on the key technology of image segmentation, feature extraction and disease diagnosisrecognition, which relyed firmly on the goal of improving recognition accuracy and efficiencyof crop diseases and its cases study of apple, cucumber and capsicum disease. The chief workand major innovations are as follows:
(1) In view of the characteristics of noise and blurred edges for plant lesion colorimages, a novel C-V model named WCCV based on level set and weighted color informationwas proposed in this paper and applied to plant lesion image segmentation.The WCCVsegmentation model is suited to different disease identification and can identify lesion diseaseautomatically. Experimental results show that the proposed model has better property than thetraditional C-V model, and have many advantages such as anti-noise and scalability propertieson3R-B image model for capsicum water shortages disease and3R-G image model for applerust disease.
(2) According to the flaw of WCCV model, an improved C-V model was proposed inthis paper and applied to plant leaf lesion image segmentation. At first, a point in lesion areais selected, and the mean value calculated from its3×3territory is used to compute thesimilarity between this point and other points in the image, and the foreground andbackground are determined. Then the ration of foreground and background mean pixels fromR,G, B channels is used as weighted value of these three channels, respectively. Finally, thelevel set function is solved iteratively to gain the segmentation contour, while let the distancevalue less than the average distance value of external energy region be zero in the signeddistance function.Experimental results show that the average segmentation accuracy of theproposed method is0.42%and43.55%higher than that of WCCV model and the traditionalC-V model. For large pixel pictures, the average running time of the proposed method is lessthan1/1000of WCCV model and the traditional C-V model. It reduces the running time andimproves the efficiency of algorithm execution greatly.
(3) Aiming at the shortcoming of the long running time and not high classification rate of color moments, the weighted feature extraction method based on color moments andwavelet decomposition was proposed. At first, the original image is transformed into H, S andV-channel images to get the wavelet decomposition of each channel subgraphs. Secondly, thedecomposition subgraphs of the integration color and wavelet features are gained and thefirst-order, second-order and third-order moments features of the decomposition subgraphsare calculated. And the energy coefficients are as the weighted features value of the colormoments of the subgraphs and finally the feature vector is gained. The experimental resultsdemonstrate that when the polynomial kernel function-based SVM(support vector machine)and the bior2.4-based wavelet are used, the proposed method recognition correct ratios are88.57%,88.46%, and92.31%for apple mosaic virus, apple rust and apple alternaria leaf spot,respectively, and the average recognition ratio is89.78%. The proposed approachsignificantly improves the recognition correct ratio compared to the25.67%and80.14%recognition correct ratios for color moments-based and wavelet-based feature extractionmethods, respectively.
(4) A YUV and wavelet packet-based multi-channel feature extraction algorithm wasproposed. Due to the drawback of the wavelet decomposition-used the feature extractionmethod is normally only using the low-frequency sub-band information of the image, so theuse of wavelet packet decomposition for all frequency channels is a comprehensive analysisof images texture features. Firstly, the input image is converted into the Y, U, V channelssubgraph, respectively. Then the wavelet packet energy features of the Y, U andV-component images are calculated. Finally the wavelet packet energy features among thesub-quantum images are obtained as the disease image feature vector. The experimentalresults demonstrate that when using the polynomial kernel function-based SVM and the haar-based wavelet packet, the average recognition correct ratio is89.10%.Compared with thefeature extraction method based on wavelet transforming, the proposed approach boosts12.16percent recognition correct ratio.
(5) The genetic algorithm (GA) is used to select the parameters of the SVM methodautomatically and the orthogonal method is utilized to determine the best GA parameters.Firstly, the color moments and wavelet-based features of apple disease leaf images areextracted as feature vectors. Then the proposed GA-SVM method is used to classify appleleaf disease images.The orthogonal experimental results demonstrate that the proposedGA-SVM model recognition correct ratios are94.47%,91.44%, and91.26%for apple mosaicvirus, apple rust and apple alternaria leaf spot, respectively. And the average recognitioncorrect ratio is92.39%.Compared with the recognition method based on SVM, the proposedapproach shows5.21%higher recognition correct ratio than that of SVM.
(6) Considering the difficulty of parameter determination in the original SVM and thecomplexity of genetic algorithm, the particle swarm optimization algorithm (PSO) is used toselect the parameters of the SVM automatically and obtain an optimized function. The PSO algorithm has no crossover and mutation operation, less parameters and easier to use.And itsprinciple is more simple than that of GA. Firstly, the color moments and wavelet-basedfeatures of apple disease leaf images are extracted as feature vectors. Then the proposedPSO-SVM model is used to classify apple leaf disease images. The orthogonal experimentalresults show that the recognition correct ratios are90.24%,87.26%, and85.23%for applemosaic virus, apple rust and apple alternaria leaf spot, respectively. Compared with therecognition method of GA-based, the proposed approach costs10.86%less processing timethan that of GA-SVM.
（1）针对植物病斑彩色图像噪声大和边缘模糊等特点，提出了一种基于水平集和加权颜色信息的改进C-V模型。借助水平集方法对病斑图像的RGB分量图像颜色信息取加权值，以差分图像能量作为能量函数最终值，以适应不同病害种类。试验结果表明，经过RGB加权的辣椒缺水病斑图像用3R-B图像模型，苹果锈病病斑图像用3R-G图像模型自动分割，比传统C-V模型分割效果好，性能明显提高，抗噪性和可扩展性好。
（2）针对加权颜色信息C-V模型运行时间长及人工选取权重参数难等问题，提出了基于相似度改进C-V模型的植物叶部病斑彩色图像分割方法。通过计算病斑彩色图像R、G、B通道的前景与背景像素均值的比例，作为病斑图像R、G、B通道的能量权值；每次迭代中将符号距离函数中小于外部能量区域符号距离平均值的距离值归零，得收敛分割曲线。试验结果表明，该方法平均准确率分别高于基于加权颜色信息的C-V模型和传统C-V模型0.42和43.55个百分点，且抗噪性好；对于高分辨率彩色图片，平均运行时间不到这二者的1/1000，大大提高了算法效率。
（3）针对颜色矩运行时间长及分类率不高的问题，提出了基于颜色矩和小波变换的加权特征提取方法，该方法分别对H、S和V通道图像进行小波分解根据其1-3阶矩特征得到每个子图的能量系数，将其作为特征的权重。试验显示，用支持向量机多项式核函数，小波基为bior2.4时提取特征的识别正确率最高，花叶病、锈病和斑点落叶病平均识别正确率为89.78%，与基于颜色矩和小波的特征提取方法的识别正确率（25.67%和80.14%）相比，显著提高了识别正确率。
（4）针对小波分解进行特征提取通常仅利用了图像低频子带信息的缺点，提出了基于YUV和小波包的多通道特征提取算法，以全面分析图像纹理特征。该方法对输入图像的Y、U、V通道子图像进行小波包分解，以Y、U、V分量子图像各自小波包能量特征和分量子图像之间的小波包能量特征作为病害图像特征向量。试验结果表明，当小波基为haar，支持向量机为多项式核函数时，花叶病、锈病和斑点落叶病的平均识别正确率为89.10%，比基于小波的特征提取方法识别正确率提高12.16个百分点。
（5）针对SVM模型中参数难以确定的问题，提出了基于遗传算法支持向量机模型（GA-SVM）的苹果叶部病害识别方法。该方法用遗传算法自动获取SVM参数，GA参数用旋转正交方法得到，获得合适的GA-SVM模型后，将基于颜色矩和小波变换的加权特征作为特征向量进行分类。试验结果表明：当粒子数M=50，交叉率Pc=0.7，变异率Pm=0.05，迭代次数G m=100时，花叶病、锈病和斑点落叶病的平均识别正确率为92.39%，比SVM模型提高了5.21%识别正确率。
（6）针对SVM模型中参数难确定及遗传算法复杂问题，提出了基于粒子群算法支持向量机模型（PSO-SVM）的苹果叶部病害识别方法。该方法用粒子群算法确定SVM模型的惩罚因子和核参数的最优数值，得到合适的PSO-SVM模型后，以基于颜色矩和小波的加权特征作为特征向量进行分类。经旋转正交试验探明较优粒子群算法参数为c1=c2=2.05，粒子数m=20时，病害识别正确率较高，苹果花叶病、锈病和斑点落叶病的识别正确率分别为90.24%、87.26%和85.23%，平均运行时间比GA-SVM方法减少10.86个百分点，提高了识别效率。
The image analysis-based research on plant leaf disease diagnosis recognitiontechnology has a great significance to prevente the occurrence of crop disasters effectively,reduce the impact of the crops diseased, increase crop yield and reduce pesticides onagricultural products and environmental pollution. On the basis of adequate summary aboutthe advanced achievements at home and aboard, in this paper systematical research has beenmade on the key technology of image segmentation, feature extraction and disease diagnosisrecognition, which relyed firmly on the goal of improving recognition accuracy and efficiencyof crop diseases and its cases study of apple, cucumber and capsicum disease. The chief workand major innovations are as follows:
(1) In view of the characteristics of noise and blurred edges for plant lesion colorimages, a novel C-V model named WCCV based on level set and weighted color informationwas proposed in this paper and applied to plant lesion image segmentation.The WCCVsegmentation model is suited to different disease identification and can identify lesion diseaseautomatically. Experimental results show that the proposed model has better property than thetraditional C-V model, and have many advantages such as anti-noise and scalability propertieson3R-B image model for capsicum water shortages disease and3R-G image model for applerust disease.
