基于局部线性嵌入的降维算法研究及其在精准农业中的应用
|
摘要
传统的粗放型农业生产模式效率低下且对生态环境的污染严重,已经不适应新世纪农业发展的需求。现代农业逐渐摆脱原始农业、传统农业和工业化农业的束缚,进入以知识高度密集为主要特点的知识农业发展新阶段。将现代信息技术、生物技术和工程装备技术应用于农业生产的“精准农业(Precision Agriculture)"已经成为现代农业的重要生产形式。
将图像处理和机器视觉等技术的应用是精准农业实施中的主要特色之一。通过对光学图像或者高光谱图像的智能分析,有效提高作业效率。但是光学图像数据提供的信息有限,在很多应用中存在局限性。而高光谱遥感图像因为波段众多,光谱分辨率和空间分辨率都很高,因此对地物的分辨更加准确,在精准农业的应用中具有其他数据无法比拟的优势,已经成为未来精准农业应用中的主要数据形式。
这些新的数据分析手段虽然给农业生产带来了革命性的变化,但是另一方面也因为其数据量巨大,不仅给存储和传输带来了困难,同时也给数据的分析和处理带来了巨大的挑战。因此如何有效降低数据的维数,减少数据量是精准农业图像分析中的一个重要课题。本文主要研究局部线性嵌入算法在精准农业数据降维问题中的应用。结合精准农业实施中如杂草识别等问题的需要,主要围绕局部线性嵌入算法监督性的实现、近邻参数自适应选择、适当的分类算法的设计等问题进行了深入研究。主要的研究工作与创新成果如下：
(1)信息技术、模式识别技术在精准农业中的主要应用之一就是依据图像和光谱数据完成对作物属性的自动识别。而常规的局部线性嵌入算法是一种非监督算法,直接应用于分类识别中往往效果不佳。针对这个缺陷,提出一种基于Fisher准则的监督局部线性嵌入算法。算法首先对训练样本进行Fisher投影变换,寻找最佳投影方向。在此方向上各类样本具有最大可分性。利用训练样本在该投影轴上的投影距离来构造邻域结构,则可以最大程度得利用训练样本的监督信息指导降维,从而有效提高识别率。实验结果表明,基于Fisher准则的监督局部线性嵌入算法比常规局部线性嵌入算法具有更优异的降维效果,用简单的分类算法就可以实现较高的识别率。
(2)局部线性嵌入算法应用于分类识别问题时,其精度还受到另外一个因素的影响,即局部线性嵌入算法主要参数之一的近邻参数κ。该参数选择的恰当与否将严重影响识别结果。但是目前还没有特别成熟的选择算法出现,多数情况下是根据实验结果进行多次反复人工尝试。这也成为局部线性嵌入算法发展中的瓶颈。针对精准农业中所处理数据的特点以及局部线性嵌入算法邻域构造对识别效果的影响,设计一种基于监督局部线性嵌入方法的近邻参数自适应调整的算法。实验结果表明,该方法可以根据所采集数据的分布特点自动确定近邻参数,在保证高识别率的前提下又增强了算法的稳定性和实用性。
(3)降维算法只是数据处理的第一步,确保高识别率的另外一个重要环节是分类算法的选择。而局部线性嵌入算法对于新增测试样本必须和训练样本重新训练完成降维后才能进行分类,计算量大,效率低下。根据局部线性嵌入算法利用重构误差构造邻域结构的特点,将测试样本与正负类流形重构误差的大小作为判断训练样本类别属性的根据。这种分类方法是直接基于数据流形本身的特点构造的,又不需要引入新的未知参数,具有应用方便的特点。实验结果证实监督局部线性嵌入和这种分类算法的结合可以保证较高的识别精度。
(4)杂草识别是精准农业应用中的主要问题之一。因为自然界生物的多样性,即使同种植物形态颜色上也具有一定的差异,而异类植物却又可能具有相似性。利用传统的机器视觉方法,通过颜色,形态等特征识别精度不高,而且容易受到自然环境的影响。本文主要面向玉米田间实地采集的图像数据完成杂草识别任务。该组图像中环境很复杂,玉米和多种杂草共生。设计了根据形态学方法自动分割杂草和玉米的方法,然后利用监督局部线性嵌入对分割后的图像进行降维,并用支持向量机完成分类识别,最终取得了理想的实验结果。证明了基于Fisher准则的局部线性嵌入算法在非实验室环境下也具有很好的适应性。
(5)高光谱数据结合了光谱分析和图像处理的优势,在精准农业中的病虫害监测,品质检测等多个问题中都取得了成功的应用。针对实验室采集的患有条锈病的小麦叶片成像高光谱数据,根据“图谱合一”的思想,将一种图像纹理特征分析手段——灰度共生矩阵和光谱信息进行联合分析,充分利用了成像光谱数据的优势。实验结果表明,这种将传统图像分析手段和光谱数据结合的方法能够更好地发现作物受病害影响的程度,尤其是作物受病害影响初期或者称为隐性病时期,识别效果更优于传统的光谱分析方法。
China is a agricultural country with a population of billions, the problem of agriculture has always been one of the primary issue in the governments at all levels. Traditional agriculture in our country has been called the "intensive cultivation". This ensures our agriculture production have the advantages of higher per mu yield, but on the other hand, relying on artificial intensive cultivation purely must lead to low productivity problem. Modern agriculture is getting rid of the bondage of primitive agriculture、traditional agriculture and industrial agriculture, and entering into the knowledge agriculture development stage with the main characteristics of knowledge intensive.The Precision Agriculture which applied the modern information technology, biotechnology and engineering equipment technology applied in agricultural production has became the main production form of knowledge agriculture of every country in the new century.
When the image processing and machine vision technology are applied in the precision agriculture, the intelligent analysis result of the images can be used to guide the robot to accomplish some field works automatically, which can improve the efficiency rapidly. But the information in optical image data is limited, it is not enough for many applications. Hyperspectral remote sensing image having plenty of bands, high spectral resolution and high pixel resolution, therefore it can provide more accurate information of ground objects, which has incomparable advantage over other datas.And in recent years, its application in precision agriculture has become increasingly widespread. For example, by satellite remote sensing technology hundreds of hectares of land are measured out the fertility of different plots, and control the agricultural machinery to complete the quantitative fertilization according to the local situation; the spectrum characteristics of crops can also be captured utilizing the ground remote sensing device. And these information can used to distinguish weeds from crops or judge degree damaged by diseases. It is hard to achieved relying on traditional agricultural methods.
These new data analysis means has brought a revolutionary improvement to the agricultural production.But on the other hand,because of the huge datasize, not only the storage and transportation become a difficult task, but also the analysis and processing of datas have a greater challenges. So how to effectively reduce the dimension of data and the datasize is an important research subject in precision agriculture image analysis. This paper mainly studies the local linear embedding algorithm application to the problem of data dimension reduction in precision agriculture. Meeted the need of classification problem in the implementation of precision agriculture,such as weed identification, mainly around how to utilize the supervised information of learning samples in locally linear embedding algorithm, the adaptive selection of parameters, and the proper classification algorithm design were studied. The main research work and innovative results are as follows:
(1)The basic theory of manifold learning method and developments are introduced.The influence of neighbor parametes、intrinsic dimension、noise and other issues to the dimension reduction effect is researched. The characteristics of the manifold method which is used commonly are analyzed, and the sensitivity to the parameters of them is compared. A kind of important research issue in the precision agriculture is to complete the automatic identification of some properties of the crops by intellectual technology, which is the typical applications of information technology and pattern recognition in precision agriculture. But the conventional locally linear embedding algorithm is an unsupervised algorithm, so its application in identify crop variety or diseases directly are often ineffective. A supervisied local linear embedding algorithm based on Fisher criterion is proposed. Firstly,the Fisher projection was carried out on the training samples to find out the best projection direction,and different kind of samples in this direction has the maximum separability. The projection distance of training samples in this direction is used to construct the neighborhood structure, which can make use of the training samples' supervision information to instruct dimension reduction, so as to improve the recognition rate. The experimental results show that the supervied local linear embedding algorithm based on Fisher projection is more excellent than the conventional algorithm, so it can achieve high recognition rate only by some simple classification algorithm.
