基于数字图像的水稻氮磷钾营养诊断与建模研究
|
摘要
数字诊断技术是近年来水稻营养诊断的主要发展方向,建立高效、快速、实用的水稻数字诊断技术体系具有十分重要的意义。本研究以扫描仪和低空无人机机载数码相机两种数字图像获取方式,分别获取水稻叶片扫描图像和田间冠层图像,分析叶片和冠层数字图像特征与水稻氮磷钾营养状况的关系,选择图像光谱敏感特征,建立营养模式识别规则及定量化模型。同时将作物营养专家的诊断经验量化处理,以作为水稻营养诊断的辅助因子。本研究的主要工作、认识及结论如下：
1.两种方式获取的数字图像对比
为了能够快速、准确的提取水稻叶片特征,本文利用扫描仪采集水稻叶片数字图像,采集过程受环境影响小,方便快捷,扫描图像的背景单一也为叶片特征的准确提取提供了保证。为了对比扫描数字图像和数码相机获取数字图像之间的异同,本文根据数字图像质量评价方法,以两种途径获取的水稻叶片数字图像为对象,从彩色度、对比度和信息度三方面进行对比分析。结果表明：两种图像在三项评价标准下,彩色度和信息度不存在显著差异,扫描图像保持数字图像信息量丰富的优点；两种图像对比度差异较大,但扫描图像的对比度的离散程度较小,数据表现出较强稳定性。因此,利用扫描方式获取的叶片数字图像能够保证颜色、纹理和形状的准确提取,对比度的稳定性又进一步证明,以扫描为手段获取图像进行图像分析做理论性研究是有独特优势的。基于对比分析的结果,同时考虑到扫描获取日益普遍,本文对影响元素缺乏种类及程度判断的叶片局部关键信息量化获取采用扫描方式,而对水稻冠层整体信息的采集选择数码相机。
2.基于叶片扫描图像的氮磷钾营养诊断规则的建立
在不同氮磷钾营养状态下,水稻植株会表现出不同差异,水稻叶片表现更加明显。本文以氮磷钾不同营养水平处理的水培水稻为材料,利用扫描方式获取叶片样本数字图像,采用数字图像技术提取叶片颜色、纹理、形状特征,并根据水稻叶片不同缺素种类下的生理症状表现,针对性的加入一些特异性的识别特征。单因素营养水平间特征差异性对比和特征选择出的最优特征集合显示,氮营养诊断中,叶片颜色因子对结果的预测具有重要作用；磷营养诊断中,纹理特征间差异性明显,可用于磷营养水平的区分；钾营养诊断中,叶片斑点面积比例特征可区分和识别钾营养水平。对缺素叶片样本进行分类识别,获取不同营养水平的识别规则。结果表明,对氮、磷、钾单一元素处理的样本识别结果中,缺素样本均能以高精度识别率被识别出,并且呈现出随着营养水平的升高,识别率降低,老叶识别效果好于新叶的规律。
分别对两年缺氮、缺磷、缺钾和正常叶片样本的诊断识别中,筛选出的特征对比表现出,缺磷对水稻叶片图像直方图均值和熵纹这两个纹理特征影响比较大；对缺钾叶片易出现斑点的水稻品种,斑点比例对缺钾样本区分度较高。因此,纹理特征和斑点特征分别可以作为缺磷和缺钾样本的典型特征。缺磷和缺钾样本的典型特征使得两种缺素种类样本识别率较高,分别为97.1%和100%。以2009年试验数据为训练样本建立的规则对缺氮的样本识别精度为77.8%,正常样本的识别率为90.3%。以叶片图像特征为依据对三种缺素样本和正常样本的区分结果表明,各类缺素样本能够以高精度的识别率被区分出来,以缺素水稻叶片典型性特征作为依据进行水稻缺素种类的诊断识别是可行的。
3.基于无人机冠层图像的水稻氮素营养诊断
以旋翼无人机为平台,获取水稻冠层图像具有快速、便捷、区域性强等优点,以水稻冠层图像为研究对象进行营养诊断能够达到实时、高效的目的。本文以旋翼无人机机载数码相机获取的不同氮肥处理水稻冠层图像为对象,提取与地面取样点对应的图像特征,分析图像特征与地面测定值之间的关系,探求利用低空冠层图像对水稻营养状况进行监测的可行性。结论如下：冠层水稻高光谱曲线在可见光区域的趋势和深绿色指数DGCI与叶片含氮量呈极显著二次曲线关系表明,冠层图像的RGB、HSI颜色空间特征与水稻氮营养水平显著相关,可用于估测水稻氮肥营养状况,对冠层图像的8个纹理特征值与对应点的水稻叶片氮含量做相关分析,获得5个相关性较高的纹理特征。通过RGB、HSI颜色空间特征和纹理特征三方面与不同水稻氮营养水平冠层图像综合分析,说明利用冠层图像对水稻氮肥营养状况估测具有可行性。从六个不同施氮区域随机提取100个样点的图像特征,获取每个样点的特征值,并进行施氮水平的识别。识别结果显示不施氮肥的区域识别率最高,达100%,正常施氮水平的识别率最低为55.9%,50%正常施氮量田块识别率为85.7%,75%正常施氮量田块识别率为61.7%,150%正常施氮量田块识别率为85.1%,习惯施肥田块识别率为80%。
4.叶片含氮量预测模型的建立
为了能更精确的衡量水稻氮营养状况,预测叶片氮含量,本文分别以不同氮处理叶片图像特征和冠层图像特征选择出的特征集合为依据,利用因子分析的方法,将众多特征转化为少数几个互不相关的综合指标,解释各因子含义,并构建综合预测因子。对水培叶片图像和冠层图像的分析结果表明：叶片特征组成的因子可以分为颜色因子、纹理因子、形状因子,对结果贡献率分别为40.04%、29.62%和26.44%。冠层图像特征组成的因子分为颜色因子和纹理因子,各自贡献率为85.55%和9.27%,对比单叶和冠层分析结果可知,利用叶片特征对叶片氮含量预测时,颜色因子的贡献率虽然最高,但纹理和形状因子的共同贡献率较高,对结果的预测有不可忽视的作用；而冠层特征各因子中,颜色因子是对营养状态预测的主导因子,纹理因子贡献率较低,这也是两种诊断的差异之一。以综合预测因子Fz值为自变量,叶片含氮量N为因变量,获得水培氮水平处理叶片含氮量的预测模型N=2.8967e-0.3312FZ和大田不同施氮水平水稻’叶片含氮量模型N=-0.01FZ2-0.39FZ+2.315
5.专家经验的量化及对营养诊断的辅助作用由于水稻品种多样,而且生长环境差别较大,品种间叶片特征的表达有很大差异,为了保证诊断结果的准确性以及诊断规则的广泛适用性,在研究过程中,收集大量水稻营养诊断经验知识,从中筛选出便于获取的一些经验性特征为研究对象,这些特征能够通过无损、方便、快捷的方法获取或表达,以水培模式培养的氮磷钾缺素水平水稻植株为试验样本,探讨了水稻经验性诊断经验的量化方法,并利用这些量化的经验性特征对不同样本进行分类识别。结果表明：以筛选出的能够判断水稻氮磷钾营养状态的3个经验性特征RLS(叶鞘比)、DL(叶间距)、Cl5/Cl4(第五叶与第四叶颜色比)作为研究对象,利用图像分析技术和其他便捷方式将经验特征量化,并通过监督离散和决策树的方法分别对氮磷钾三种不同营养的64个样本进行分类诊断,并得到区间形式的诊断规则,分类结果评价显示精度较高。
Recently, digital diagnosis technology have been well developed and widely used in our dairy life. Recognization of nutrition status is a hot topic in agricultual system. For rice system, efficient, quick and practical are the key words. In this study, we proposed two platforms to get the canopy and leaf image of paddy field. One is remote-controlled helicopter (Herakles II) set up with digital camera, the other is the scanner. Significant efforts have been made in the development of the modeling. A good relationship between digital image characteristics and NPK status of rice is developed. Additionally, auxiliary factors play an important role in modeling the recognization of nutrition pattern. The results are as follows:
1. Comparison of images obtained from different sensors
The scanner and the digital camera were selected to collect images of rice leaves. After compared with characteristics of color, contrast and informativity between these two images, there was no significant difference. Howerer, the informatin got from the scanner were more exactly, as the scanned image can make the shape and texture information more stable with less noise information. Thus, the scanner was used to extract reliable fractional information of rice leaves, while canopy information of rice was collect by the use of digital camera.