(2) According to the flaw of WCCV model, an improved C-V model was proposed inthis paper and applied to plant leaf lesion image segmentation. At first, a point in lesion areais selected, and the mean value calculated from its3×3territory is used to compute thesimilarity between this point and other points in the image, and the foreground andbackground are determined. Then the ration of foreground and background mean pixels fromR,G, B channels is used as weighted value of these three channels, respectively. Finally, thelevel set function is solved iteratively to gain the segmentation contour, while let the distancevalue less than the average distance value of external energy region be zero in the signeddistance function.Experimental results show that the average segmentation accuracy of theproposed method is0.42%and43.55%higher than that of WCCV model and the traditionalC-V model. For large pixel pictures, the average running time of the proposed method is lessthan1/1000of WCCV model and the traditional C-V model. It reduces the running time andimproves the efficiency of algorithm execution greatly.
(3) Aiming at the shortcoming of the long running time and not high classification rate of color moments, the weighted feature extraction method based on color moments andwavelet decomposition was proposed. At first, the original image is transformed into H, S andV-channel images to get the wavelet decomposition of each channel subgraphs. Secondly, thedecomposition subgraphs of the integration color and wavelet features are gained and thefirst-order, second-order and third-order moments features of the decomposition subgraphsare calculated. And the energy coefficients are as the weighted features value of the colormoments of the subgraphs and finally the feature vector is gained. The experimental resultsdemonstrate that when the polynomial kernel function-based SVM(support vector machine)and the bior2.4-based wavelet are used, the proposed method recognition correct ratios are88.57%,88.46%, and92.31%for apple mosaic virus, apple rust and apple alternaria leaf spot,respectively, and the average recognition ratio is89.78%. The proposed approachsignificantly improves the recognition correct ratio compared to the25.67%and80.14%recognition correct ratios for color moments-based and wavelet-based feature extractionmethods, respectively.
(4) A YUV and wavelet packet-based multi-channel feature extraction algorithm wasproposed. Due to the drawback of the wavelet decomposition-used the feature extractionmethod is normally only using the low-frequency sub-band information of the image, so theuse of wavelet packet decomposition for all frequency channels is a comprehensive analysisof images texture features. Firstly, the input image is converted into the Y, U, V channelssubgraph, respectively. Then the wavelet packet energy features of the Y, U andV-component images are calculated. Finally the wavelet packet energy features among thesub-quantum images are obtained as the disease image feature vector. The experimentalresults demonstrate that when using the polynomial kernel function-based SVM and the haar-based wavelet packet, the average recognition correct ratio is89.10%.Compared with thefeature extraction method based on wavelet transforming, the proposed approach boosts12.16percent recognition correct ratio.
(5) The genetic algorithm (GA) is used to select the parameters of the SVM methodautomatically and the orthogonal method is utilized to determine the best GA parameters.Firstly, the color moments and wavelet-based features of apple disease leaf images areextracted as feature vectors. Then the proposed GA-SVM method is used to classify appleleaf disease images.The orthogonal experimental results demonstrate that the proposedGA-SVM model recognition correct ratios are94.47%,91.44%, and91.26%for apple mosaicvirus, apple rust and apple alternaria leaf spot, respectively. And the average recognitioncorrect ratio is92.39%.Compared with the recognition method based on SVM, the proposedapproach shows5.21%higher recognition correct ratio than that of SVM.
(6) Considering the difficulty of parameter determination in the original SVM and thecomplexity of genetic algorithm, the particle swarm optimization algorithm (PSO) is used toselect the parameters of the SVM automatically and obtain an optimized function. The PSO algorithm has no crossover and mutation operation, less parameters and easier to use.And itsprinciple is more simple than that of GA. Firstly, the color moments and wavelet-basedfeatures of apple disease leaf images are extracted as feature vectors. Then the proposedPSO-SVM model is used to classify apple leaf disease images. The orthogonal experimentalresults show that the recognition correct ratios are90.24%,87.26%, and85.23%for applemosaic virus, apple rust and apple alternaria leaf spot, respectively. Compared with therecognition method of GA-based, the proposed approach costs10.86%less processing timethan that of GA-SVM.