(2)After the supervision problem is solved,there is another factor will affect the identification precision when the locally linear embedding algorithm is applied to the identification problems in precision agriculture, namely the neighbor parameter which is one of the main parameters in locally linear embedding algorithm. Whether the selection of this parameter is appropriate will seriously affect the recognition result. And this parameter selection is directly related to the characteristics of the datasets processed. There is no mature theory to direct this selection method currently, in most cases,the selection is obtained according to the result of many repeated experiments artificially. It has become a bottleneck in the development of local linear embedding algorithm. Aiming at the characteristics of data processed in the precision agriculture and the influence of neighborhood structure to recognition effect, the adaptive algorithm based on the supervised locally linear embedding. The experimental results show that this algorithm can ascertain neighbor parameter automatically according to the distribution characteristics of the dataset, on the premise of guarantee to obtain high recognition rate the algorithm efficiency is improved, so practicability is enhanced.
(3)For classification problems, dimension reduction algorithm is just the first step, the another important link to ensure high recognition rate is the choice of classification algorithm. The locally linear embedding algorithm for the new test samples must repeat all steps again to finish dimension reduction with the training samples before classification, amount of calculation is large and the efficiency is low. Because the neighborhood structure is established according to the reconstruction error in the local linear embedding,a classification algorithm is used which compute the reconstruction error of the test samples versus the positive and negative manifolds and then judge the catigory of samples according to reconstruction error. This classification method is directly based on the characteristics of data's manifold itself, and it does not introduce new unknown parameters, so it has the characteristics of easy application.
(4)Weed identification is one of the main problems in application of precision agriculture. Because of the biological diversity in the nature, even if the same plants, there also has a certain differences on color and configuration, while different plants may be very similar. Using the traditional machine visual methods, by such as color and shape characteristics, the identification accuracy is not very high, and easily affected by the natural environment. Aimed at images aquired On corn field which have weeds and corn with complex symbiotic environment, a method is designed to segment weeds and corn automatically by the image morphology. Then using supervised locally linear embedding dimension reduction was carried out on the image after segmentation, the ideal experimental results were obtained. The local linear embedding algorithm based on Fisher projection also has the very good adaptability in the natural environment is proved.
For the wheat blade hyperspectral datas which have rust disease collected in laboratory, according to the thought "the unity of the image and spectrum", a kind of image texture feature analysis method——gray symbiotic matrix(GLCM) is introduced, and conjoint analysis based on the GLCM and spectral information is carried out,so the advantages of imaging spectral datas are utilized fully. The experimental results show that this combination of traditional image analysis methods with the spectral method can recognize crops affected by the disease,especially in the early stage which can also be called recessive period, the identification effect is much better than that is obtained by the traditional spectral analysis method.
将图像处理和机器视觉等技术的应用是精准农业实施中的主要特色之一。通过对光学图像或者高光谱图像的智能分析,有效提高作业效率。但是光学图像数据提供的信息有限,在很多应用中存在局限性。而高光谱遥感图像因为波段众多,光谱分辨率和空间分辨率都很高,因此对地物的分辨更加准确,在精准农业的应用中具有其他数据无法比拟的优势,已经成为未来精准农业应用中的主要数据形式。
这些新的数据分析手段虽然给农业生产带来了革命性的变化,但是另一方面也因为其数据量巨大,不仅给存储和传输带来了困难,同时也给数据的分析和处理带来了巨大的挑战。因此如何有效降低数据的维数,减少数据量是精准农业图像分析中的一个重要课题。本文主要研究局部线性嵌入算法在精准农业数据降维问题中的应用。结合精准农业实施中如杂草识别等问题的需要,主要围绕局部线性嵌入算法监督性的实现、近邻参数自适应选择、适当的分类算法的设计等问题进行了深入研究。主要的研究工作与创新成果如下：
(1)信息技术、模式识别技术在精准农业中的主要应用之一就是依据图像和光谱数据完成对作物属性的自动识别。而常规的局部线性嵌入算法是一种非监督算法,直接应用于分类识别中往往效果不佳。针对这个缺陷,提出一种基于Fisher准则的监督局部线性嵌入算法。算法首先对训练样本进行Fisher投影变换,寻找最佳投影方向。在此方向上各类样本具有最大可分性。利用训练样本在该投影轴上的投影距离来构造邻域结构,则可以最大程度得利用训练样本的监督信息指导降维,从而有效提高识别率。实验结果表明,基于Fisher准则的监督局部线性嵌入算法比常规局部线性嵌入算法具有更优异的降维效果,用简单的分类算法就可以实现较高的识别率。
(2)局部线性嵌入算法应用于分类识别问题时,其精度还受到另外一个因素的影响,即局部线性嵌入算法主要参数之一的近邻参数κ。该参数选择的恰当与否将严重影响识别结果。但是目前还没有特别成熟的选择算法出现,多数情况下是根据实验结果进行多次反复人工尝试。这也成为局部线性嵌入算法发展中的瓶颈。针对精准农业中所处理数据的特点以及局部线性嵌入算法邻域构造对识别效果的影响,设计一种基于监督局部线性嵌入方法的近邻参数自适应调整的算法。实验结果表明,该方法可以根据所采集数据的分布特点自动确定近邻参数,在保证高识别率的前提下又增强了算法的稳定性和实用性。
(3)降维算法只是数据处理的第一步,确保高识别率的另外一个重要环节是分类算法的选择。而局部线性嵌入算法对于新增测试样本必须和训练样本重新训练完成降维后才能进行分类,计算量大,效率低下。根据局部线性嵌入算法利用重构误差构造邻域结构的特点,将测试样本与正负类流形重构误差的大小作为判断训练样本类别属性的根据。这种分类方法是直接基于数据流形本身的特点构造的,又不需要引入新的未知参数,具有应用方便的特点。实验结果证实监督局部线性嵌入和这种分类算法的结合可以保证较高的识别精度。
(4)杂草识别是精准农业应用中的主要问题之一。因为自然界生物的多样性,即使同种植物形态颜色上也具有一定的差异,而异类植物却又可能具有相似性。利用传统的机器视觉方法,通过颜色,形态等特征识别精度不高,而且容易受到自然环境的影响。本文主要面向玉米田间实地采集的图像数据完成杂草识别任务。该组图像中环境很复杂,玉米和多种杂草共生。设计了根据形态学方法自动分割杂草和玉米的方法,然后利用监督局部线性嵌入对分割后的图像进行降维,并用支持向量机完成分类识别,最终取得了理想的实验结果。证明了基于Fisher准则的局部线性嵌入算法在非实验室环境下也具有很好的适应性。
(5)高光谱数据结合了光谱分析和图像处理的优势,在精准农业中的病虫害监测,品质检测等多个问题中都取得了成功的应用。针对实验室采集的患有条锈病的小麦叶片成像高光谱数据,根据“图谱合一”的思想,将一种图像纹理特征分析手段——灰度共生矩阵和光谱信息进行联合分析,充分利用了成像光谱数据的优势。实验结果表明,这种将传统图像分析手段和光谱数据结合的方法能够更好地发现作物受病害影响的程度,尤其是作物受病害影响初期或者称为隐性病时期,识别效果更优于传统的光谱分析方法。
China is a agricultural country with a population of billions, the problem of agriculture has always been one of the primary issue in the governments at all levels. Traditional agriculture in our country has been called the "intensive cultivation". This ensures our agriculture production have the advantages of higher per mu yield, but on the other hand, relying on artificial intensive cultivation purely must lead to low productivity problem. Modern agriculture is getting rid of the bondage of primitive agriculture、traditional agriculture and industrial agriculture, and entering into the knowledge agriculture development stage with the main characteristics of knowledge intensive.The Precision Agriculture which applied the modern information technology, biotechnology and engineering equipment technology applied in agricultural production has became the main production form of knowledge agriculture of every country in the new century.