2. Establishing diagnose rules of rice NPK nutrition status
Rice leaves showed significant variations at different nutrition status. After analizing the characteristics of the digital image, leaf color information, leaf texture (mean, entropy) and spot area information played an important role in recognizing the N, P and K nutrition. In addition, rough set theory was used to establish the recognization rules for different nutrition status. The results showed that leaves with single nutrient deficiency can be recognized with high rate, with a precentage of 77.8% (N),97.1% (P) and 100% (K) respectively. Note that the old leaf can get a better result compared to the new one.
3. Recognization of nutrition status by the use of remote-controlled canopy images
Due to the advantages of real-time, exact and high efficiency, the remote-controlled helicopter with digital camera was selected as the monitoring platform. There was a good relationship between image characteristics and observations. Specifically, hyperspectral characteristics in the visible region and the parameter of dark green color index (DGCI) have got a significant quadric relationship with nitrogen content. Additionally, RGB and HSI color space and five texture characteristics also had outstanding relationship with N nutrition status. All the results indicated that it was practical to recognize the N nutrition status at canopy scale by the use of this proposed platform. Samples without nitrogen input had got highest accuracy, while the accuracy of samples with normal N input was lowest.
4. model establishment for predicting leaf nitrogen content
The selected factors in establishing the recognization modeling are different at leaf and canopy level. For leaf scale, the factors are color, texture and shape, with contribution rates 40.04%,29.62% and 26.44%, respectively. For canopy scale, there are color and texture factor, with contribution rates 85.55%,9.27%, respectively. A model was established as follows N=2.8967e-0.3312FZ and N=-0.01FZ2-0.39FZ+2.315
5. Quantify expert experiences and its auxiliary role in nutrition diagnose
Leaf characteristics are different. In order to insure accuracy and extensive applicability, a lot of expert diagnosis experience has been used. In this study, rice samples were classified using three empirical characteristics (RLS, DL, CI5/CI4) and then quantified by the use of supervised discretization method. Interval rules were established based on the classification results.
1.两种方式获取的数字图像对比
为了能够快速、准确的提取水稻叶片特征,本文利用扫描仪采集水稻叶片数字图像,采集过程受环境影响小,方便快捷,扫描图像的背景单一也为叶片特征的准确提取提供了保证。为了对比扫描数字图像和数码相机获取数字图像之间的异同,本文根据数字图像质量评价方法,以两种途径获取的水稻叶片数字图像为对象,从彩色度、对比度和信息度三方面进行对比分析。结果表明：两种图像在三项评价标准下,彩色度和信息度不存在显著差异,扫描图像保持数字图像信息量丰富的优点；两种图像对比度差异较大,但扫描图像的对比度的离散程度较小,数据表现出较强稳定性。因此,利用扫描方式获取的叶片数字图像能够保证颜色、纹理和形状的准确提取,对比度的稳定性又进一步证明,以扫描为手段获取图像进行图像分析做理论性研究是有独特优势的。基于对比分析的结果,同时考虑到扫描获取日益普遍,本文对影响元素缺乏种类及程度判断的叶片局部关键信息量化获取采用扫描方式,而对水稻冠层整体信息的采集选择数码相机。
2.基于叶片扫描图像的氮磷钾营养诊断规则的建立
在不同氮磷钾营养状态下,水稻植株会表现出不同差异,水稻叶片表现更加明显。本文以氮磷钾不同营养水平处理的水培水稻为材料,利用扫描方式获取叶片样本数字图像,采用数字图像技术提取叶片颜色、纹理、形状特征,并根据水稻叶片不同缺素种类下的生理症状表现,针对性的加入一些特异性的识别特征。单因素营养水平间特征差异性对比和特征选择出的最优特征集合显示,氮营养诊断中,叶片颜色因子对结果的预测具有重要作用；磷营养诊断中,纹理特征间差异性明显,可用于磷营养水平的区分；钾营养诊断中,叶片斑点面积比例特征可区分和识别钾营养水平。对缺素叶片样本进行分类识别,获取不同营养水平的识别规则。结果表明,对氮、磷、钾单一元素处理的样本识别结果中,缺素样本均能以高精度识别率被识别出,并且呈现出随着营养水平的升高,识别率降低,老叶识别效果好于新叶的规律。
分别对两年缺氮、缺磷、缺钾和正常叶片样本的诊断识别中,筛选出的特征对比表现出,缺磷对水稻叶片图像直方图均值和熵纹这两个纹理特征影响比较大；对缺钾叶片易出现斑点的水稻品种,斑点比例对缺钾样本区分度较高。因此,纹理特征和斑点特征分别可以作为缺磷和缺钾样本的典型特征。缺磷和缺钾样本的典型特征使得两种缺素种类样本识别率较高,分别为97.1%和100%。以2009年试验数据为训练样本建立的规则对缺氮的样本识别精度为77.8%,正常样本的识别率为90.3%。以叶片图像特征为依据对三种缺素样本和正常样本的区分结果表明,各类缺素样本能够以高精度的识别率被区分出来,以缺素水稻叶片典型性特征作为依据进行水稻缺素种类的诊断识别是可行的。
3.基于无人机冠层图像的水稻氮素营养诊断
以旋翼无人机为平台,获取水稻冠层图像具有快速、便捷、区域性强等优点,以水稻冠层图像为研究对象进行营养诊断能够达到实时、高效的目的。本文以旋翼无人机机载数码相机获取的不同氮肥处理水稻冠层图像为对象,提取与地面取样点对应的图像特征,分析图像特征与地面测定值之间的关系,探求利用低空冠层图像对水稻营养状况进行监测的可行性。结论如下：冠层水稻高光谱曲线在可见光区域的趋势和深绿色指数DGCI与叶片含氮量呈极显著二次曲线关系表明,冠层图像的RGB、HSI颜色空间特征与水稻氮营养水平显著相关,可用于估测水稻氮肥营养状况,对冠层图像的8个纹理特征值与对应点的水稻叶片氮含量做相关分析,获得5个相关性较高的纹理特征。通过RGB、HSI颜色空间特征和纹理特征三方面与不同水稻氮营养水平冠层图像综合分析,说明利用冠层图像对水稻氮肥营养状况估测具有可行性。从六个不同施氮区域随机提取100个样点的图像特征,获取每个样点的特征值,并进行施氮水平的识别。识别结果显示不施氮肥的区域识别率最高,达100%,正常施氮水平的识别率最低为55.9%,50%正常施氮量田块识别率为85.7%,75%正常施氮量田块识别率为61.7%,150%正常施氮量田块识别率为85.1%,习惯施肥田块识别率为80%。
4.叶片含氮量预测模型的建立
为了能更精确的衡量水稻氮营养状况,预测叶片氮含量,本文分别以不同氮处理叶片图像特征和冠层图像特征选择出的特征集合为依据,利用因子分析的方法,将众多特征转化为少数几个互不相关的综合指标,解释各因子含义,并构建综合预测因子。对水培叶片图像和冠层图像的分析结果表明：叶片特征组成的因子可以分为颜色因子、纹理因子、形状因子,对结果贡献率分别为40.04%、29.62%和26.44%。冠层图像特征组成的因子分为颜色因子和纹理因子,各自贡献率为85.55%和9.27%,对比单叶和冠层分析结果可知,利用叶片特征对叶片氮含量预测时,颜色因子的贡献率虽然最高,但纹理和形状因子的共同贡献率较高,对结果的预测有不可忽视的作用；而冠层特征各因子中,颜色因子是对营养状态预测的主导因子,纹理因子贡献率较低,这也是两种诊断的差异之一。以综合预测因子Fz值为自变量,叶片含氮量N为因变量,获得水培氮水平处理叶片含氮量的预测模型N=2.8967e-0.3312FZ和大田不同施氮水平水稻’叶片含氮量模型N=-0.01FZ2-0.39FZ+2.315
5.专家经验的量化及对营养诊断的辅助作用由于水稻品种多样,而且生长环境差别较大,品种间叶片特征的表达有很大差异,为了保证诊断结果的准确性以及诊断规则的广泛适用性,在研究过程中,收集大量水稻营养诊断经验知识,从中筛选出便于获取的一些经验性特征为研究对象,这些特征能够通过无损、方便、快捷的方法获取或表达,以水培模式培养的氮磷钾缺素水平水稻植株为试验样本,探讨了水稻经验性诊断经验的量化方法,并利用这些量化的经验性特征对不同样本进行分类识别。结果表明：以筛选出的能够判断水稻氮磷钾营养状态的3个经验性特征RLS(叶鞘比)、DL(叶间距)、Cl5/Cl4(第五叶与第四叶颜色比)作为研究对象,利用图像分析技术和其他便捷方式将经验特征量化,并通过监督离散和决策树的方法分别对氮磷钾三种不同营养的64个样本进行分类诊断,并得到区间形式的诊断规则,分类结果评价显示精度较高。
Recently, digital diagnosis technology have been well developed and widely used in our dairy life. Recognization of nutrition status is a hot topic in agricultual system. For rice system, efficient, quick and practical are the key words. In this study, we proposed two platforms to get the canopy and leaf image of paddy field. One is remote-controlled helicopter (Herakles II) set up with digital camera, the other is the scanner. Significant efforts have been made in the development of the modeling. A good relationship between digital image characteristics and NPK status of rice is developed. Additionally, auxiliary factors play an important role in modeling the recognization of nutrition pattern. The results are as follows:
1. Comparison of images obtained from different sensors
The scanner and the digital camera were selected to collect images of rice leaves. After compared with characteristics of color, contrast and informativity between these two images, there was no significant difference. Howerer, the informatin got from the scanner were more exactly, as the scanned image can make the shape and texture information more stable with less noise information. Thus, the scanner was used to extract reliable fractional information of rice leaves, while canopy information of rice was collect by the use of digital camera.
2. Establishing diagnose rules of rice NPK nutrition status
Rice leaves showed significant variations at different nutrition status. After analizing the characteristics of the digital image, leaf color information, leaf texture (mean, entropy) and spot area information played an important role in recognizing the N, P and K nutrition. In addition, rough set theory was used to establish the recognization rules for different nutrition status. The results showed that leaves with single nutrient deficiency can be recognized with high rate, with a precentage of 77.8% (N),97.1% (P) and 100% (K) respectively. Note that the old leaf can get a better result compared to the new one.
3. Recognization of nutrition status by the use of remote-controlled canopy images
Due to the advantages of real-time, exact and high efficiency, the remote-controlled helicopter with digital camera was selected as the monitoring platform. There was a good relationship between image characteristics and observations. Specifically, hyperspectral characteristics in the visible region and the parameter of dark green color index (DGCI) have got a significant quadric relationship with nitrogen content. Additionally, RGB and HSI color space and five texture characteristics also had outstanding relationship with N nutrition status. All the results indicated that it was practical to recognize the N nutrition status at canopy scale by the use of this proposed platform. Samples without nitrogen input had got highest accuracy, while the accuracy of samples with normal N input was lowest.
4. model establishment for predicting leaf nitrogen content
The selected factors in establishing the recognization modeling are different at leaf and canopy level. For leaf scale, the factors are color, texture and shape, with contribution rates 40.04%,29.62% and 26.44%, respectively. For canopy scale, there are color and texture factor, with contribution rates 85.55%,9.27%, respectively. A model was established as follows N=2.8967e-0.3312FZ and N=-0.01FZ2-0.39FZ+2.315
5. Quantify expert experiences and its auxiliary role in nutrition diagnose
Leaf characteristics are different. In order to insure accuracy and extensive applicability, a lot of expert diagnosis experience has been used. In this study, rice samples were classified using three empirical characteristics (RLS, DL, CI5/CI4) and then quantified by the use of supervised discretization method. Interval rules were established based on the classification results.
引文
1.A. An, Y. Huang, X. Huang, N. Cercone. Feature selection with rough sets for web page classification transactions on rough sets[J]. SpringerLink Publishers,2004,:1-13.
2. A. Chouchoulas. Incremental feature selection based on rough set theory[D], Dissertation Thesis, Division of Informatics, University of Edinburgh,2001.
3. A. E. Hassanien, J.M.H. Ali. Enhanced rough sets rule reduction algorithm for classfication digital mammography[J]. Intelligent system journal, Freund & Pettman.2004,13 (2).
4. A.L. Blum, P. Langley. Selection of relevant features and examples in machine learning[J]. Artificial Intelligence.1997,97:245-271.
5. Adamsen F J, Paul J Pinter, J r E M, et al. Measuring wheat senescence with a digital camera[J]. Crop Science.1999,39:719-724.
6. Alchanatis, V., Navon, A., Glazer, L., Levski, S.. An image analysis system for measuring insect feeding effects caused by biopesticides[J]. Journal of Agricultural Engineering Research. 2000,77:289-296.
7. Arregui, L.M., Lasa, B., Lafarga, A.. Evaluation of chlorophyll meter as tools for N fertilization in winter wheat under humid Mediterranean conditions[J]. European Journal of Agronomy.2006,24.140-148.
8. B.Mak, T.Munakata. Rule extraction from expert heuristics:a comparative study of rough sets with neural networks and ID3[J]. European Journal of Operational Research 2002,136: 212-229.
9. Blackmer T M, Schepers J S, Varvel G E, et al. Analysis of aerial photography for nitrogen stress within corn fields[J]. Agronomy Journal.1996,88:729-733.
10. Blackmer, T.M., Schepers, J.S., Varvel, G.E. et al. Light reflectance compared with other nitrogen stress measurements in corn leaves[J]. Agronomy Journal.1994,86:934-938.
11. Blaekshwa Robert E.. Merits of a weed-sensings Pryaer to conrtol weeds in consevration fallow and cropping systems[J]. Weed Seienee,1998.46:120-122.
12. Bodo Mistele, Urs Schmidhalter. Estimating the nitrogen nutrition index using spectral canopy reflectance measurements [J]. European Journal of Agronomy 2008,29:184-190.
13. C.P. Wijekoon, P.H. Goodwin, T. Hsiang. Quantifying fungal infection of plant leaves by digital image analysis using Scion Image software[J]. Journal of Microbiological Methods.2008, 74:94-101.
14.Camargo Neto, Meyer, G.E., Jones, D.D., et al. Plant species idenfication using elliptic fourier analysis[J]. Computers and Electronics in Agriculture.2006b,.50,.121-134.
15. Carreres R, Sendra J, Ballesteros R... Effects of preflood nitrogen rate and midseason nitrogen timing on flooded rice[J]. Journal of Agriculture Science,2000,134:379-390.