引文
陈兵旗,郭学梅,李晓华.2009.基于图像处理的小麦病害诊断算法.农业机械学报,40(12):190-195
边肇祺,张学工等.2000.模式识别.北京:清华大学出版社,296-304
蔡鸿昌,崔海信,宋卫堂等.2006.辣椒初花期叶片光合色素含量与颜色特征的初步研究.农业工程学报,22(9):34-38
崔艳丽,程鹏飞,董晓志,等.2005.温室植物病害的图像处理及特征值提取方法的研究.农业工程学报,21(增刊):32-34
邓继忠,李敏,袁之报,等.2012.基于图像识别的小麦腥黑穗病害特征提取与分类.农业工程学报,28(3):172-175
陈武凡.2002.小波分析及其在图像处理中的应用.北京:科学出版社,156-160
刁智华.2010.大田小麦叶部病害智能诊断系统研究与应用.[博士学位论文].合肥.中国科学技术大学
关海鹏,许少华,谭峰.2010.基于遗传模糊神经网络的植物病斑区域图像分割模型.农业机械学报,41(11):163-167
冯洁,廖宁放,赵波,等.2008.多光谱成像技术诊断植物病虫害的人工神经网络模型.光学技术,34(5):717-720
葛婧.2007.基于计算机图像处理技术的作物病害等级检测.[硕士学位论文].合肥.安徽农业大学
葛婧,邵陆寿,丁克坚,等.2008.玉米小斑病病害程度图像检测.农业机械学报,39(1):114-117
耿楠,于伟,宁纪锋.2011.基于水平集和先验信息的农业图像分割方法.农业机械学报,42(9):167-172
郭文强.2009数字图像处理.西安:西安电子科技大学出版社
何东健,耿楠,张义宽.2008.数字图像处理(第二版).西安:西安电子科技大学出版社,32-37
韩殿元,黄心渊,付慧.2012.基于彩色通道相似性图像分割方法的植物叶面积计算.农业工程学报,28(6):179-182
霍海娥,霍海波,杨长生.2010.SOFC的支持向量机（SVM）辨识建模.系统仿真学报,22(6):1557-1560
胡秋霞,田杰,何东健,等.2012.基于改进型C-V模型的植物病斑图像分割.农业机械学报,43(5):157-161
黄元元,刘宁钟.2012.一种新的基于颜色特征的图像检索方法.小型微型计算机系统,33(3):609-613
黄志开.2006.彩色图像特征提取与植物分类研究.[博士学位论文].合肥.中国科学技术大学
冀荣华,祁力钧,傅泽田.2007.自动对靶施药系统中植物病害识别技术的研究.农业机械学报,38(6):190-192
李冠林,马占鸿,黄冲等.2010.基于K_means硬聚类算法的葡萄病害彩色图像分割方法.农业工程学报,26(2):32-36（增刊）
赖军臣,李少昆,明博,等.2009.作物病害机器视觉诊断研究进展.中国农业科学,42(4):1215-1221
龙满生,何东健.2007.玉米苗期杂草的计算机识别技术研究.农业工程学报,23(7):139-143
吕强,蔡健荣,赵杰文,等.2010.自然场景下树上柑橘实时识别技术.农业机械学报,41(2):185-188
刘树文,王庆伟,何东健,等.2006.基于模糊神经网络的葡萄病害诊断系统研究.农业工程学报,22(9):144-147
刘晴蕊,何东健,张宏鸣,朱珊娜,郭云忠.2011.苹果病害智能诊断方法研究与设计.农机化研究,33(4):76-78
刘志华,程鹏飞.2006.辣椒侵染性病害图像处理及特征值提取方法的研究.山西农业大学学报,26(3):351-354
李峥嵘,刘月娥,何东健,等.2007.基于内容的小麦害虫图像检索系统研究与实现.农业工程学报,23(11):210-214
李岳阳.2010.彩色图像滤波算法的研究.[博士学位论文].无锡.江南大学
李宗儒.2010.基于图像分析的苹果病害识别技术研究.[硕士学位论文].杨凌.西北农林科技大学
毛罕平,徐贵力,李萍萍.2003a.番茄缺素叶片的图像特征提取和优化选择研究.农业工程学报,19(2):133-136
毛罕平,徐贵力,李萍萍.2003b.基于计算机视觉的番茄营养元素亏缺的识别.农业机械学报,34(2):73-75
毛罕平,张艳诚,胡波.2008.基于模糊C均值聚类的作物病害叶片图像分割方法研究.农业工程学报,24(9:136-140
毛亮,薛月菊,孔德运,等.2011.基于稀疏场水平集的荔枝图像分割算法.农业工程学报,27(4):345-349
马晓丹,祁广云.2006.基于神经网络的大豆叶片病斑的识别与研究.黑龙江八一农垦大学学报,18(2):84-87
宁纪锋,吴成柯,姜光,等.2008.基于偏微分方程和分水岭算法的图像分割.模式识别与人工智能,21(5):664-669
祁广云,马晓丹,关海鸥.2009.采用改进遗传算法提取大豆叶片病斑图像.农业工程学报,25(5):142-144
房俊龙,张长利,潘伟,等.2004.用遗传算法训练的人工神经网络识别番茄生理病害果.农业工程学报,20(3):113-116
潘振宽,李华,魏伟波,等.2009.三维图像多相分割的变分水平集方法.计算机学报,32(12):2464-2473.
任传贤2010.面向人脸识别的快速特征提取与稀疏表示方法研究.[博士学位论文].广州.中山大学
任东.2007.基于支持向量机的植物病害识别研究.[博士学位论文].吉林.吉林大学
宋凯,孙晓艳,纪建伟.2007.基于支持向量机的玉米叶部病害识别.农业工程学报,23(1):156-157
孙国祥,汪小旵,何国敏.2010.基于边缘链码信息的番茄苗重叠叶面分割算法.农业工程学报,26(12):206-210
石磊,王红军,吴国新.2010.基于小波包分析的旋转机械故障诊断研究.北京信息科技大学学报(自然科学版),25(3):43-47
唐晶磊.2010.喷药机器人杂草识别与导航参数获取方法研究.[博士学位论文].杨凌.西北农林科技大学
田有文,张长水,李成华.2004.支持向量机在植物病斑形状识别中的应用研究.农业工程学报,20(3):134-136
田有文.2005.叶部病害计算机图像识别方法的研究.[博士学位论文].沈阳.沈阳农业大学
田有文,张长水,李成华,等.2007.基于支持向量机的葡萄病害图像识别方法.农业工程学报,23(6):175-178
田有文,李天来,张琳,等.2010.高光谱图像技术诊断温室黄瓜病害的方法.农业工程学报,26(5):202-20
温芝元,曹乐平.2012.基于补偿模糊神经网络的脐橙不同病虫害图像识别.农业工程学报,28(11):152-156
武深秋.2004.苹果斑点落叶病的防治[J].河北果树,(5):36
吴书有.2009.基于振动信号分析方法的电力变压器状态监测与故障诊断研究.[博士学位论文].合肥.中国科学技术大学
吴献超,刘莎,闰琳,等.2009.基于小波子带能量加权的人脸识别方法.宁波大学学报(理工版),22（2）:207-211
王大凯,侯榆青,彭进业.2008.图像处理的偏微分方程方法.北京:科学出版社,208-210
王国平,竇连登.2002.果树病虫害诊断与防治原色图谱.北京:金盾出版社
王建宇,张峰,周献中,史迎春,骆文.2006.利用小波变换和K均值聚类实现字幕区域分割.计算机辅助设计与图形学学报,18(10):1508-1512
王克如.2005.基于图像识别的作物病虫草害诊断研究.[博士学位论文].北京.中国农业科学院
王娜,王克如,谢瑞芝,等.2009.基于Fisher判别分析的玉米叶部病害图像识别.中国农业科学,42(11):3836-3842
王守志,何东健,李文,等.2009.基于核K-均值聚类算法的植物叶部病害识别.农业机械学报,40(3):152-155
王守志,何东健,韩金玉.2011.基于并行点火ＰＣＮＮ的玉米病害彩色图像分割方法.农业机械学报,42(11):148-153
王小平,曹立明.2000.遗传算法-理论、应用与软件实现.西安:西安交通大学出版社,28-51
王昱洁.2011.音频隐写分析机理与关键技术研究.[博士学位论文].合肥.中国科学技术大学
项荣,应义斌,蒋焕煜,等.2012.基于边缘曲率分析的重叠番茄识别.农业机械学报,43(3):157-162
熊雪梅,姬长英,Claudio Moraga.2004.基于参数化遗传神经网络的植物病害预测方法.农业机械学报,35(6):110-114
熊勇.2005.粒子群优化算法的行为分析与应用实例.[博士学位论文].杭州.浙江大学
许高凤,丁士圻,郭丽华,等.2009.基于小波的人脸去光照识别算法研究.系统仿真学报,21(14):4362-4366
徐贵力,毛罕平,李萍萍.2002.缺素叶片彩色图像颜色特征提取的研究.农业工程学报,18(4):150-154
徐琨,李燕.2005.基于分块颜色矩和纹理特征的图像检索方法.西安石油大学学报(自然科学版),20(2):77-79
许学斌,张德运,张新曼,等.2009.基于特征层和二代曲波变换的多模生物特征融合识别方法.西安交通大学学报,43(10):32-36
许相莉.基于智能计算的图像检索算法研究.[博士学位论文].长春:吉林大学,2011
谢强军.2009.变分水平集理论及其在医学图像分割中的应用.[博士学位论文].杭州.浙江大学
余建英，何旭宏.2003.数据统计分析与SPSS应用.北京:人民邮电出版社,87-89
尹秀珍.2011.低分辨率苹果果实病害图像识别方法研究.[硕士学位论文].杨凌.西北农林科技大学
袁媛,李淼,梁青,等.2011.基于水平集的作物病叶图像分割方法.农业工程学报,27(2):208-211
杨蜀秦,宁纪锋,何东健.2010.一种基于主动轮廓模型的连接米粒图像分割算法.农业工程学报,2010,26(2):207-211
赵玉霞,王克如,白中英,李少昆,谢瑞芝,高世菊.2007.基于图像识别的玉米叶部病害诊断研究.中国农业科学,40(4):698-703
朱景福.2009.基于小波收缩与各向异性扩散及其等价性的图像去噪与分割.[博士学位论文].哈尔滨.哈尔滨工程大学
郑向伟.2008.求解优化问题的微粒群算法及其应用研究.[博士学位论文].济南.山东师范大学
张静,王双喜,董晓志,等.2006.基于温室植物叶片纹理的病害图像处理及特征值提取方法的研究.沈阳农业大学学报,37(3):282-285
张开华.2009.主动轮廓模型在图像分割中的应用研究.[硕士学位论文].合肥.中国科学技术大学
张敏,朱庆生,杨方云,等.2008.柑桔溃疡病自动识别方法及其仿真研究.系统仿真学报,20(8):2056-2058
张亚静,李民赞,刘刚,等.2009.基于机器视觉和信息融合的邻接苹果分割算法.农业机械学报,40(11):180-183
Andreas Koschan Mongi Abidi章毓晋(译).2009.彩色数字图像处理.北京:清华大学出版社,54-58
穗波信雄.1989.根据图像提取植物的生长信息.农业机械学会关西支部第6次支部研究资料,10:1-2
Kenneth.R.Castalman.1996.Digital Image Processing.Prentice hall.朱志刚,林学阎,石定机等译.2002.北京:电子工业出版社
Ahmad I S, Reid J F.1996. Evaluation of colour representations for maize images. Journal of AgriculturalEngineering Research,63:185-196
Astola J,Haavisto P,Neuvo Y.1990. Vector median filter. Processing of the IEEE,78:678-689.
Aitkenhead M J, Dalgetty I A, Mullins C E, Mcdonald A, Strachan N.2003.Weed and crop discriminationusing image analysis and artificial intelligence methods. Computers and Electronics in Agriculture,39(3):157-171