When the image processing and machine vision technology are applied in the precision agriculture, the intelligent analysis result of the images can be used to guide the robot to accomplish some field works automatically, which can improve the efficiency rapidly. But the information in optical image data is limited, it is not enough for many applications. Hyperspectral remote sensing image having plenty of bands, high spectral resolution and high pixel resolution, therefore it can provide more accurate information of ground objects, which has incomparable advantage over other datas.And in recent years, its application in precision agriculture has become increasingly widespread. For example, by satellite remote sensing technology hundreds of hectares of land are measured out the fertility of different plots, and control the agricultural machinery to complete the quantitative fertilization according to the local situation; the spectrum characteristics of crops can also be captured utilizing the ground remote sensing device. And these information can used to distinguish weeds from crops or judge degree damaged by diseases. It is hard to achieved relying on traditional agricultural methods.
These new data analysis means has brought a revolutionary improvement to the agricultural production.But on the other hand,because of the huge datasize, not only the storage and transportation become a difficult task, but also the analysis and processing of datas have a greater challenges. So how to effectively reduce the dimension of data and the datasize is an important research subject in precision agriculture image analysis. This paper mainly studies the local linear embedding algorithm application to the problem of data dimension reduction in precision agriculture. Meeted the need of classification problem in the implementation of precision agriculture,such as weed identification, mainly around how to utilize the supervised information of learning samples in locally linear embedding algorithm, the adaptive selection of parameters, and the proper classification algorithm design were studied. The main research work and innovative results are as follows:
(1)The basic theory of manifold learning method and developments are introduced.The influence of neighbor parametes、intrinsic dimension、noise and other issues to the dimension reduction effect is researched. The characteristics of the manifold method which is used commonly are analyzed, and the sensitivity to the parameters of them is compared. A kind of important research issue in the precision agriculture is to complete the automatic identification of some properties of the crops by intellectual technology, which is the typical applications of information technology and pattern recognition in precision agriculture. But the conventional locally linear embedding algorithm is an unsupervised algorithm, so its application in identify crop variety or diseases directly are often ineffective. A supervisied local linear embedding algorithm based on Fisher criterion is proposed. Firstly,the Fisher projection was carried out on the training samples to find out the best projection direction,and different kind of samples in this direction has the maximum separability. The projection distance of training samples in this direction is used to construct the neighborhood structure, which can make use of the training samples' supervision information to instruct dimension reduction, so as to improve the recognition rate. The experimental results show that the supervied local linear embedding algorithm based on Fisher projection is more excellent than the conventional algorithm, so it can achieve high recognition rate only by some simple classification algorithm.
(2)After the supervision problem is solved,there is another factor will affect the identification precision when the locally linear embedding algorithm is applied to the identification problems in precision agriculture, namely the neighbor parameter which is one of the main parameters in locally linear embedding algorithm. Whether the selection of this parameter is appropriate will seriously affect the recognition result. And this parameter selection is directly related to the characteristics of the datasets processed. There is no mature theory to direct this selection method currently, in most cases,the selection is obtained according to the result of many repeated experiments artificially. It has become a bottleneck in the development of local linear embedding algorithm. Aiming at the characteristics of data processed in the precision agriculture and the influence of neighborhood structure to recognition effect, the adaptive algorithm based on the supervised locally linear embedding. The experimental results show that this algorithm can ascertain neighbor parameter automatically according to the distribution characteristics of the dataset, on the premise of guarantee to obtain high recognition rate the algorithm efficiency is improved, so practicability is enhanced.
(3)For classification problems, dimension reduction algorithm is just the first step, the another important link to ensure high recognition rate is the choice of classification algorithm. The locally linear embedding algorithm for the new test samples must repeat all steps again to finish dimension reduction with the training samples before classification, amount of calculation is large and the efficiency is low. Because the neighborhood structure is established according to the reconstruction error in the local linear embedding,a classification algorithm is used which compute the reconstruction error of the test samples versus the positive and negative manifolds and then judge the catigory of samples according to reconstruction error. This classification method is directly based on the characteristics of data's manifold itself, and it does not introduce new unknown parameters, so it has the characteristics of easy application.
(4)Weed identification is one of the main problems in application of precision agriculture. Because of the biological diversity in the nature, even if the same plants, there also has a certain differences on color and configuration, while different plants may be very similar. Using the traditional machine visual methods, by such as color and shape characteristics, the identification accuracy is not very high, and easily affected by the natural environment. Aimed at images aquired On corn field which have weeds and corn with complex symbiotic environment, a method is designed to segment weeds and corn automatically by the image morphology. Then using supervised locally linear embedding dimension reduction was carried out on the image after segmentation, the ideal experimental results were obtained. The local linear embedding algorithm based on Fisher projection also has the very good adaptability in the natural environment is proved.
For the wheat blade hyperspectral datas which have rust disease collected in laboratory, according to the thought "the unity of the image and spectrum", a kind of image texture feature analysis method——gray symbiotic matrix(GLCM) is introduced, and conjoint analysis based on the GLCM and spectral information is carried out,so the advantages of imaging spectral datas are utilized fully. The experimental results show that this combination of traditional image analysis methods with the spectral method can recognize crops affected by the disease,especially in the early stage which can also be called recessive period, the identification effect is much better than that is obtained by the traditional spectral analysis method.
引文
[1]于合龙.精准农业生产中若干智能决策问题研究[D].吉林长春：吉林大学,2010.
[2]王位斌.信息化在农业生产中的应用及其影响要素研究——以江苏省精准农业发展模式为例[D].江苏南京：南京邮电大学,2011
[3]汪懋华.精细农业发展与工程技术创新[J].农业工程学报,1999,6(1)：1-8
[4]蒋恩臣.精准农业及其应用前景分析[J].佳木斯大学学报,1999,17(1)：96-100
[5]韩俊东.精准农业——21世纪世界农业技术新潮流[J].发现,2001,70(1)：55
[6]Robert P C. Precision agriculture:An information revolution in agriculture[J].Agriculture Outlook Forum.1999:1-5
[7]牛晓颖.精准农业变量施肥技术及其实施系统的研究[D].河北保定：河北农业大学,2005
[8]武志杰.我国化肥生产应用中的问题及对策[J].科技导报,1997(9)：37-38
[9]徐蓉,姜峰,姚鸿勋.流形学习概述[J].智能系统学报.2006,1(1)：44-51
[10]He X, Cai D, Liu H, et al. Locality preserving indexing for document representation. Proc. of the 27rd ACM SIGIR [C].2004:96-103.
[11]Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding [J]. Science,2000,290(5500):2323-2326.