16. Cartelat, A., Cerovic, Z.G., et al. Optically assessed contents of leaf polyphenolics and chlorophyll as indicators of nitrogen dfeciency in wheat (Triticum aestivum L.)[J]. Field.Crops Research.2005,91:35-49.
17. Chaoyang Wu, Zheng Niu, Quan Tang, et al. Estimating chlorophyll content from hyperspectral vegetation indices:Modeling and validation[J]:Agricultural and Forest Meteorology.2008,148:1230-1241.
18. Chaoyang Wu, Zheng Niu, Quan Tang. Remote estimation of gross primary production in wheat using chlorophyll-related vegetation indices[J]. Agricultural and Forest Meteorology,2009, 149:1015-1021.
19. Chappelle EW, Kim MS, McMurtrey JE.. Ratio analysis of reflectance spectra (RARS):An algorithm for the remote estimation of the concentrations of chlorophyll A, chlorophyll B, and carotenoids in soybean leaves[J]. Remote Sensing of Environment.1992,39:239-247.
20. Curran PJ, Dungan JL, Macler BA, Plummer SE.. The effect of a red leaf pigment on the relationship between red.edge and chlorophyll concentration[J]. Remote Sensing of Environment. 1991,35:69-76.
21. D. Langoni, M.H. Weatherspoon, S.Y. Foo, et al. A speed and accuracy test of backpropagation and RBF neural networks for small-signal models of active devices[J]. Engineering Applications of Artificial Intelligence.2006,19:883-890.
22. D. Reum, Q. Zhang. Wavelet based multi-spectral image analysis of maize leaf chlorophyll content[J]. Computers and Electronics in Agriculture,2007,56:60-71.
23. D.H. Zhao, J.L. Li, J.G. Qi, et al. Identification of red and NIR spectral regions and vegetative indices for discrimination of cotton nitrogen stress and growth stage[J]. Computers and Electronics in Agriculture.2005,48:155-169.
24. Daughtry C. S. T., C. L. Walthall, et al. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance[J]. Remote Sensing of Environment,2000-,74:229-239.
25.Douglas E. Karcher, Michael D.. Richardson. Quantifying turfgrass color using digital image analysis[J]. Crop Science,2003,43:943-951.
26. Eileen M. Perry, Joan R. Davenport. Spectral and spatial differences in response of vegetation indices to nitrogen treatments on apple[J]. Computers and Electronics in Agriculture, 2007,59:56-65.
27. El-Faki, M.S., Zhang, N., Peterson, D.E.. Weed detection using color machine vision[J]. Transactions of the ASAE 2000b,43:1969-1978.
28. Ellis J. Clarke, Bruce A. Barton. Entropy and MDL discretization of continuous variables for bayesian belief networks[J]. International Journal of Intelligent System.2000,15:61-92.
29. El-Shikha, D.M., Waller, P., Hunsaker, D.. Ground-based remote sensing for assessing water and nitrogen status of broccoli [J]. Agricultural Water Management.2007,92:183-193:
30. Fernandez, S. Radiometric characteristics of tritium aestivum cv, Astral under water and nitrogen stress [J]. International Journal of Remote Sensing,1994,15(9):1867-1884.
31. Filelia I. The red edge position and shape as indicators of plant chlorophyll cotent, biomass and hydri status[J]. International Journal of Remote Sensing,1994,15(7):1459-1470.
32. Filella L, L. Serra, and J. Penuelas. Evaluating wheat nitrogen status with canopy reflectance indices and discriminate analysis[J]. Crop Science,1995,35:1400-1405.
33. Follet R. H. and R. F. Follett. Use of a chlorophyll meter to evaluate the nitrogen status of dryland winter wheat[J]. Communication in Soil Science and Plant Analysis,1992,23(7&8):687-697.
34. Fox, R.H., Piekielek, W.P., et al. K.M. Using a chlorophyll meter to predict nitrogen fertilizer needs of winter wheat[J]. Communication in Soil Science and Plant Analysis,1994,25 (3-4):171-181.
35. G. Acciani, G. Brunetti, G. Fornarelli. A multiple neural network system to classify solder joints on integrated circuits[J]. International Journal of Computational Intelligence Research.2006, 2 (4):337-348.
36. George E. Meyer, Joao Camargo Neto. Verification of color vegetation indices for automated crop imaging applications[J]. Computers and Electronics in Agriculture,2008,63:282-293.
37. Giltelson A.A., Kaufman Y.J., Stark R., et al. Novel algorithm for remote estimation of vegetation fraction[J]. Remote Sensing of Environment 2002,80,76-87.
38. Gitelson A.A., Gritz Y., Merzlyak. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves[J]. Journal of Plant Physiology 2003,160:271-282.
39. Glover F. Scatter search and path relinking[J]. In:D Come, M Dorigo and F Glover (eds.) New Ideas in Optimisation, Wiley,1999.
40.Graeff, S., Steffens, D., Schubert, S.. Use of reflectance measurements for the early detection of N, P, Mg, and Fe d(?)ciencies in Zea mays[J]. Journal of Plant Nutrition and Science,2001, 164:445-450.
41. Guyer D E, Miles G. E., Gualtne, L. D., et al. Application of machine vision to shape analysis in leaf and plant identification[J]. Transactions of the ASAE.1993,36(1):163-171.
42. H. Midelfart, J. Komorowski. K. Norsett, et al. Learning rough set classfiers from gene expressions and clinical data[J]. Fundamenta Informatic.2002,53:155-183.
43.-H. Nakayama, Y. Hattori, R. Ishii. Rule extraction based on rough set theory and its application to medical data analysis[J]. Proceedings of the IEEE SMC Conference,1999,99 (5): 924-929.
44. HU Zhen-qi, HE Fen-qin, YIN Jian-zhong, et al. Estimation of Fractional Vegetation Cover Based on Digital Camera Survey Data and a Remote Sensing Model[J]. Journal of China University of Mining & Technology.2007,17(1):0116-0120.
45. Hunt, E.R., Cavigelli, M., Daughtry, et al. Evaluation of digital photography from model aircraft for remote sensing of crop biomass[J]. Precision Agriculture 2005,6 (4):359-378.
46. Ingrouille M J, Laird S M.. A quantitative approach to oak variability in some.north London woodlands [J]. The London Naturalist,1986,65:35-46.
47. J. Dougherty, R. Kohavi, M. Sahami. Supervised and unsupervised discretization of continuous features[J]. Proceedings of the Twelfth International Conference on Machine Learning,1995.
48. Jagdish K L, Agnes T P, Gloria C, et al. Nondestructive estimation of shoot-nitrogen indifferent rice genotypes[J]. Agronomy Journa,1998,90:33-40.
49. Jia, L., Chen, X., Zhang, F., Roemheld, et al. Use of digital camera to assess nitrogen status of winter wheat in the Northern. China Plain[J]. Journal of Plant Nutrition and Soil Science,2004, 27:441-450.
50. Johnson, J. F.. Nitrogen influence on fresh-leaf NIR spectra[J]. Remote. Sensing of Environment; 2001,78(3):314-320.
51. K. Thangavel, Q. Shen, A. Pethalakshmi. Application of clustering for feature selection based on rough set theory approach[J]. Journal of Artificial Intelligence and Machine Learning. 2006;-6 (1):19-27.
52. Krebel, Ulrich H G.. Pairwise classification and support vector machines[J]. Suppport Vector Lemaing. Massachusetts.1999,255-268,
53. Kwack,M.S.,Kim, E.N., Lee,H.,Kim, et al. Digital image analysis to measure lesion area of cucumber anthracnose by colletotrichum orbiculare[J]. Journal of General Plant Pahtology.2005, 71:418-421.