BurksT F,Sheare S A,Heath J R,et al.2005.Evaluation of neural-network classifiers for weeds speciesdiscrimination.Bio-systems Engineering,91(3):293-304
Burks T F,Shearer S A, Payne F A.2000. Classification of weed species using color texture features anddiscrimination analysis. Transcations of ASAE,43(2):441-448.
Camargo Neto,George.E.Meyer,David.DJones,Ashok.K.Salnal.2006. Plants species identification usingElliptic Fourier leaf shape analysis.Computers and Electronics in Agriculture,50(2):121-134
Caoa L J, Chuab K S, Chongc W K, et al.2003.A comparison of PCA, KPCA and ICA for dimensionalityreduction in support vector machine. Neurocomputing55,321-336
Chan T, Vese L. An active contour model without edges. Scale-Space Theories in Computer Vision,1999,1682:141-151
Chan T, Yezrielev Sandberg B, Vese L.2001. Active contours without edges for vector-valued images. IEEETransactions on Image Processing,11(2):266-277
Chesmore D, Bemard T,Inman A J,et al.2003.Image analysis for the identification of the quarantine pestTilletia indica, EPPO Bulletin,33(3):495-499
Cormen T H, Leiserson C E, Rivest R L. An introduction to generic algorithms. MIT Press,2000:527-532
Cui D, Zhang O, Li M Z,et al.2009. Detection of soybean rust using a multispectral image sensor.Sensingand Instrumentation for Food Quality and Safety,3(1):49-56
Dash M, Choi K, Scheuermann P, Liu H.2002.Feature selection for clustering-a filter solution.Proc.SecondInt’l Conf.Data Mining,115-122
Eberhart R C and Shi Y.2004.Guest Editorial Special issue on particle swarm optimization.IEEETransaction on evolutionary computation,8(3):201-203
Erikssons J, Koivunen V.2006. Complex random vectors and ICA models:identifiability, uniqueness,andseparability. IEEE Trans on Information Theory,52(3):1017-1029
Evans L C, Gariepy R F.1992. Measure theory and fine properties of functions. Ohio: CRC Press
He D J,Shao J M, Gen N, et al.2007.A model for image categorisation based on a biological visualmechanism.New Zealand Journal of Agricultural Research,50:781-787
He D J, Liu S W, Liang X H,et al.2011.Improved saliency toolbox/Itti model for region of interestextraction. Opt. Eng.50(9),097202
Hsu C W, Lin C J.2002.A comparison of methods for multi-class support vector machines. IEEETransactions on Neural Networks,13(2):415-425
Hu Q X,Tian J,He D J.2011.Plant leaf disease recognition based on PSO-SVM algorithm.ICIC ExpressLetters, l5(9A):3183-3188
Huang K Y.2007.Application of artificial neural network for detecting Phalaenopsis seedling diseasesusing color and texture features. Computers and Electronics in Agriculture,57(1):3-11
Huanga Y, Lanb Y, Thomsona S J, et al.2010.Development of soft computing and applications inagricultural and biological engineering.Computers and Electronics in Agriculture71,107-127
Huerta E B, Beatrice D, Hao J K.2006.A hybrid GA/SVM approach for gene selection and classification ofmicro array data. Lecture Notes in computer Science,3907:34-44
Karimi Y, Prasher S O, Patel R M, Kim S H.2006.Application of support vector machine technology forweed and nitrogen stress detection in corn.Computers and electronics in agriculture,(51):99-109
Keerthi S S and Lin C J. Asymptotic behaviors of support vector machines withGaussian kernel. NeuralComputation,2003,15(7):1667-1689
Kijsirikul B and Ussivakul N.2002.Multiclass support vector machines using adaptive directed acyclicgraph. In Proceedings of International Joint Conference on Neural Networks,980-985
Lee H M, Chen C M, Chen J M, Jou Y L.2001.An efficient fuzzy classifier with feature selection based onfuzzy entropy.IEEE Trans.on systems and cybernetics-Part B:Cybernetics,31(3):26-432
Lee K Y, ESharkawi M A.2002. Modern heuristic optimization techniques with applications to powersystems. IEEE Power Engineering Society,45-51
Li B N, Chui C K, Chang S, et al.2011.Integrating spatial fuzzy clustering with level set methods forautomated medical image segmentation.Computers in Biology and Medicine,41(1):1-10
Li C, Kao C, Gore J C, and Ding Z.2008.Minimization of region-scalable fitting energy for imagesegmentation. IEEE Transaction on Image Processing,17(10):1940-1949
Li C M, Kao C Y, Gore J, et al.2007. Implicit Active Contours Driven by Local Binary Fitting Energy.In:Computer Vision and Pattern Recognition, CVPR '07. IEEE Conference on. Minneapolis, Minnesota,USA. Ieee:1-7
Li C M,Xu C Y, Senior Member, et al.2010.Distance regularized level set evolution and its application toimage segmentation.IEEE Transaction on Image Processing,19(12):3243-3254
Li Y F,Zhu Q S,Cao Y K.2007.Segmentation of agriculture products images by fuzzy art.http://www.google.com.hk/search?hl=zh&source=hp&q=image+Segmentation+agriculture&btnG=Google+%E6%90%9C%E7%B4%A2&gbv=2
Lie J, Lysaker M, Tai X C.2006. A binary level set model and some applications to mumford-shah imagesegmentation.IEEE Transaction on Image Processing,15(5):1171-1181
Liu G, Shen H Y, Yang X H, et al.2005. Research on prediction about fruit tree diseases and insect pestsbased on neural network. Artificial Intelligence Applications and Innovations,187:731-740