[12]尹峻松,肖健,周宗潭等.非线性流形学习方法的分析与应用[J].自然科学进展,2007,17(8)：1015-1025.
[13]赵连伟,罗四维,赵艳敞等.高维数据流形的低维嵌入及嵌入维数研究[J].软件学报,2005,16(8)：1423-1430.
[14]R.S.Bennet. The Intrinsic Dimensionality of Signal Collections [J]. IEEE Transactions on Information Theory,1969,15:517-525.
[15]K.Fukunaga and D.R. Olsen, An Algorithm for Finding Intrinsic Dimensionality of Data [J].IEEE Transactions on Computer,1971,20:176-183.
[16]C.K.Chen and H. C.Andrews, Nonlinear Intrinsic Dimensionality Computations [J].IEEE Transactions on Computer,1974,23:178-184
[17]D.H. Schwartzmann and J. J. Vidal, An Algorithm for Determining the Topological Dimensionality of Point clusters [J]. IEEE Transactions on Computers,1975,24:1175-1182.
[18]K.Pettis, T.Bailey, A.K.Jain and R.Dubes, An Intrinsic Dimensionality Estimator Nearneighbor from Information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1979,1:25-27
[19]Levina, E., Biekel, P., Maximum likelihood estimation of intrinsic dimension[C].In Proeeedings of Neural Information Processing Systems (NIPS,2005),2005:777-784.
[20]Choi, H., Choi, S., Kernel Isomap on noisy manifold [C].InProceedings of the 4th IEEE International Conference on Development and Learning (ICDL'05),2005:208-213.
[21]Chang, H., Yeung, D.Y. Robust locally linear embedding[J]. Pattern Recognition,2006,39(6):1053-106
[22]张善文,王献峰.基于加权局部线性嵌入的植物叶片图像识别方法[J].农业工程学报,2011,27(12)：141-145
[23]He, X., Yan, S., Hu, Y., et al. Face recognition using Laplacian faces[J].IEEE Transactions on Pattern Analysis and Maehine Intelligence,2005,27(3):328-340.
[24]Muller, K, R., Mika, S., Ratsch, G, et al. An introduction to kernel-based learning algorithms[J].IEEE Transactions on Neural Networks,2001,12(2):181-120
[25]Li B, Wang C, Huang D S. Supervised feature extraction based on orthogonal discriminant projection [J]. Neurocomputing,2009,73:191-196.
[26]Zhao H, Sun S, Jing Z, et al. Local structure based supervised feature extraction [J]. Pattern Recognition,2006,39(8):1546-1550.
[27]徐立本.机器学习引论[M].长春：吉林大学出版社.1993.
[28]王珏,石纯一.机器学习研究[J].广西师范大学学报(自然科学版),2003,21(2)：1-15.
[29]鲁珂.流形学习方法在Web图像检索中的应用研究[D].四川成都：电子科技大学,2004.
[30]孟德宇,徐宗本,戴明伟.一种新的有监督流形学习方法[J].计算机研究与发展.2007,44(12)：2072-2077.
[31]Zhang J, LIS, Wang J. Nearest Manifold Approach for Face Recognition[C]. Proceedings of Sixth IEEE International Conference on Automatic Face and Gesture Recognition,2004: 223-228.
[32]Geng X, Zhan D, Zhou Z. Supervised Nonlinear Dimensionality Reduction for Visualizstion And Classification [J]. IEEE Transaction on Systems, Man. and Cybernetics-Part B: Cybernetics,2005,35 (6):1098-1107.
[33]Ridder D, Kouropteva O, Okun O, etal. Supervised Locally Linear Embedding[C]. Proceedings of Joint International Conference on ICANN/ICONIP. Springer,2003:333-341.
[34]王国强,欧宗瑛,刘典婷.基于监督保持近邻投影的人脸识别方法[J].计算机工程,2008,34(8)：4-6.
[35]Saul, L.K., Roweis, S.T. Think globally, fit locally:Unsupervised learning of low Dimensional manifolds [J]. Jounal of Machine Learning Research,2004,4(2):119-155.
[36]Zhang,J.P., He,L., Zhou,Z.H., Ensemble-based discriminant manifold learning for face recognition[C].Advances in Natural Computation, Part.1, Proceedings, Lecture Notes in Computer Science,2006,4221:29-38.
[37]Zhang, J.P., Shen,H.X., Zhou,2.H., Unified locally linear embedding and linear Discriminant analysis algorithm(U.LLELDA) for face recognition[C].Advances in Biometric Person Authentieation,Proceedings,2004,3338:296-304.
[38]Pang, Y.W., Liu, Z.K., Yu, N.H. A new nonlinear feature extraction method for face recognition[J].Neuro computing,2006,69(7-9):949-953
[39]De Ridder,D.,Loog,M.,Reinders,M.J.T.,Local fisher embedding[C].In Proceeings of the 17th Intenational Conference on Pattern Recognition(ICPR,2004),2004,2:295-298.
[40]Bai, Z., Demmel, J., Dongarra, J., et al. Templates for the Solution of Algebraic Eigenvalue Problems:A Practical Guide[M].Philadelphia:Society for Industrial and Applied Mathematies,2000.
[41]Fisher R A. The use of multiple measurements in taxonomic problems[J]. Annals of Eugenics,1936,7(2):179-188.
[42]Zhao W, Nandhakumar N. Linear discriminant analysis of MPF for face recognition[C].Pattern Recognition,1998. Proceedings. Fourteenth International Conference on. IEEE,1998,1:185-188.
[43]Wilks S S. Mathematical statistics [M]. New York:Wiley.1962
[44]Duda R and Hart P. Pattern classification and scene analysis [M]. New York:Wiley.1973.
[45]张善文,王献峰.基于加权局部线性嵌入的植物叶片图像识别方法[J].农业工程学报,2011,27(12)：141-145.
[46]Cover T M, Hart P E. Nearest neighbour pattern classification[J].IEEE Transactions on Information Theory,1967,13:21-27.
[47]刘春红.超光谱遥感图像降维及分类方法研究[D].哈尔滨：哈尔滨工程大学,2005.
[48]柴绍斌.基于神经网络的数据分类研究[D].大连：大连理工大学,2007.
[49]Cortes C, Vapnik V. Support-vector networks [J]. Machine Learning,1995,20(3):273-297.
[50]姚力群,陶卿.分类问题的一种流形学习算法[J].模式识别与人工智能,2005,18(5)：542-545
[51]刘毅,王海清.采用最小二乘支持向量机的青霉素发酵过程建模研究[J].生物工程学报,2006,22(1)：144-149
[52]相征,张太镒,孙建成.基于最小二乘支持向量机的非线性系统建模[J].系统仿真学报,2006,18(9)：2684-2687
[53]杜树新,吴铁军.用于回归估计的支持向量机方法[J].系统仿真学报,2003,15(11)：1580-1585,1633
[54]Balasubramanian M, Schwartz EL. The Isomap Algorithm and Topological Stability[J]. Science,2002,295(5552):7a.
[55]文贵华,江丽君,文军.基于邻域优化的局部线性嵌入[J].系统仿真学报,2007,19(13)：3119-3122
[56]Quansheng Jiang, Yepin Lu, Zuokui Hong. A neighborhood parameter optimization method of LLE based on topology Preservation[C]. International Conference on Electronic & Mechanical Engineering and Information Technology,2011:4231-4234
[57]Zhenyue Zhang, Jing Wang, Hongyuan Zha. Adaptive Manifold Learning[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2012, 34(2):253-165
[58]Jun Zhang, Jin-Ge Sang, Jiao-Min Liu. An Adaptive Manifold Learning Algorithm based on ISOMAP[C]. International Conference on Research Challenges in Computer Science, 2009:104-107
[59]J Wang, Z Y Zhang, H Y Zha. Adaptive Manifold Learning[C]. Proceedings of 18th Annual Conference on Neural Information Processing System,2004.