54. L. Jia, X. Chen, F. Zhang, A. Buerkert. Optimum nitrogen fertilization of winter wheat based on color digital camera images[J]. Communications in Soil Science and Plant Analysis,2007,38 (11):1385-1394.
55. L. Jia; X. Chen, F. Zhang. Optimum nitrogen fertilization of winter wheat based on color digital camera images[J]. Communications in Soil Science and Plant Analysis,2007,38: 1385-1394.
56. L.H. Chen, T.Y. Wang. Artificial neural networks to classify mean shifts from multivariate x2 chart signals[J]. Computers & Industrial Engineering.2004,47 (2-3):195.-205.
57. Laura Grunenfelder, Larry K. Hiller, N. Richard Knowles. Color indices for the assessment of chlorophyll development and greening of fresh market potatoes[J]. Postharvest Biology and Technology.2006,40:73-81.
58. Lee Tarpley, et al, Reflectance indices with precision and accuracy in predicting cotton leaf nitrogen concentration[J].Crop Science,2000,40:1814-1819.
59. Lemaire, G., Khaity, M., Onillon, B.,Allirand. Dynamics of accumulation.and partitioning of N leaves, stems and roots of lucerne in adense canopy[J]. Annals of Botany.1992,70:429-435.
60. Liu, Y.,Tong, Y., Smith, E.A.. Leaf chlorophyll readings as an indicator for spinach yield and nutritional quality with different nitrogen fertilizer applications[J]. Journal of Plant Nutrition and Soil Science.2006,29:1207-1217.
61. Mark A. Hall. Correlation-based feature selection for machine learning[D]. Hamilton, NewZealand. The University of Waikato.1999.
62. Michael Flowers, Randall Weisz, Ronnie Heiniger, Field validation of. a remote sensing technique for early nitrogen application decisions in wheat[J]. Agronomy Journal,2003, 95:167-176.
.63. Michael Flowers, Randall Weisz, Ronnie Heiniger. Quantitative approaches for using color infrared photography for assessing in-season nitrogen status in winter wheat[J]. Agronomy Journal,2003,95,1189-1200
64. Michela Milano. Operations research/computer science interfaces series[M]. Springer.2003, 139-152.
65. Miguel Pagola, Ruben Ortiza, Ignacio Irigoyen, et al. New method to assess barley nitrogen nutrition status based on image colour analysis comparison with SPAD-502[J]. Computers and Electronics in Agriculture.2009,65:213-218.
66. N. Kwak, C.H. Choi. Input feature selection by mutual information based on Parzen window [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24 (12):1667-1671.
67. N. Moroney, M. D. Fairchild, R. R. Hunt, et al. The CIECAM02 color appearance model[J]. IS&T/SIS Tenth Color Imaging Conference,2002.
68. Noura Ziadi, Marianne Brassard, Gilles Belanger, et al. Chlorophyll measurements and nitrogen nutrition index for the evaluation of corn nitrogen status[J]. Agronomy Journal.2008, 100(5):1264-1273
69. Oide M., Ninomiya S. Discrimination of soybean leaflet shape by neural newtorks with image input[J]. Computers and Electronics in Agriculture.2000,29:.59-72.
70. Peng S, Garcia F V, Laza R C, et al. Increased N-use efficiency using a chlorophyll meter on high-yielding irrigated rice[J].Field Crops Research.1996,47:243-252.
71. Pinar A. Grass chlorophyll and the reflectance red edge[J]. International Journal of Remote Sensing,1996,17(2):351-357.
72. R. Kawashima, M. Sugiura, T. Kato, et al. An algorithm for estimating chlorophyll content in leaves using a video camera[J]. Annals of Botany.1998,80:49-54,.
73. R. Kohavi, G.H. John. Wrappers for feature subset selection[J]. Arf(?)cial Intelligence.1997, 97 (1-2):273-324.
74. R. Li, Z. Wong. Mining classification rules using rough sets and neural etworks[J].European Journal of Operational Research.2004,157:439-448.
75. Rafael C. Gonzalez, Richard E. Woods. Digital image processing eecond edition [M]. Publishing House of Electronics Industry. Beijing.2007.
76. Railyan V Y. Red edge structure of canopy reflectance spectra of triticale[J]. Remote Sensing Environment,1993,46(2):173-182.
77. Rasmus Houborg, Martha Anderson, Craig Daughtry, Utility of an image-based canopy reflectance modeling tool for remote estimation of LAI and leaf chlorophyll content at thefield scale[J]. Remote Sensing of Environment 2009,113:259-274.
78. Ray T S. Landmark eigenshpae analysis:homologous contours:leaf shpae in syngonium (Araceae) [J]. American Journal of Botany.1992,79:69-76.
79. Roth G. W., Fox R.H., Marshall H. G..Plant Tissue test for predicting nitrogen fertilizer requirement of winter wheat[J]. Agronomy Journal.1989,81(3):502-507.
80. S.L. Osborne, J. S. Schepers, D. D. Francis, et al. Detection of phosphorus and nitrogen deficiencies in corn using spectral radiance measurements[J]. Agronomy Journal,2002.94 (6), .1215-1221.
81.S.S.R. Abidi, K.M. Hoe, A. Goh, Analyzing data clusters:A rough set approach to extract cluster-defining symbolic rules[M]. LNCS 2189, in:Proceedings of the IDA,2001.
82. Scharpf, P.C. and Lory, J.A. Calibrating corn color from aerial photographs to predict sidedress nitrogen need[J]. Agronomy Journal,2002,94:397-404.
83. Seaife M.A. and K.L.Stevens. Monitoring sap nitratein vegetable crops:coneeniration of test strips with eectrode and effeets of time of day and leaf position[J]. Communications in soil science and plant analysis,1983,14(9):761-771.
84. Shannon L. Osborne; James S. Schepers, Mike R. Schlemmer, Detecting nitrogen.and phosphorus stress in corn using multi-spectral imagery[J]. Communications in Soil Science and Plant Analysis,2004,35:505-516.
85. Shibayama. Estimating grain yield of maturing rice canopies using high spectral resolution reflectance measurements[J], Remote Sensing Environment,1991,36(1):45-53.
86. Shibayama.Sessonal visible near-infrared and mid-infrared spectra of rice canopies in relation to LAI and aboveground dry Phytomass[J].Remote Sensing Environment,1989,27(2): 119-127.
87. Shibayamsa, M, and Akiyama, T.A.. Spectroradiometer for field use.VII. radiometric estimation of nitrogen levels in field rice canopies [J]. Japanese Journal of Crop Science,1986, 55(4):439-455.
88. Shigeto Kawashima, Makoto Nakatani. An algorithm for estimating chlorophyll content in leaves using a video camera[J]. Annals of Botany.1998,81:49-54.
89. Soderkvisti O. Computer vision classification of leaves from swedish tree [D]. Linkoping: Linkoping University,2001.
90. Tei, F., p. Benincasa and M.Guidueei. Critical nitrogen concentration in processing tomato[J]. European Journal of Agronomy,2002b,18:45-55.
91. Wengang Zhou, Chunguang Zhou, Guixia Liu, et al. Feature selection for microarray data analysis using mutual information and rough set theory[J]. Artificial Intelligence Applications and Innovations,2007,204:492-499.
92. Wester Veld, S M, Mckeown A W, et al. Chlorophyll and nitrate meters as nitrogen monitoring tools for selected vegetables in southern Ontario[J]. Acta Hort.,2002, 627(8): 259-266.
93. X. Hu. Using rough sets theory and database operations to construct a good ensemble of classifiers for datamining applications[J]. Proceedings of ICDM.2001:.233-240.