Liu H, Yu L.2005.Toward integrating feature selection algorithms for classification and clustering[J].IEEETransactions on Knowledge and Data Engineering,17(4):491-502
Liu J H.2009.Improvement and the basic theory of particle swarm optimization. Changsha：Central SouthUniversity,22-27
Liu Y, Zheng Y F.2005.One-against-all multi-Class SVM classification using reliability measures.Proceedings of the2005International Joint Conference on Neural Networks. Mont real,Canada
Luo Y H, Fu C Y.2011.Midfrequency-based real-time blind image restoration via independent componentanalysis and genetic algorithms. Opt. Eng.50(4),047004
Mark J L, Michael K N, Cheung Y M, et al.2008. Agglomerative fuzzy K-means clustering algorithm withselection of number of cluster. IEEE Transactions on Knowledge and Data Engineering,20(11):1519-1534
Martin D P, Rybicki E P.1998. Microcomputer-based quantification of maize streak virus symptoms in zeamays. Phytopathology,88(5):422-427
Mei S Y, Liu Y, Wu G F, et al.2005. Rough reducts based SVM ensemble.Gordon Research Conference.New Hampshire:[s. n.],571-574
Michael Ferris and Todd Munson.2003.Interior point methods for massive support vector machines.SIAMJournal on Optimization,13(3):783-804
Miriam Lindenthal,Ulrike Steiner, et a1.2005.Effect of downy mildew development oil transpiration ofcucumber leaves visualized by digital infrared thermography.The American Phytopathological society,95(3):233-240
Muller K R, Mika S, Ratsch G,et al.2001.An introduction to kernel-based learning algorithms. IEEE TransNeural Network,12:181-201
Mumford D, Shah J.1989. Optimal approximations by piecewise smooth functions and associatedvariational problems. Communications on pure and applied mathematics,42(5):577-685
Paschos G.2000. Fast color texture recognition using chromaticity moments. Pattern Recognition Letters,21:837-841
Patil J K, Kumar R.2011. Advances in image processing for detection of plant diseases.Journal ofAdvanced Bioinformatics Applications and Research,2(2):135-141
Phetkaew T, KIJ Sirikul B, Rivepiboon W.2003.Reordering adaptive directed acyclic graphs: an improvedalgorithm for multiclass support vector machines.Proceedings of the2003International JointConference on Neural Networks. Portland,OR,USA
Pydipati R, Burks T F, Lee W S.2006.Identification of citrus disease using color texture features anddiscriminant analysis. Computers and Electronics in Agriculture,52:49-59
Qiao L Y, Peng X Y, Ma Y T.2006. GA-SVM wrapper for feature subset selection. Journal of ElectronicMeasurement and Instrument,20(1):1-4
Reyes M and Coello C.2006.Multi-objective particle swarm optimizers: A survey of the state-of-the-art.International Journal of Computational Intelligence Research,3(2):287-308
Ruiz L A, Recio J A, Fernández-Sarría A, et al.2011. A feature extraction software tool for agriculturalobject-based image analysis. Computers and Electronics in Agriculture76,284-296
Sankarana S, Mishraa A, Ehsani R, et al.2010. A review of advanced techniques for detecting plantdiseases, Computers and Electronics in Agriculture72,1-13
Sanyal P, Patel S C.2008.Pattern recognition method to detect two diseases in rice plants. Appliedengineering in agriculture,56(6):319-325
Sena Jr D G, Pinto F A C, Queiroz D M, Viana P A.2003.Fall armyworm damaged maize plantidentification using digital images.Biosystems Engineering,85(4):449-454
Shatadal P, Tan J.2003.Identifying damaged soybeans by color image analysis. Applied Engineering inAgriculture,19(1):65-69
Solberg A H S, Jain A K.1997.Texture fusion and feature selection applied to SAR imagery.IEEE Trans onGeosciences and Remote Sensing,35(2):475-479
Somol P,Novovivova J,Pudil P.2006.Flexible-hybrid sequential floating search in statistical featureselection. Lecture Notes in Computer Science, Berlin:Springer-Verlag,632-639
Tian Z, Duan C J, Yuan K H, et al.2010. A texture feature-based method for dynamic organ tracking.International Journal of Innovative Computing, Information and Control,6(12):5697-5708
Wahba G, Lin Y, Zhang H, et al.2000.Generalized approximate cross validation for support vectormachines or another way to look at margin quantities. Advances in Large Margin Classifiers.MITPress,297-209
Yang C X, and Wang N.2011.On the improvements of particle swarm optimization for global optimization.ICIC Express Letters,5(3):809-815
Yang J, Honavar V.1998.Feature subset selection using a genetic algorithm.Intelligent System and TheirApplications,IEEE,13(2):44-49
Yang Z,Rao M N,Elliott N C,et al.2005. Using ground-based multispectral radiometry to detect stress inwheat caused by geenbug (Homoptera:Aphididae) infestation.Computers and electronics in agriculture,47:121-135
Yutake S, Tsuguo O, Kenji I, et al.1999. Automatic diagnosis of plant diseases. Journal of TSAM,6l(2):119-126
Zhang M H, Lv J Q, Yang J.2011.Human detection using relational color similarity features.Opt. Eng.,50(9),097201
Zhang X, Li D L, Yang W ZH, et al.2011. A fast segmentation method for high-resolution color images offoreign fibers in cotton.Computers and Electronics in Agriculture,78:71-79
Zheng L Y, Zhang J T, Wang Q Y.2009. Mean-shift-based color segmentation of images containing greenvegetation. Computers and Electronics in Agriculture,65:93-98