[60]Jia Wei, Hong Peng, Yi-Shen Lin,et al. ADAPTIVE NEIGHBORHOOD SELECTION FOR MANIFOLD LEARNING[C]. Proceedings of the Seventh International Conference on Machine Learning and Cybernetics, Kunming,2008,7:380-384
[61]惠康华,肖柏华,王春恒.基于自适应近邻参数的局部线性嵌入[J].模式识别与人工智能,2010,23(6)：842-846
[62]N Mekuz,J K Tsotsos.Paramaterless Isomap with Adaptive Neighborhood Selection[C].28th Annual Symposium of the German Association for Pattern Recognition,2006.
[63]Yang Li. Building k Edge-Disjoint Spanning Trees of Minimum Total Length for Isometric Data Embedding. IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(10): 1680-1683
[64]B. Yang, S. Chen. Sample dependent graph construction with application to dimensionality reduction. Neurocomputing. In Press, Corrected Proof,2010
[65]张兴福,黄少滨.自适应近邻的局部线性嵌入算法[J].哈尔滨工程大学学报,2012,33(4)：489-495
[66]张兴福.基于流形学习的局部降维算法研究[D].哈尔滨：哈尔滨工程大学,2013.
[67]陈德润,王秀,王书茂.农田杂草识别技术的现状与展望[J].中国农机化,2005,2：35~38.
[68]Thompson J F, Stafford J V, Miller P C H. Potential for automatic weed detection and selective herbicide application[J].Crop Protection,1991,10(4):254-259.
[69]Burks T F, Shearer S A, Payne F A. Classification of weed species using color texture features and discriminant analysis[J].Transactions of the American Society of Agricultural Engineers(Trans. ofASAE),2000,43(2):441-448
[70]Ahmad I S, Reid J F.Evaluation of color representations for maize image[J].Journal of Agricultural Engineering Research,1996,63:185-196
[71]Woebbecke D M,Meyer G E,Von Bargen K,et al.Color indices for identification under various soil,residue,and lighting conditions[J].Trans. of ASAE,1995,38(1):259-269
[72]沈宝国,陈树人,尹建军.基于颜色特征的棉田绿色杂草图像识别方法[J].农业工程学报,2009,25(6)：163-167
[73]Woebbecke D M, Meyer G E, Von Bargen K, et al. Shape feature for identifying young weeds using image analysis[J]. Transactions of the ASAE,1995,38(1):271-281.
[74]Yonekawa S, Sakai N, Kitani O. Identification of idealized leaf types using simple dimensionless shape factors by imaged analysis[J]. Transactions of the ASAE,1996,39(4): 1525-1533.
[75]Sogaard H T. Weed Classification by Active Shape Models[J]. Biosystems Engineering, 2005,91(3):271-281.
[76]Aitkenhead M J, Dalgetty I A, Mullins C E, et al. Weed and crop discrimination using image analysis and artificial intelligence methods[J]. Computers and Electronics in Agriculture,2003, 39(3):157-171.
[77]龙满生,何东健.玉米苗期杂草的计算机识别技术研究[J].农业工程学报,2007,23(7)：139-144.
[78]纪寿文,王荣本,陈佳娟,等.应用计算机图像处理技术识别玉米苗期杂草的研究[J].农业工程学报,2001,17(2)：154-156.
[79]Shearer S A, Holmes R G. Plant identification using color cooccurrence matrices [J].Transact ions of the ASAE,1990,33 (6):2037-2044.
[80]Meyer G E, Mehta T, KocherM F, et al. Textural imaging and discriminant analysis for distinguishing weeds for spotspraying [J].Transactions of the ASAE,1998,41(4):1189-1197.
[81]Burk s T F, Shearer S A, Gates R S. Backp ropagation neural netwo rk design and evaluation for classifying weed species using color image texture [J]. Transactions of the ASAE,2000,43 (4):1029-1037.
[82]祖琴,陈湘萍,邓巍.光谱图像技术在精准施药中的应用[J].农机化研究,2013,35(3)：19-23.
[83]Exposito M J, Granados F L, Atenciano S, et al. Discrimination of Weed Seedlings, Wheat(Triticum aestivum)stubble and sunflower (Helianthusannuus) by near-infrared reflectance spectroscopy(NIRS)[J]. Crop Protection,2003,22(10):1177-1180.
[84]Piron A, Leemans V, Kleynen O. Selection of the most efficient wavelength bands for discriminating weeds from crop[J]. Computer and Electronics in Agriculture,2008,62:141-148.
[85]Thenkabail P S, Enclona E A, Ashton M S, et a 1.Accuracy Assessments of Hyperspectral Waveband Performance for Vegetation Analysis Applications[J]. Remote Sensing of Environment,2004, (91):354-376.
[86]毛文华,王月青,王一鸣,张小超.苗期作物和杂草的光谱分析与识别[J].光谱学与光谱分析.2005,25(6)：984-987.
[87]刘波,方俊永,刘学等.基于成像光谱技术的作物杂草识别研究[J].光谱学与光谱分析.2010,30(7)：1830-1833.
[88]Jolliffe I.T.. Principal Component Analysis, Springer Series in Statisties[M]. Springer-Verlag, Berlin,1986
[89]Fukunaga K.,.Introduction to Statistical Pattern Recognition[M]. Academic Press, SanDiego, California,1990
[90]Saul L.K., Roweis S.T., Think globally, fitlocally:unsupervised learning of nonlinear manifolds[J].Joumal of Machine Learning Research,2003,4:119-155
[91]Kouropteva O., Okun O., Pietikanen M., Incremental locally linear embedding[J]. pattern Recognition,2005,38:1764-1767
[92]Hadid A., Koouropteva, O., Pietikanen M., Unsupervised learning using locally linear embedding:Experiments with face Pose analysis[C].In Proc 16th Internat.Conf.on Pattern Recognition,2002:111-114.
[93]Suykens J A K, Vandewalle J.Least Squares Support Vector Machines Classifiers[J]. Neural Processing Letters,1999,9(3):293-300
[94]Strange R N, Scott P R. Plant Disease:A threat to global food security[J]. Annual reviews phytopathol,2005,43:83-116.
[95]霍治国,刘万才,邵振润等.试论开展中国农作物病虫害危害流行的长期气象预测研究[J].自然灾害学报,2000,9(1)：117-121.
[96]张竞成,袁琳,王纪华等。作物病虫害遥感监测研究进展[J].农业工程学报,2012,28(20)：1-11
[97]Xu,G.L., Zhang, F.L., Shah, S.G.,et at. Use of leaf color images to identify nitrogen and potassium deficient tomatoes[J]. Pattern Recognition Letters,2011,32(11):1584-1590.
[98]Burgos-Artizzu, X.P., Angela, R., Alberto, T., et al. Analysis of natural images processing for the extraction of agricultural elements[J]. Image and Vision Computing,2010,28(1):138-149
[99]Burgos-Artizzu, X.P., Ribeiro,A., Guijarro, M.. Real-time image processing for crop/weed discrimination in maize fields, Computers and Electronics in Agriculture,2011,75(2):337-346
[100]Alberto, T., Gonzalo P., Burgos-Artizzu, X.P. A computer vision approach for weeds identification through Support Vector Machines[J]. Applied Soft Computing,2011,11(1): 908-915.