94. X.L. Li, Z.L. Du, T. Wang, et al. Audio feature selection based on rough set[J]. International Journal of Information Technology.2005,11 (6):117-123.
95. Yang C.C., Prasher S.O., Landry, J., et al. Development of an image processing system and a fuzzy algorithm for site-specific herbicide applications[J]. Precision Agriculture,2003; 4,5-18.
96. Z. Marzuki, F. Ahmad. Data mining discretization methods and.performances[J]. Proceedings of the International Conference on Electrical engineering informatics,:2007,.6: 535-537.
97. Z. Pawlak, J. Grzymala-Busse, R. Slowinski, et al, Rough sets.communications of the ACM[J].1995,38 (11):89-95.
98.艾天成,李方敏,周治安,等.作物叶片叶绿素含量与SPAD值相关性研究[J].湖北农学院学报,2000,20(1)：6-8.
99.蔡剑,邹薇,曹卫星 等.施氮水平对啤酒大麦叶片光合、SPAD和叶绿素荧光特性的影响[J].麦类作物学报,2007,27(1)：97-101
100.曹昊.BP神经网络在城镇基准地价评估中的应用及其成果网络发布研究[D].浙江大学硕士论文.2005.5
101.陈防,鲁剑巍SPAD-502叶绿素计在作物营养快速诊断上的应用初探[J].湖北农业科学,1996(2)：31-34.
102.陈佳娟,纪寿文,李娟,等.采用计算机视觉进行棉花虫害程度的自动测定[J].农业工程学报,2001,17(2)：157-160.
103.程一松,胡春胜,郝二波,等.氮素胁迫下的冬小麦高光谱特征提取与分析[J].资源科学,2003,25(1):86-93.
104.崔继林,易琼华.单季晚稻群体叶色“黑黄”变化的生理特点及其在高产形成中的作用[C].陈永康水稻高产经验研究(第1集).上海科技出版社.1964,30-42
105.房一鸣.用分类树算法进行上市公司评级的实证研究[D].对外经济贸易大学硕士论文,2006.4
106.冯伟,姚霞,朱艳,等.基于高光谱遥感的小麦叶片含氮量监测模型研究[J].麦类作物学报,2008,28(5)：851-860
107.何火娇,杨红云,唐建军,等.基于图像处理的水稻叶片三维可视化研究[J].江西农业大学学报,2008,30(1)：149-153
108.黄娟琴.杭州市区湿地资源遥感调查与监测研究[D].浙江大学硕士论文,2005.5
109.黄志开.彩色图像特征提取与植物分类研究[D].中国科学技术大学博士论文,2006.11
110.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田间杂草的研究[J].农业工程学报,2001,17(2)：154-156.
111.冀高.基于数字图像处理的棉花群体特征提取[D].北京邮电大学硕士论文,2007.2
112.贾良良,陈新平,作物氮营养诊断的无损测试技术[J].世界农业,2001,6：36-37.
113.姜雪.基于高分辨率遥感影像的矿区土地利用／土地覆盖信息提取技术研究[D].首都师范大学硕士论文,2007.6
114.金军,徐大勇,胡曙云,等.叶绿素仪穗肥诊断及其在水稻优质栽培中的应用[J].耕作与栽培,2003,2：14-16.
115.景娟娟,王纪华,王锦地,等.不同氮素营养条件下的冬小麦生理及光谱特性[J].遥感信息,2003,2：28-31.
116.雷泽湘,艾天成.草莓叶片叶绿素含量、含氮量与SPAD值间的关系[J].湖北农学院学报,2001,21(2)：138-140.
117.李合生.植物生理生化实验原理和技术[M].高等教育出版社.2000
118.李井会.不同氮肥运筹下马铃薯氮素利用特性及营养诊断的研究[D].吉林农业大学硕士论文.2006.6
119.李小正.基于机器视觉的棉花叶部特征图像识别的研究[D].北京邮电大学硕士论文.2007.2
120.李志宏,刘宏斌,张福锁.应用叶绿素仪诊断冬小麦氮营养状况的研究[J].植物营养与肥料学报,2003,9(4)：401-405.
121.刘国栋,刘更另.论缓解我国钾资源短缺问题的新对策[J].中国农业科学,1995,28(1)；25-32.
122.刘顺忠.数理统计理论、方法、应用和软件计算[M].武汉：华中科技大学出版社,2005：165.
123.刘艳菊,朱永官,丁辉,等.不同氮肥水平下SPAD读数与菠菜硝态氮含量关系的初步研究[J].农业环境科学学报,2004,23(3)：484-487.
124.吕雄杰.土壤水分与水稻氮素状况光谱特征研究[D].南京农业大学硕士论文,2004.6
125.罗鹏.基于3S技术的兰溪市低丘红壤资源调查及开发利用潜力评价[D].浙江大学硕士论文,2006.6
126.马瑞升.微型无人机航空遥感系统及其影像几何纠正研究[D].南京农业大学硕士论文,2004.6
127.毛罕平,徐贵力,等.番茄缺素叶片的图像特征提取和优化选择研究[J].农业工程学报,2003,19(2)：133-136.
128.孟军,陈温福,徐正进.水稻株型与冠层三维结构计算机模拟初报[J].中国农学通报,2005,21(6)：403-406.
129.牛铮,陈永华,隋洪智,等.叶片化学组分成像光谱遥感探测机理分析[J].遥感学报,2000,4(2)：125-130.
130.潘瑞帜,董愚得.植物生理学[M].高等教育出版社.1995.
131.邵新庆,冯全,邵世禄,等.基于叶片图像的植物鉴别技术研究进展[J].甘肃农业大学学报,2010,45(2)：156-160
132.石伟勇著.植物营养诊断与施肥[M].中国农业出版社.2005.
133.石媛媛,邓劲松,王珂,等.利用计算机视觉和光谱分割技术进行水稻叶片钾胁迫特征提取与诊断研究[J].光谱学与光谱分析.2010.30(1)：214-219.
134.宋述尧,王秀峰.数字图像技术在黄瓜氮素营养诊断上的应用研究[J].吉林农业大学学报,2008,30(4)：460-465.
135.宋绪忠,赵永军,张金凤,等.茶树叶片叶绿素含量与夜色值相关性研究[J].山东林业科技,2002,6：10-12.
136.孙伟艳.模式分类中特征选择问题的研究[D].哈尔滨理工大学硕士论文,2009.3
137.谭永生.像素级中高分辨率遥感影像融合研究[D].浙江大学硕士论文,2007.5
138.唐延林,黄敬峰.农业高光谱遥感研究的现状与发展趋势[J].遥感技术与应用,2002,16(4)：248-250.
139.唐延林,王人潮,张金恒,等.高光谱与叶绿素计快速测定大麦氮素营养状况研究[J].麦类作物学报,2003,23(1)：63-66.
140.陶勤南,方萍,吴良欢.水稻氮素营养的叶色诊断研究[J].土壤,1990,22(4)：190-193,197
141.田勇超,曹卫星,王绍华,等.不同水、氮条件下水稻不同叶位水、氮含量及光合速率的变化特征.作物学报,2004,30(11)：1129-1134.
142.王洪春.单季晚稻高产中叶色黑黄变化的生理基础探讨[C],陈永康水稻高产经验研究(第1集).上海科技出版社,1964,43-55.
143.王娟,雷咏雯,张永帅,等.应用数字图像分析技术进行棉花氮素营养诊断的研究[J].中国生态农业学报,2008,16(1)：145-149.
144.王娟.应用图像分析技术进行棉花氮素营养诊断的研究[D].石河子大学硕士论文,2006.6
145.王康,沈荣开,唐友生.用叶绿素测值(SPAD)评估夏玉米氮素状况的试验研究[J].灌溉排水,2002,21(4)：1-3,12.