边肇祺,张学工等.2000.模式识别.北京:清华大学出版社,296-304
蔡鸿昌,崔海信,宋卫堂等.2006.辣椒初花期叶片光合色素含量与颜色特征的初步研究.农业工程学报,22(9):34-38
崔艳丽,程鹏飞,董晓志,等.2005.温室植物病害的图像处理及特征值提取方法的研究.农业工程学报,21(增刊):32-34
邓继忠,李敏,袁之报,等.2012.基于图像识别的小麦腥黑穗病害特征提取与分类.农业工程学报,28(3):172-175
陈武凡.2002.小波分析及其在图像处理中的应用.北京:科学出版社,156-160
刁智华.2010.大田小麦叶部病害智能诊断系统研究与应用.[博士学位论文].合肥.中国科学技术大学
关海鹏,许少华,谭峰.2010.基于遗传模糊神经网络的植物病斑区域图像分割模型.农业机械学报,41(11):163-167
冯洁,廖宁放,赵波,等.2008.多光谱成像技术诊断植物病虫害的人工神经网络模型.光学技术,34(5):717-720
葛婧.2007.基于计算机图像处理技术的作物病害等级检测.[硕士学位论文].合肥.安徽农业大学
葛婧,邵陆寿,丁克坚,等.2008.玉米小斑病病害程度图像检测.农业机械学报,39(1):114-117
耿楠,于伟,宁纪锋.2011.基于水平集和先验信息的农业图像分割方法.农业机械学报,42(9):167-172
郭文强.2009数字图像处理.西安:西安电子科技大学出版社
何东健,耿楠,张义宽.2008.数字图像处理(第二版).西安:西安电子科技大学出版社,32-37
韩殿元,黄心渊,付慧.2012.基于彩色通道相似性图像分割方法的植物叶面积计算.农业工程学报,28(6):179-182
霍海娥,霍海波,杨长生.2010.SOFC的支持向量机（SVM）辨识建模.系统仿真学报,22(6):1557-1560
胡秋霞,田杰,何东健,等.2012.基于改进型C-V模型的植物病斑图像分割.农业机械学报,43(5):157-161
黄元元,刘宁钟.2012.一种新的基于颜色特征的图像检索方法.小型微型计算机系统,33(3):609-613
黄志开.2006.彩色图像特征提取与植物分类研究.[博士学位论文].合肥.中国科学技术大学
冀荣华,祁力钧,傅泽田.2007.自动对靶施药系统中植物病害识别技术的研究.农业机械学报,38(6):190-192
李冠林,马占鸿,黄冲等.2010.基于K_means硬聚类算法的葡萄病害彩色图像分割方法.农业工程学报,26(2):32-36（增刊）
赖军臣,李少昆,明博,等.2009.作物病害机器视觉诊断研究进展.中国农业科学,42(4):1215-1221
龙满生,何东健.2007.玉米苗期杂草的计算机识别技术研究.农业工程学报,23(7):139-143
吕强,蔡健荣,赵杰文,等.2010.自然场景下树上柑橘实时识别技术.农业机械学报,41(2):185-188
刘树文,王庆伟,何东健,等.2006.基于模糊神经网络的葡萄病害诊断系统研究.农业工程学报,22(9):144-147
刘晴蕊,何东健,张宏鸣,朱珊娜,郭云忠.2011.苹果病害智能诊断方法研究与设计.农机化研究,33(4):76-78
刘志华,程鹏飞.2006.辣椒侵染性病害图像处理及特征值提取方法的研究.山西农业大学学报,26(3):351-354
李峥嵘,刘月娥,何东健,等.2007.基于内容的小麦害虫图像检索系统研究与实现.农业工程学报,23(11):210-214
李岳阳.2010.彩色图像滤波算法的研究.[博士学位论文].无锡.江南大学
李宗儒.2010.基于图像分析的苹果病害识别技术研究.[硕士学位论文].杨凌.西北农林科技大学
毛罕平,徐贵力,李萍萍.2003a.番茄缺素叶片的图像特征提取和优化选择研究.农业工程学报,19(2):133-136
毛罕平,徐贵力,李萍萍.2003b.基于计算机视觉的番茄营养元素亏缺的识别.农业机械学报,34(2):73-75
毛罕平,张艳诚,胡波.2008.基于模糊C均值聚类的作物病害叶片图像分割方法研究.农业工程学报,24(9:136-140
毛亮,薛月菊,孔德运,等.2011.基于稀疏场水平集的荔枝图像分割算法.农业工程学报,27(4):345-349
马晓丹,祁广云.2006.基于神经网络的大豆叶片病斑的识别与研究.黑龙江八一农垦大学学报,18(2):84-87
宁纪锋,吴成柯,姜光,等.2008.基于偏微分方程和分水岭算法的图像分割.模式识别与人工智能,21(5):664-669
祁广云,马晓丹,关海鸥.2009.采用改进遗传算法提取大豆叶片病斑图像.农业工程学报,25(5):142-144
房俊龙,张长利,潘伟,等.2004.用遗传算法训练的人工神经网络识别番茄生理病害果.农业工程学报,20(3):113-116
潘振宽,李华,魏伟波,等.2009.三维图像多相分割的变分水平集方法.计算机学报,32(12):2464-2473.
任传贤2010.面向人脸识别的快速特征提取与稀疏表示方法研究.[博士学位论文].广州.中山大学
任东.2007.基于支持向量机的植物病害识别研究.[博士学位论文].吉林.吉林大学
宋凯,孙晓艳,纪建伟.2007.基于支持向量机的玉米叶部病害识别.农业工程学报,23(1):156-157
孙国祥,汪小旵,何国敏.2010.基于边缘链码信息的番茄苗重叠叶面分割算法.农业工程学报,26(12):206-210
石磊,王红军,吴国新.2010.基于小波包分析的旋转机械故障诊断研究.北京信息科技大学学报(自然科学版),25(3):43-47
唐晶磊.2010.喷药机器人杂草识别与导航参数获取方法研究.[博士学位论文].杨凌.西北农林科技大学
田有文,张长水,李成华.2004.支持向量机在植物病斑形状识别中的应用研究.农业工程学报,20(3):134-136
田有文.2005.叶部病害计算机图像识别方法的研究.[博士学位论文].沈阳.沈阳农业大学
田有文,张长水,李成华,等.2007.基于支持向量机的葡萄病害图像识别方法.农业工程学报,23(6):175-178
田有文,李天来,张琳,等.2010.高光谱图像技术诊断温室黄瓜病害的方法.农业工程学报,26(5):202-20
温芝元,曹乐平.2012.基于补偿模糊神经网络的脐橙不同病虫害图像识别.农业工程学报,28(11):152-156
武深秋.2004.苹果斑点落叶病的防治[J].河北果树,(5):36
吴书有.2009.基于振动信号分析方法的电力变压器状态监测与故障诊断研究.[博士学位论文].合肥.中国科学技术大学
吴献超,刘莎,闰琳,等.2009.基于小波子带能量加权的人脸识别方法.宁波大学学报(理工版),22（2）:207-211
王大凯,侯榆青,彭进业.2008.图像处理的偏微分方程方法.北京:科学出版社,208-210
王国平,竇连登.2002.果树病虫害诊断与防治原色图谱.北京:金盾出版社
王建宇,张峰,周献中,史迎春,骆文.2006.利用小波变换和K均值聚类实现字幕区域分割.计算机辅助设计与图形学学报,18(10):1508-1512
王克如.2005.基于图像识别的作物病虫草害诊断研究.[博士学位论文].北京.中国农业科学院
王娜,王克如,谢瑞芝,等.2009.基于Fisher判别分析的玉米叶部病害图像识别.中国农业科学,42(11):3836-3842
王守志,何东健,李文,等.2009.基于核K-均值聚类算法的植物叶部病害识别.农业机械学报,40(3):152-155
王守志,何东健,韩金玉.2011.基于并行点火ＰＣＮＮ的玉米病害彩色图像分割方法.农业机械学报,42(11):148-153
王小平,曹立明.2000.遗传算法-理论、应用与软件实现.西安:西安交通大学出版社,28-51
王昱洁.2011.音频隐写分析机理与关键技术研究.[博士学位论文].合肥.中国科学技术大学
项荣,应义斌,蒋焕煜,等.2012.基于边缘曲率分析的重叠番茄识别.农业机械学报,43(3):157-162
熊雪梅,姬长英,Claudio Moraga.2004.基于参数化遗传神经网络的植物病害预测方法.农业机械学报,35(6):110-114
熊勇.2005.粒子群优化算法的行为分析与应用实例.[博士学位论文].杭州.浙江大学
许高凤,丁士圻,郭丽华,等.2009.基于小波的人脸去光照识别算法研究.系统仿真学报,21(14):4362-4366
徐贵力,毛罕平,李萍萍.2002.缺素叶片彩色图像颜色特征提取的研究.农业工程学报,18(4):150-154
徐琨,李燕.2005.基于分块颜色矩和纹理特征的图像检索方法.西安石油大学学报(自然科学版),20(2):77-79
许学斌,张德运,张新曼,等.2009.基于特征层和二代曲波变换的多模生物特征融合识别方法.西安交通大学学报,43(10):32-36
许相莉.基于智能计算的图像检索算法研究.[博士学位论文].长春:吉林大学,2011
谢强军.2009.变分水平集理论及其在医学图像分割中的应用.[博士学位论文].杭州.浙江大学
余建英，何旭宏.2003.数据统计分析与SPSS应用.北京:人民邮电出版社,87-89
尹秀珍.2011.低分辨率苹果果实病害图像识别方法研究.[硕士学位论文].杨凌.西北农林科技大学
袁媛,李淼,梁青,等.2011.基于水平集的作物病叶图像分割方法.农业工程学报,27(2):208-211
杨蜀秦,宁纪锋,何东健.2010.一种基于主动轮廓模型的连接米粒图像分割算法.农业工程学报,2010,26(2):207-211
赵玉霞,王克如,白中英,李少昆,谢瑞芝,高世菊.2007.基于图像识别的玉米叶部病害诊断研究.中国农业科学,40(4):698-703
朱景福.2009.基于小波收缩与各向异性扩散及其等价性的图像去噪与分割.[博士学位论文].哈尔滨.哈尔滨工程大学
郑向伟.2008.求解优化问题的微粒群算法及其应用研究.[博士学位论文].济南.山东师范大学
张静,王双喜,董晓志,等.2006.基于温室植物叶片纹理的病害图像处理及特征值提取方法的研究.沈阳农业大学学报,37(3):282-285
张开华.2009.主动轮廓模型在图像分割中的应用研究.[硕士学位论文].合肥.中国科学技术大学
张敏,朱庆生,杨方云,等.2008.柑桔溃疡病自动识别方法及其仿真研究.系统仿真学报,20(8):2056-2058
张亚静,李民赞,刘刚,等.2009.基于机器视觉和信息融合的邻接苹果分割算法.农业机械学报,40(11):180-183
Andreas Koschan Mongi Abidi章毓晋(译).2009.彩色数字图像处理.北京:清华大学出版社,54-58
穗波信雄.1989.根据图像提取植物的生长信息.农业机械学会关西支部第6次支部研究资料,10:1-2
Kenneth.R.Castalman.1996.Digital Image Processing.Prentice hall.朱志刚,林学阎,石定机等译.2002.北京:电子工业出版社
Ahmad I S, Reid J F.1996. Evaluation of colour representations for maize images. Journal of AgriculturalEngineering Research,63:185-196
Astola J,Haavisto P,Neuvo Y.1990. Vector median filter. Processing of the IEEE,78:678-689.
Aitkenhead M J, Dalgetty I A, Mullins C E, Mcdonald A, Strachan N.2003.Weed and crop discriminationusing image analysis and artificial intelligence methods. Computers and Electronics in Agriculture,39(3):157-171