[101]Wang D, Dowell F E, Lan Y, et al. Determing pecky rice kernels using visible and near-infrared spectroscocy[J].Int J Food Prop,2002,5(3):629-639.
[102]郭洁滨,黄冲,王海光等.基于高光谱遥感技术的不同小麦品种条锈病病情指数的反演[J].光谱学与光谱分析,2009,29(12)：3353-3357.
[103]刘占宇,孙华生,黄敬峰.基于学习矢量量化神经网络的水稻白穗和正常穗的高光谱识别[J].中国水稻科学,2007,21(6)：658-662.
[104]袁琳,张竞成,赵晋陵等.基于叶片光谱分析的小麦白粉病与条锈病区分及病情反演 研究[J].光谱学与光谱分析,2013,33(6)：1608-1614
[105]冯伟,王晓宇,宋晓等。白粉病胁迫下小麦冠层叶绿素密度的高光谱估测[J].农业工程学报,2013,29(13)：114-123
[106]黄木易,王纪华,黄文江等.冬小麦条锈病的光谱特征及遥感监测[J].农业工程学报2003,19(6)：154-158
[107]李小龙,马占鸿,孙振宇等。基于图像处理的小麦条锈病菌夏孢子模拟捕捉的自动计数[J].农业工程学报,2013,29(2)：199-206
[108]陈兵旗,郭学梅,李晓华。基于图像处理的小麦病害诊断算法[J].农业机械学报,2009,40(12)：190-195
[109]赵芸。基于高光谱和图像处理技术的油菜病虫害旱情检测方法和病理研究[D].杭州：浙江大学,2013.
[110]王立志。基于流形学习的高光谱图像降维与分类研究[D].重庆：重庆大学,2012.
[111]童庆禧,张兵,郑兰芬.高光谱遥感的多学科应用[M].北京：电子工业出版社,2006
[112]张良培,张立福.高光谱遥感[M].武汉：武汉大学出版社,2005
[113]D. A. Landgrebe. Multispectral land sensing:where from, where to[J].IEEE Trans.Geosci. Remote,2005,43(3):414-421
[114]J A Richards. Analysis of remote sensed data:the formative decades and the future[J].IEEE Trans. Geosci. Remote,2005,43(3):422-432
[115]马丽.基于流形学习算法的高光谱图像分类和异常检测[D].湖北武汉：华中科技大学,2010
[116]黄玮.高光谱遥感分类与信息提取综述[J].数字技术与应用,2010,5：134-136
[117]刘丽,匡纲要。图像纹理特征提取方法综述[J].中国图像图形学报,2009,14(4)：622-635
[118]Haralick R M,Shanmugam K,Din Stein I. Texture features for image classification[J].IEEE Transactions on Systems,Man and Cybernetics,1973,3(6):610-6
[119]Barald i A, Parmiggiani F. An investigation of the textual characteristics associated with gray level co-occurrence matrix statistical parameters [J]. IEEE Transactions on Geo science and Remote Sensing,1995,33 (2):293-304.
[2]王位斌.信息化在农业生产中的应用及其影响要素研究——以江苏省精准农业发展模式为例[D].江苏南京：南京邮电大学,2011
[3]汪懋华.精细农业发展与工程技术创新[J].农业工程学报,1999,6(1)：1-8
[4]蒋恩臣.精准农业及其应用前景分析[J].佳木斯大学学报,1999,17(1)：96-100
[5]韩俊东.精准农业——21世纪世界农业技术新潮流[J].发现,2001,70(1)：55
[6]Robert P C. Precision agriculture:An information revolution in agriculture[J].Agriculture Outlook Forum.1999:1-5
[7]牛晓颖.精准农业变量施肥技术及其实施系统的研究[D].河北保定：河北农业大学,2005
[8]武志杰.我国化肥生产应用中的问题及对策[J].科技导报,1997(9)：37-38
[9]徐蓉,姜峰,姚鸿勋.流形学习概述[J].智能系统学报.2006,1(1)：44-51
[10]He X, Cai D, Liu H, et al. Locality preserving indexing for document representation. Proc. of the 27rd ACM SIGIR [C].2004:96-103.
[11]Roweis S T, Saul L K. Nonlinear dimensionality reduction by locally linear embedding [J]. Science,2000,290(5500):2323-2326.
[12]尹峻松,肖健,周宗潭等.非线性流形学习方法的分析与应用[J].自然科学进展,2007,17(8)：1015-1025.
[13]赵连伟,罗四维,赵艳敞等.高维数据流形的低维嵌入及嵌入维数研究[J].软件学报,2005,16(8)：1423-1430.
[14]R.S.Bennet. The Intrinsic Dimensionality of Signal Collections [J]. IEEE Transactions on Information Theory,1969,15:517-525.
[15]K.Fukunaga and D.R. Olsen, An Algorithm for Finding Intrinsic Dimensionality of Data [J].IEEE Transactions on Computer,1971,20:176-183.
[16]C.K.Chen and H. C.Andrews, Nonlinear Intrinsic Dimensionality Computations [J].IEEE Transactions on Computer,1974,23:178-184
[17]D.H. Schwartzmann and J. J. Vidal, An Algorithm for Determining the Topological Dimensionality of Point clusters [J]. IEEE Transactions on Computers,1975,24:1175-1182.
[18]K.Pettis, T.Bailey, A.K.Jain and R.Dubes, An Intrinsic Dimensionality Estimator Nearneighbor from Information[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1979,1:25-27
[19]Levina, E., Biekel, P., Maximum likelihood estimation of intrinsic dimension[C].In Proeeedings of Neural Information Processing Systems (NIPS,2005),2005:777-784.
[20]Choi, H., Choi, S., Kernel Isomap on noisy manifold [C].InProceedings of the 4th IEEE International Conference on Development and Learning (ICDL'05),2005:208-213.
[21]Chang, H., Yeung, D.Y. Robust locally linear embedding[J]. Pattern Recognition,2006,39(6):1053-106
[22]张善文,王献峰.基于加权局部线性嵌入的植物叶片图像识别方法[J].农业工程学报,2011,27(12)：141-145
[23]He, X., Yan, S., Hu, Y., et al. Face recognition using Laplacian faces[J].IEEE Transactions on Pattern Analysis and Maehine Intelligence,2005,27(3):328-340.
[24]Muller, K, R., Mika, S., Ratsch, G, et al. An introduction to kernel-based learning algorithms[J].IEEE Transactions on Neural Networks,2001,12(2):181-120
[25]Li B, Wang C, Huang D S. Supervised feature extraction based on orthogonal discriminant projection [J]. Neurocomputing,2009,73:191-196.
[26]Zhao H, Sun S, Jing Z, et al. Local structure based supervised feature extraction [J]. Pattern Recognition,2006,39(8):1546-1550.
[27]徐立本.机器学习引论[M].长春：吉林大学出版社.1993.
[28]王珏,石纯一.机器学习研究[J].广西师范大学学报(自然科学版),2003,21(2)：1-15.
[29]鲁珂.流形学习方法在Web图像检索中的应用研究[D].四川成都：电子科技大学,2004.
[30]孟德宇,徐宗本,戴明伟.一种新的有监督流形学习方法[J].计算机研究与发展.2007,44(12)：2072-2077.
[31]Zhang J, LIS, Wang J. Nearest Manifold Approach for Face Recognition[C]. Proceedings of Sixth IEEE International Conference on Automatic Face and Gesture Recognition,2004: 223-228.