146.王珂,沈掌泉,Abou-Ismailo,等.不同钾营养水平的水稻冠层和叶片光谱特征研究初报[J].科技通报,1997,13(4)：211-214.
147.王路,张蕾,周彦军,等.基于LVQ神经网络大植物种类识别[J].吉林大学学报(理学版),2007,45(3)：42-426.
148.王人潮,陈铭臻.水稻遥感估产的农学机理研究[J].浙江农业大学学报,1993,19(增刊)：7-29.
149.王绍华,曹卫星,王强盛,等.水稻叶色分布特点与氮素营养诊断[J].中国农业科学,2002,35(12)：1461-1466.
150.王绍华,刘胜环,王强盛,等.水稻产量形成与叶片含氮量及夜色的关系[J].南京农业大学学报,2005,25(4)：1-5.
151.王树文.计算机视觉技术在农产品自动检测与分级中的研究—番茄的表面缺陷自动检测与分类.东北农业大学硕士学位论文,2002.
152.王晓峰,黄德双,杜吉祥,等.叶片图像特征提取与识别技术的研究.计算机工程与应用,2006,3：190-193.
153.王晓静,张炎,李磐,等.地面数字图像技术在棉花氮素营养诊断中的初步研究[J].棉花学报,2007,19(2)：106-113.
154.王新辉.面向对象的高分辨率影像香榧分布信息提取研究[D].浙江大学硕士论文,2008.5
155.王秀峰.应用数字图像技术进行黄瓜和番茄氮素营养诊断的研究[D].吉林农业大学硕士论文,2005.6
156.邬飞波,许馥华,金珠群.利用叶绿素计对短季棉氮素营养诊断的初步研究[J].作物学报,1999,25(4)：483-488.
157.吴富宁.图象处理技术在冬小麦氮营养诊断中的应用[D].中国农业大学硕士论文,2004.6
158.吴良欢,陶勤南.水稻叶绿素计诊断追氮法研究[J].浙江农业大学学报,1999,25(2)：135-138.
159.肖焱波,贾良良,陈新平.应用数字图像分析技术进行冬小麦拔节期氮营养诊断[J].中国农学通报,2008,24,(8)：448-453
160.谢华,沈荣开,徐成剑,等.水、氮效应与叶绿素关系试验研究[J].中国农村水利电力,2003,8：40-43.
161.徐贵力,毛罕平,李萍萍.缺素叶片彩色图像颜色特征提取的研究[J].农业工程学报,2002,4：150-153.
162.徐豪.不同尺度田块信息遥感获取研究[D].浙江大学硕士论文,2007.5
163.徐师华,王修兰,吴毅明.不同光质(光谱)对作物生长发育的影响[J].生态农业研究,2003,8(1)：18-20.
164.薛利红,曹卫星,罗卫红,等.基于冠层反射光谱的水稻群体叶片氮素状况检测[J].中国农业科学,2003,36(7)：807-812.
165.薛利红,曹卫星,罗卫红,等.小麦叶片氮素状况与光谱特性的相关性研究[J].植物生态学报,2004,28(2)：172-177.
166.薛利红,罗卫红,曹卫星,等.作物水分和氮素光谱诊断研究进展[J].遥感学报,2003,7(1)：73-80.
167.杨长明,杨林章,韦朝领,等.不同品种水稻群体冠层光谱特征比较研究[J].应用生态学报,2002,13(6)：689-692.
168.杨相恒.氮、磷交互作用下小麦氮素营养丰缺的光谱诊断与估测[J].遥感信息,1992,4：28-34.
169.杨香凤.基于粗糙集的港口竞争力评价模型的构建与应用[D].江西财经大学硕士论文,2006.10
170.张宏名.农田作物光谱特征及应用[J].光谱学与光谱分析,1994,14(5)：25-30.
171.张金恒,王珂.基于鲜叶光谱估测氮素营养的新植被指数[J].农业工程学报,2008,24(3)：158-161.
172.张霞,刘良云,赵春江,等.利用高光谱遥感图像估算小麦氮含量[J].遥感学报,2003,7(3)：176-782.
173.张选怀,吴明山.水稻施用钾肥的效应[M].磷肥与复肥,2003,18(5)：63-68.
174.张玉森,姚霞,曹卫星,等.应用近红外光谱预测水稻叶片氮含量[J].应用生态学报,2010,36(4)：704-712.
175.张元.基于多光谱机器视觉的油菜氮素营养检测方法研究[D].江苏大学硕士论文,2009.6
176.章仲楚.面向对象的杭州西溪湿地遥感方法研究[D].浙江大学硕士论文,2007.11.
177.赵德华,李建龙,宋子健,等.不同施氮水平下棉花群体反射光谱的差异性分析[J].作物学报,2004,30(11)：1169-1172.
178.周冬琴,朱艳,田永超,等.以冠层反射光谱监测水稻叶片氮积累量的研究[J].作物学报,2006,32(9)：1316-1322.
179.祝锦霞,邓劲松,王珂,等.基于数字图像技术和水稻静态扫描叶片的氮素营养诊断研究[J].光谱学与光谱分析,2009.29(8)：2171-2175.
2. A. Chouchoulas. Incremental feature selection based on rough set theory[D], Dissertation Thesis, Division of Informatics, University of Edinburgh,2001.
3. A. E. Hassanien, J.M.H. Ali. Enhanced rough sets rule reduction algorithm for classfication digital mammography[J]. Intelligent system journal, Freund & Pettman.2004,13 (2).
4. A.L. Blum, P. Langley. Selection of relevant features and examples in machine learning[J]. Artificial Intelligence.1997,97:245-271.
5. Adamsen F J, Paul J Pinter, J r E M, et al. Measuring wheat senescence with a digital camera[J]. Crop Science.1999,39:719-724.
6. Alchanatis, V., Navon, A., Glazer, L., Levski, S.. An image analysis system for measuring insect feeding effects caused by biopesticides[J]. Journal of Agricultural Engineering Research. 2000,77:289-296.
7. Arregui, L.M., Lasa, B., Lafarga, A.. Evaluation of chlorophyll meter as tools for N fertilization in winter wheat under humid Mediterranean conditions[J]. European Journal of Agronomy.2006,24.140-148.
8. B.Mak, T.Munakata. Rule extraction from expert heuristics:a comparative study of rough sets with neural networks and ID3[J]. European Journal of Operational Research 2002,136: 212-229.
9. Blackmer T M, Schepers J S, Varvel G E, et al. Analysis of aerial photography for nitrogen stress within corn fields[J]. Agronomy Journal.1996,88:729-733.
10. Blackmer, T.M., Schepers, J.S., Varvel, G.E. et al. Light reflectance compared with other nitrogen stress measurements in corn leaves[J]. Agronomy Journal.1994,86:934-938.
11. Blaekshwa Robert E.. Merits of a weed-sensings Pryaer to conrtol weeds in consevration fallow and cropping systems[J]. Weed Seienee,1998.46:120-122.
12. Bodo Mistele, Urs Schmidhalter. Estimating the nitrogen nutrition index using spectral canopy reflectance measurements [J]. European Journal of Agronomy 2008,29:184-190.
13. C.P. Wijekoon, P.H. Goodwin, T. Hsiang. Quantifying fungal infection of plant leaves by digital image analysis using Scion Image software[J]. Journal of Microbiological Methods.2008, 74:94-101.
14.Camargo Neto, Meyer, G.E., Jones, D.D., et al. Plant species idenfication using elliptic fourier analysis[J]. Computers and Electronics in Agriculture.2006b,.50,.121-134.
15. Carreres R, Sendra J, Ballesteros R... Effects of preflood nitrogen rate and midseason nitrogen timing on flooded rice[J]. Journal of Agriculture Science,2000,134:379-390.