BurksT F,Sheare S A,Heath J R,et al.2005.Evaluation of neural-network classifiers for weeds speciesdiscrimination.Bio-systems Engineering,91(3):293-304
Burks T F,Shearer S A, Payne F A.2000. Classification of weed species using color texture features anddiscrimination analysis. Transcations of ASAE,43(2):441-448.
Camargo Neto,George.E.Meyer,David.DJones,Ashok.K.Salnal.2006. Plants species identification usingElliptic Fourier leaf shape analysis.Computers and Electronics in Agriculture,50(2):121-134
Caoa L J, Chuab K S, Chongc W K, et al.2003.A comparison of PCA, KPCA and ICA for dimensionalityreduction in support vector machine. Neurocomputing55,321-336
Chan T, Vese L. An active contour model without edges. Scale-Space Theories in Computer Vision,1999,1682:141-151
Chan T, Yezrielev Sandberg B, Vese L.2001. Active contours without edges for vector-valued images. IEEETransactions on Image Processing,11(2):266-277
Chesmore D, Bemard T,Inman A J,et al.2003.Image analysis for the identification of the quarantine pestTilletia indica, EPPO Bulletin,33(3):495-499
Cormen T H, Leiserson C E, Rivest R L. An introduction to generic algorithms. MIT Press,2000:527-532
Cui D, Zhang O, Li M Z,et al.2009. Detection of soybean rust using a multispectral image sensor.Sensingand Instrumentation for Food Quality and Safety,3(1):49-56
Dash M, Choi K, Scheuermann P, Liu H.2002.Feature selection for clustering-a filter solution.Proc.SecondInt’l Conf.Data Mining,115-122
Eberhart R C and Shi Y.2004.Guest Editorial Special issue on particle swarm optimization.IEEETransaction on evolutionary computation,8(3):201-203
Erikssons J, Koivunen V.2006. Complex random vectors and ICA models:identifiability, uniqueness,andseparability. IEEE Trans on Information Theory,52(3):1017-1029
Evans L C, Gariepy R F.1992. Measure theory and fine properties of functions. Ohio: CRC Press
He D J,Shao J M, Gen N, et al.2007.A model for image categorisation based on a biological visualmechanism.New Zealand Journal of Agricultural Research,50:781-787
He D J, Liu S W, Liang X H,et al.2011.Improved saliency toolbox/Itti model for region of interestextraction. Opt. Eng.50(9),097202
Hsu C W, Lin C J.2002.A comparison of methods for multi-class support vector machines. IEEETransactions on Neural Networks,13(2):415-425
Hu Q X,Tian J,He D J.2011.Plant leaf disease recognition based on PSO-SVM algorithm.ICIC ExpressLetters, l5(9A):3183-3188
Huang K Y.2007.Application of artificial neural network for detecting Phalaenopsis seedling diseasesusing color and texture features. Computers and Electronics in Agriculture,57(1):3-11
Huanga Y, Lanb Y, Thomsona S J, et al.2010.Development of soft computing and applications inagricultural and biological engineering.Computers and Electronics in Agriculture71,107-127
Huerta E B, Beatrice D, Hao J K.2006.A hybrid GA/SVM approach for gene selection and classification ofmicro array data. Lecture Notes in computer Science,3907:34-44
Karimi Y, Prasher S O, Patel R M, Kim S H.2006.Application of support vector machine technology forweed and nitrogen stress detection in corn.Computers and electronics in agriculture,(51):99-109
Keerthi S S and Lin C J. Asymptotic behaviors of support vector machines withGaussian kernel. NeuralComputation,2003,15(7):1667-1689
Kijsirikul B and Ussivakul N.2002.Multiclass support vector machines using adaptive directed acyclicgraph. In Proceedings of International Joint Conference on Neural Networks,980-985
Lee H M, Chen C M, Chen J M, Jou Y L.2001.An efficient fuzzy classifier with feature selection based onfuzzy entropy.IEEE Trans.on systems and cybernetics-Part B:Cybernetics,31(3):26-432
Lee K Y, ESharkawi M A.2002. Modern heuristic optimization techniques with applications to powersystems. IEEE Power Engineering Society,45-51
Li B N, Chui C K, Chang S, et al.2011.Integrating spatial fuzzy clustering with level set methods forautomated medical image segmentation.Computers in Biology and Medicine,41(1):1-10
Li C, Kao C, Gore J C, and Ding Z.2008.Minimization of region-scalable fitting energy for imagesegmentation. IEEE Transaction on Image Processing,17(10):1940-1949
Li C M, Kao C Y, Gore J, et al.2007. Implicit Active Contours Driven by Local Binary Fitting Energy.In:Computer Vision and Pattern Recognition, CVPR '07. IEEE Conference on. Minneapolis, Minnesota,USA. Ieee:1-7
Li C M,Xu C Y, Senior Member, et al.2010.Distance regularized level set evolution and its application toimage segmentation.IEEE Transaction on Image Processing,19(12):3243-3254
Li Y F,Zhu Q S,Cao Y K.2007.Segmentation of agriculture products images by fuzzy art.http://www.google.com.hk/search?hl=zh&source=hp&q=image+Segmentation+agriculture&btnG=Google+%E6%90%9C%E7%B4%A2&gbv=2
Lie J, Lysaker M, Tai X C.2006. A binary level set model and some applications to mumford-shah imagesegmentation.IEEE Transaction on Image Processing,15(5):1171-1181
Liu G, Shen H Y, Yang X H, et al.2005. Research on prediction about fruit tree diseases and insect pestsbased on neural network. Artificial Intelligence Applications and Innovations,187:731-740
Liu H, Yu L.2005.Toward integrating feature selection algorithms for classification and clustering[J].IEEETransactions on Knowledge and Data Engineering,17(4):491-502