[32]Geng X, Zhan D, Zhou Z. Supervised Nonlinear Dimensionality Reduction for Visualizstion And Classification [J]. IEEE Transaction on Systems, Man. and Cybernetics-Part B: Cybernetics,2005,35 (6):1098-1107.
[33]Ridder D, Kouropteva O, Okun O, etal. Supervised Locally Linear Embedding[C]. Proceedings of Joint International Conference on ICANN/ICONIP. Springer,2003:333-341.
[34]王国强,欧宗瑛,刘典婷.基于监督保持近邻投影的人脸识别方法[J].计算机工程,2008,34(8)：4-6.
[35]Saul, L.K., Roweis, S.T. Think globally, fit locally:Unsupervised learning of low Dimensional manifolds [J]. Jounal of Machine Learning Research,2004,4(2):119-155.
[36]Zhang,J.P., He,L., Zhou,Z.H., Ensemble-based discriminant manifold learning for face recognition[C].Advances in Natural Computation, Part.1, Proceedings, Lecture Notes in Computer Science,2006,4221:29-38.
[37]Zhang, J.P., Shen,H.X., Zhou,2.H., Unified locally linear embedding and linear Discriminant analysis algorithm(U.LLELDA) for face recognition[C].Advances in Biometric Person Authentieation,Proceedings,2004,3338:296-304.
[38]Pang, Y.W., Liu, Z.K., Yu, N.H. A new nonlinear feature extraction method for face recognition[J].Neuro computing,2006,69(7-9):949-953
[39]De Ridder,D.,Loog,M.,Reinders,M.J.T.,Local fisher embedding[C].In Proceeings of the 17th Intenational Conference on Pattern Recognition(ICPR,2004),2004,2:295-298.
[40]Bai, Z., Demmel, J., Dongarra, J., et al. Templates for the Solution of Algebraic Eigenvalue Problems:A Practical Guide[M].Philadelphia:Society for Industrial and Applied Mathematies,2000.
[41]Fisher R A. The use of multiple measurements in taxonomic problems[J]. Annals of Eugenics,1936,7(2):179-188.
[42]Zhao W, Nandhakumar N. Linear discriminant analysis of MPF for face recognition[C].Pattern Recognition,1998. Proceedings. Fourteenth International Conference on. IEEE,1998,1:185-188.
[43]Wilks S S. Mathematical statistics [M]. New York:Wiley.1962
[44]Duda R and Hart P. Pattern classification and scene analysis [M]. New York:Wiley.1973.
[45]张善文,王献峰.基于加权局部线性嵌入的植物叶片图像识别方法[J].农业工程学报,2011,27(12)：141-145.
[46]Cover T M, Hart P E. Nearest neighbour pattern classification[J].IEEE Transactions on Information Theory,1967,13:21-27.
[47]刘春红.超光谱遥感图像降维及分类方法研究[D].哈尔滨：哈尔滨工程大学,2005.
[48]柴绍斌.基于神经网络的数据分类研究[D].大连：大连理工大学,2007.
[49]Cortes C, Vapnik V. Support-vector networks [J]. Machine Learning,1995,20(3):273-297.
[50]姚力群,陶卿.分类问题的一种流形学习算法[J].模式识别与人工智能,2005,18(5)：542-545
[51]刘毅,王海清.采用最小二乘支持向量机的青霉素发酵过程建模研究[J].生物工程学报,2006,22(1)：144-149
[52]相征,张太镒,孙建成.基于最小二乘支持向量机的非线性系统建模[J].系统仿真学报,2006,18(9)：2684-2687
[53]杜树新,吴铁军.用于回归估计的支持向量机方法[J].系统仿真学报,2003,15(11)：1580-1585,1633
[54]Balasubramanian M, Schwartz EL. The Isomap Algorithm and Topological Stability[J]. Science,2002,295(5552):7a.
[55]文贵华,江丽君,文军.基于邻域优化的局部线性嵌入[J].系统仿真学报,2007,19(13)：3119-3122
[56]Quansheng Jiang, Yepin Lu, Zuokui Hong. A neighborhood parameter optimization method of LLE based on topology Preservation[C]. International Conference on Electronic & Mechanical Engineering and Information Technology,2011:4231-4234
[57]Zhenyue Zhang, Jing Wang, Hongyuan Zha. Adaptive Manifold Learning[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2012, 34(2):253-165
[58]Jun Zhang, Jin-Ge Sang, Jiao-Min Liu. An Adaptive Manifold Learning Algorithm based on ISOMAP[C]. International Conference on Research Challenges in Computer Science, 2009:104-107
[59]J Wang, Z Y Zhang, H Y Zha. Adaptive Manifold Learning[C]. Proceedings of 18th Annual Conference on Neural Information Processing System,2004.
[60]Jia Wei, Hong Peng, Yi-Shen Lin,et al. ADAPTIVE NEIGHBORHOOD SELECTION FOR MANIFOLD LEARNING[C]. Proceedings of the Seventh International Conference on Machine Learning and Cybernetics, Kunming,2008,7:380-384
[61]惠康华,肖柏华,王春恒.基于自适应近邻参数的局部线性嵌入[J].模式识别与人工智能,2010,23(6)：842-846
[62]N Mekuz,J K Tsotsos.Paramaterless Isomap with Adaptive Neighborhood Selection[C].28th Annual Symposium of the German Association for Pattern Recognition,2006.
[63]Yang Li. Building k Edge-Disjoint Spanning Trees of Minimum Total Length for Isometric Data Embedding. IEEE Trans on Pattern Analysis and Machine Intelligence,2005,27(10): 1680-1683
[64]B. Yang, S. Chen. Sample dependent graph construction with application to dimensionality reduction. Neurocomputing. In Press, Corrected Proof,2010
[65]张兴福,黄少滨.自适应近邻的局部线性嵌入算法[J].哈尔滨工程大学学报,2012,33(4)：489-495
[66]张兴福.基于流形学习的局部降维算法研究[D].哈尔滨：哈尔滨工程大学,2013.
[67]陈德润,王秀,王书茂.农田杂草识别技术的现状与展望[J].中国农机化,2005,2：35~38.
[68]Thompson J F, Stafford J V, Miller P C H. Potential for automatic weed detection and selective herbicide application[J].Crop Protection,1991,10(4):254-259.
[69]Burks T F, Shearer S A, Payne F A. Classification of weed species using color texture features and discriminant analysis[J].Transactions of the American Society of Agricultural Engineers(Trans. ofASAE),2000,43(2):441-448
[70]Ahmad I S, Reid J F.Evaluation of color representations for maize image[J].Journal of Agricultural Engineering Research,1996,63:185-196
[71]Woebbecke D M,Meyer G E,Von Bargen K,et al.Color indices for identification under various soil,residue,and lighting conditions[J].Trans. of ASAE,1995,38(1):259-269
[72]沈宝国,陈树人,尹建军.基于颜色特征的棉田绿色杂草图像识别方法[J].农业工程学报,2009,25(6)：163-167
[73]Woebbecke D M, Meyer G E, Von Bargen K, et al. Shape feature for identifying young weeds using image analysis[J]. Transactions of the ASAE,1995,38(1):271-281.
[74]Yonekawa S, Sakai N, Kitani O. Identification of idealized leaf types using simple dimensionless shape factors by imaged analysis[J]. Transactions of the ASAE,1996,39(4): 1525-1533.
[75]Sogaard H T. Weed Classification by Active Shape Models[J]. Biosystems Engineering, 2005,91(3):271-281.