Liu J H.2009.Improvement and the basic theory of particle swarm optimization. Changsha：Central SouthUniversity,22-27
Liu Y, Zheng Y F.2005.One-against-all multi-Class SVM classification using reliability measures.Proceedings of the2005International Joint Conference on Neural Networks. Mont real,Canada
Luo Y H, Fu C Y.2011.Midfrequency-based real-time blind image restoration via independent componentanalysis and genetic algorithms. Opt. Eng.50(4),047004
Mark J L, Michael K N, Cheung Y M, et al.2008. Agglomerative fuzzy K-means clustering algorithm withselection of number of cluster. IEEE Transactions on Knowledge and Data Engineering,20(11):1519-1534
Martin D P, Rybicki E P.1998. Microcomputer-based quantification of maize streak virus symptoms in zeamays. Phytopathology,88(5):422-427
Mei S Y, Liu Y, Wu G F, et al.2005. Rough reducts based SVM ensemble.Gordon Research Conference.New Hampshire:[s. n.],571-574
Michael Ferris and Todd Munson.2003.Interior point methods for massive support vector machines.SIAMJournal on Optimization,13(3):783-804
Miriam Lindenthal,Ulrike Steiner, et a1.2005.Effect of downy mildew development oil transpiration ofcucumber leaves visualized by digital infrared thermography.The American Phytopathological society,95(3):233-240
Muller K R, Mika S, Ratsch G,et al.2001.An introduction to kernel-based learning algorithms. IEEE TransNeural Network,12:181-201
Mumford D, Shah J.1989. Optimal approximations by piecewise smooth functions and associatedvariational problems. Communications on pure and applied mathematics,42(5):577-685
Paschos G.2000. Fast color texture recognition using chromaticity moments. Pattern Recognition Letters,21:837-841
Patil J K, Kumar R.2011. Advances in image processing for detection of plant diseases.Journal ofAdvanced Bioinformatics Applications and Research,2(2):135-141
Phetkaew T, KIJ Sirikul B, Rivepiboon W.2003.Reordering adaptive directed acyclic graphs: an improvedalgorithm for multiclass support vector machines.Proceedings of the2003International JointConference on Neural Networks. Portland,OR,USA
Pydipati R, Burks T F, Lee W S.2006.Identification of citrus disease using color texture features anddiscriminant analysis. Computers and Electronics in Agriculture,52:49-59
Qiao L Y, Peng X Y, Ma Y T.2006. GA-SVM wrapper for feature subset selection. Journal of ElectronicMeasurement and Instrument,20(1):1-4
Reyes M and Coello C.2006.Multi-objective particle swarm optimizers: A survey of the state-of-the-art.International Journal of Computational Intelligence Research,3(2):287-308
Ruiz L A, Recio J A, Fernández-Sarría A, et al.2011. A feature extraction software tool for agriculturalobject-based image analysis. Computers and Electronics in Agriculture76,284-296
Sankarana S, Mishraa A, Ehsani R, et al.2010. A review of advanced techniques for detecting plantdiseases, Computers and Electronics in Agriculture72,1-13
Sanyal P, Patel S C.2008.Pattern recognition method to detect two diseases in rice plants. Appliedengineering in agriculture,56(6):319-325
Sena Jr D G, Pinto F A C, Queiroz D M, Viana P A.2003.Fall armyworm damaged maize plantidentification using digital images.Biosystems Engineering,85(4):449-454
Shatadal P, Tan J.2003.Identifying damaged soybeans by color image analysis. Applied Engineering inAgriculture,19(1):65-69
Solberg A H S, Jain A K.1997.Texture fusion and feature selection applied to SAR imagery.IEEE Trans onGeosciences and Remote Sensing,35(2):475-479
Somol P,Novovivova J,Pudil P.2006.Flexible-hybrid sequential floating search in statistical featureselection. Lecture Notes in Computer Science, Berlin:Springer-Verlag,632-639
Tian Z, Duan C J, Yuan K H, et al.2010. A texture feature-based method for dynamic organ tracking.International Journal of Innovative Computing, Information and Control,6(12):5697-5708
Wahba G, Lin Y, Zhang H, et al.2000.Generalized approximate cross validation for support vectormachines or another way to look at margin quantities. Advances in Large Margin Classifiers.MITPress,297-209
Yang C X, and Wang N.2011.On the improvements of particle swarm optimization for global optimization.ICIC Express Letters,5(3):809-815
Yang J, Honavar V.1998.Feature subset selection using a genetic algorithm.Intelligent System and TheirApplications,IEEE,13(2):44-49
Yang Z,Rao M N,Elliott N C,et al.2005. Using ground-based multispectral radiometry to detect stress inwheat caused by geenbug (Homoptera:Aphididae) infestation.Computers and electronics in agriculture,47:121-135
Yutake S, Tsuguo O, Kenji I, et al.1999. Automatic diagnosis of plant diseases. Journal of TSAM,6l(2):119-126
Zhang M H, Lv J Q, Yang J.2011.Human detection using relational color similarity features.Opt. Eng.,50(9),097201
Zhang X, Li D L, Yang W ZH, et al.2011. A fast segmentation method for high-resolution color images offoreign fibers in cotton.Computers and Electronics in Agriculture,78:71-79
Zheng L Y, Zhang J T, Wang Q Y.2009. Mean-shift-based color segmentation of images containing greenvegetation. Computers and Electronics in Agriculture,65:93-98
© 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 |