[76]Aitkenhead M J, Dalgetty I A, Mullins C E, et al. Weed and crop discrimination using image analysis and artificial intelligence methods[J]. Computers and Electronics in Agriculture,2003, 39(3):157-171.
[77]龙满生,何东健.玉米苗期杂草的计算机识别技术研究[J].农业工程学报,2007,23(7)：139-144.
[78]纪寿文,王荣本,陈佳娟,等.应用计算机图像处理技术识别玉米苗期杂草的研究[J].农业工程学报,2001,17(2)：154-156.
[79]Shearer S A, Holmes R G. Plant identification using color cooccurrence matrices [J].Transact ions of the ASAE,1990,33 (6):2037-2044.
[80]Meyer G E, Mehta T, KocherM F, et al. Textural imaging and discriminant analysis for distinguishing weeds for spotspraying [J].Transactions of the ASAE,1998,41(4):1189-1197.
[81]Burk s T F, Shearer S A, Gates R S. Backp ropagation neural netwo rk design and evaluation for classifying weed species using color image texture [J]. Transactions of the ASAE,2000,43 (4):1029-1037.
[82]祖琴,陈湘萍,邓巍.光谱图像技术在精准施药中的应用[J].农机化研究,2013,35(3)：19-23.
[83]Exposito M J, Granados F L, Atenciano S, et al. Discrimination of Weed Seedlings, Wheat(Triticum aestivum)stubble and sunflower (Helianthusannuus) by near-infrared reflectance spectroscopy(NIRS)[J]. Crop Protection,2003,22(10):1177-1180.
[84]Piron A, Leemans V, Kleynen O. Selection of the most efficient wavelength bands for discriminating weeds from crop[J]. Computer and Electronics in Agriculture,2008,62:141-148.
[85]Thenkabail P S, Enclona E A, Ashton M S, et a 1.Accuracy Assessments of Hyperspectral Waveband Performance for Vegetation Analysis Applications[J]. Remote Sensing of Environment,2004, (91):354-376.
[86]毛文华,王月青,王一鸣,张小超.苗期作物和杂草的光谱分析与识别[J].光谱学与光谱分析.2005,25(6)：984-987.
[87]刘波,方俊永,刘学等.基于成像光谱技术的作物杂草识别研究[J].光谱学与光谱分析.2010,30(7)：1830-1833.
[88]Jolliffe I.T.. Principal Component Analysis, Springer Series in Statisties[M]. Springer-Verlag, Berlin,1986
[89]Fukunaga K.,.Introduction to Statistical Pattern Recognition[M]. Academic Press, SanDiego, California,1990
[90]Saul L.K., Roweis S.T., Think globally, fitlocally:unsupervised learning of nonlinear manifolds[J].Joumal of Machine Learning Research,2003,4:119-155
[91]Kouropteva O., Okun O., Pietikanen M., Incremental locally linear embedding[J]. pattern Recognition,2005,38:1764-1767
[92]Hadid A., Koouropteva, O., Pietikanen M., Unsupervised learning using locally linear embedding:Experiments with face Pose analysis[C].In Proc 16th Internat.Conf.on Pattern Recognition,2002:111-114.
[93]Suykens J A K, Vandewalle J.Least Squares Support Vector Machines Classifiers[J]. Neural Processing Letters,1999,9(3):293-300
[94]Strange R N, Scott P R. Plant Disease:A threat to global food security[J]. Annual reviews phytopathol,2005,43:83-116.
[95]霍治国,刘万才,邵振润等.试论开展中国农作物病虫害危害流行的长期气象预测研究[J].自然灾害学报,2000,9(1)：117-121.
[96]张竞成,袁琳,王纪华等。作物病虫害遥感监测研究进展[J].农业工程学报,2012,28(20)：1-11
[97]Xu,G.L., Zhang, F.L., Shah, S.G.,et at. Use of leaf color images to identify nitrogen and potassium deficient tomatoes[J]. Pattern Recognition Letters,2011,32(11):1584-1590.
[98]Burgos-Artizzu, X.P., Angela, R., Alberto, T., et al. Analysis of natural images processing for the extraction of agricultural elements[J]. Image and Vision Computing,2010,28(1):138-149
[99]Burgos-Artizzu, X.P., Ribeiro,A., Guijarro, M.. Real-time image processing for crop/weed discrimination in maize fields, Computers and Electronics in Agriculture,2011,75(2):337-346
[100]Alberto, T., Gonzalo P., Burgos-Artizzu, X.P. A computer vision approach for weeds identification through Support Vector Machines[J]. Applied Soft Computing,2011,11(1): 908-915.
[101]Wang D, Dowell F E, Lan Y, et al. Determing pecky rice kernels using visible and near-infrared spectroscocy[J].Int J Food Prop,2002,5(3):629-639.
[102]郭洁滨,黄冲,王海光等.基于高光谱遥感技术的不同小麦品种条锈病病情指数的反演[J].光谱学与光谱分析,2009,29(12)：3353-3357.
[103]刘占宇,孙华生,黄敬峰.基于学习矢量量化神经网络的水稻白穗和正常穗的高光谱识别[J].中国水稻科学,2007,21(6)：658-662.
[104]袁琳,张竞成,赵晋陵等.基于叶片光谱分析的小麦白粉病与条锈病区分及病情反演 研究[J].光谱学与光谱分析,2013,33(6)：1608-1614
[105]冯伟,王晓宇,宋晓等。白粉病胁迫下小麦冠层叶绿素密度的高光谱估测[J].农业工程学报,2013,29(13)：114-123
[106]黄木易,王纪华,黄文江等.冬小麦条锈病的光谱特征及遥感监测[J].农业工程学报2003,19(6)：154-158
[107]李小龙,马占鸿,孙振宇等。基于图像处理的小麦条锈病菌夏孢子模拟捕捉的自动计数[J].农业工程学报,2013,29(2)：199-206
[108]陈兵旗,郭学梅,李晓华。基于图像处理的小麦病害诊断算法[J].农业机械学报,2009,40(12)：190-195
[109]赵芸。基于高光谱和图像处理技术的油菜病虫害旱情检测方法和病理研究[D].杭州：浙江大学,2013.
[110]王立志。基于流形学习的高光谱图像降维与分类研究[D].重庆：重庆大学,2012.
[111]童庆禧,张兵,郑兰芬.高光谱遥感的多学科应用[M].北京：电子工业出版社,2006
[112]张良培,张立福.高光谱遥感[M].武汉：武汉大学出版社,2005
[113]D. A. Landgrebe. Multispectral land sensing:where from, where to[J].IEEE Trans.Geosci. Remote,2005,43(3):414-421
[114]J A Richards. Analysis of remote sensed data:the formative decades and the future[J].IEEE Trans. Geosci. Remote,2005,43(3):422-432
[115]马丽.基于流形学习算法的高光谱图像分类和异常检测[D].湖北武汉：华中科技大学,2010
[116]黄玮.高光谱遥感分类与信息提取综述[J].数字技术与应用,2010,5：134-136
[117]刘丽,匡纲要。图像纹理特征提取方法综述[J].中国图像图形学报,2009,14(4)：622-635
[118]Haralick R M,Shanmugam K,Din Stein I. Texture features for image classification[J].IEEE Transactions on Systems,Man and Cybernetics,1973,3(6):610-6
[119]Barald i A, Parmiggiani F. An investigation of the textual characteristics associated with gray level co-occurrence matrix statistical parameters [J]. IEEE Transactions on Geo science and Remote Sensing,1995,33 (2):293-304.