16. Cartelat, A., Cerovic, Z.G., et al. Optically assessed contents of leaf polyphenolics and chlorophyll as indicators of nitrogen dfeciency in wheat (Triticum aestivum L.)[J]. Field.Crops Research.2005,91:35-49.
17. Chaoyang Wu, Zheng Niu, Quan Tang, et al. Estimating chlorophyll content from hyperspectral vegetation indices:Modeling and validation[J]:Agricultural and Forest Meteorology.2008,148:1230-1241.
18. Chaoyang Wu, Zheng Niu, Quan Tang. Remote estimation of gross primary production in wheat using chlorophyll-related vegetation indices[J]. Agricultural and Forest Meteorology,2009, 149:1015-1021.
19. Chappelle EW, Kim MS, McMurtrey JE.. Ratio analysis of reflectance spectra (RARS):An algorithm for the remote estimation of the concentrations of chlorophyll A, chlorophyll B, and carotenoids in soybean leaves[J]. Remote Sensing of Environment.1992,39:239-247.
20. Curran PJ, Dungan JL, Macler BA, Plummer SE.. The effect of a red leaf pigment on the relationship between red.edge and chlorophyll concentration[J]. Remote Sensing of Environment. 1991,35:69-76.
21. D. Langoni, M.H. Weatherspoon, S.Y. Foo, et al. A speed and accuracy test of backpropagation and RBF neural networks for small-signal models of active devices[J]. Engineering Applications of Artificial Intelligence.2006,19:883-890.
22. D. Reum, Q. Zhang. Wavelet based multi-spectral image analysis of maize leaf chlorophyll content[J]. Computers and Electronics in Agriculture,2007,56:60-71.
23. D.H. Zhao, J.L. Li, J.G. Qi, et al. Identification of red and NIR spectral regions and vegetative indices for discrimination of cotton nitrogen stress and growth stage[J]. Computers and Electronics in Agriculture.2005,48:155-169.
24. Daughtry C. S. T., C. L. Walthall, et al. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance[J]. Remote Sensing of Environment,2000-,74:229-239.
25.Douglas E. Karcher, Michael D.. Richardson. Quantifying turfgrass color using digital image analysis[J]. Crop Science,2003,43:943-951.
26. Eileen M. Perry, Joan R. Davenport. Spectral and spatial differences in response of vegetation indices to nitrogen treatments on apple[J]. Computers and Electronics in Agriculture, 2007,59:56-65.
27. El-Faki, M.S., Zhang, N., Peterson, D.E.. Weed detection using color machine vision[J]. Transactions of the ASAE 2000b,43:1969-1978.
28. Ellis J. Clarke, Bruce A. Barton. Entropy and MDL discretization of continuous variables for bayesian belief networks[J]. International Journal of Intelligent System.2000,15:61-92.
29. El-Shikha, D.M., Waller, P., Hunsaker, D.. Ground-based remote sensing for assessing water and nitrogen status of broccoli [J]. Agricultural Water Management.2007,92:183-193:
30. Fernandez, S. Radiometric characteristics of tritium aestivum cv, Astral under water and nitrogen stress [J]. International Journal of Remote Sensing,1994,15(9):1867-1884.
31. Filelia I. The red edge position and shape as indicators of plant chlorophyll cotent, biomass and hydri status[J]. International Journal of Remote Sensing,1994,15(7):1459-1470.
32. Filella L, L. Serra, and J. Penuelas. Evaluating wheat nitrogen status with canopy reflectance indices and discriminate analysis[J]. Crop Science,1995,35:1400-1405.
33. Follet R. H. and R. F. Follett. Use of a chlorophyll meter to evaluate the nitrogen status of dryland winter wheat[J]. Communication in Soil Science and Plant Analysis,1992,23(7&8):687-697.
34. Fox, R.H., Piekielek, W.P., et al. K.M. Using a chlorophyll meter to predict nitrogen fertilizer needs of winter wheat[J]. Communication in Soil Science and Plant Analysis,1994,25 (3-4):171-181.
35. G. Acciani, G. Brunetti, G. Fornarelli. A multiple neural network system to classify solder joints on integrated circuits[J]. International Journal of Computational Intelligence Research.2006, 2 (4):337-348.
36. George E. Meyer, Joao Camargo Neto. Verification of color vegetation indices for automated crop imaging applications[J]. Computers and Electronics in Agriculture,2008,63:282-293.
37. Giltelson A.A., Kaufman Y.J., Stark R., et al. Novel algorithm for remote estimation of vegetation fraction[J]. Remote Sensing of Environment 2002,80,76-87.
38. Gitelson A.A., Gritz Y., Merzlyak. Relationships between leaf chlorophyll content and spectral reflectance and algorithms for non-destructive chlorophyll assessment in higher plant leaves[J]. Journal of Plant Physiology 2003,160:271-282.
39. Glover F. Scatter search and path relinking[J]. In:D Come, M Dorigo and F Glover (eds.) New Ideas in Optimisation, Wiley,1999.
40.Graeff, S., Steffens, D., Schubert, S.. Use of reflectance measurements for the early detection of N, P, Mg, and Fe d(?)ciencies in Zea mays[J]. Journal of Plant Nutrition and Science,2001, 164:445-450.
41. Guyer D E, Miles G. E., Gualtne, L. D., et al. Application of machine vision to shape analysis in leaf and plant identification[J]. Transactions of the ASAE.1993,36(1):163-171.
42. H. Midelfart, J. Komorowski. K. Norsett, et al. Learning rough set classfiers from gene expressions and clinical data[J]. Fundamenta Informatic.2002,53:155-183.
43.-H. Nakayama, Y. Hattori, R. Ishii. Rule extraction based on rough set theory and its application to medical data analysis[J]. Proceedings of the IEEE SMC Conference,1999,99 (5): 924-929.
44. HU Zhen-qi, HE Fen-qin, YIN Jian-zhong, et al. Estimation of Fractional Vegetation Cover Based on Digital Camera Survey Data and a Remote Sensing Model[J]. Journal of China University of Mining & Technology.2007,17(1):0116-0120.
45. Hunt, E.R., Cavigelli, M., Daughtry, et al. Evaluation of digital photography from model aircraft for remote sensing of crop biomass[J]. Precision Agriculture 2005,6 (4):359-378.
46. Ingrouille M J, Laird S M.. A quantitative approach to oak variability in some.north London woodlands [J]. The London Naturalist,1986,65:35-46.
47. J. Dougherty, R. Kohavi, M. Sahami. Supervised and unsupervised discretization of continuous features[J]. Proceedings of the Twelfth International Conference on Machine Learning,1995.
48. Jagdish K L, Agnes T P, Gloria C, et al. Nondestructive estimation of shoot-nitrogen indifferent rice genotypes[J]. Agronomy Journa,1998,90:33-40.
49. Jia, L., Chen, X., Zhang, F., Roemheld, et al. Use of digital camera to assess nitrogen status of winter wheat in the Northern. China Plain[J]. Journal of Plant Nutrition and Soil Science,2004, 27:441-450.
50. Johnson, J. F.. Nitrogen influence on fresh-leaf NIR spectra[J]. Remote. Sensing of Environment; 2001,78(3):314-320.
51. K. Thangavel, Q. Shen, A. Pethalakshmi. Application of clustering for feature selection based on rough set theory approach[J]. Journal of Artificial Intelligence and Machine Learning. 2006;-6 (1):19-27.
52. Krebel, Ulrich H G.. Pairwise classification and support vector machines[J]. Suppport Vector Lemaing. Massachusetts.1999,255-268,
53. Kwack,M.S.,Kim, E.N., Lee,H.,Kim, et al. Digital image analysis to measure lesion area of cucumber anthracnose by colletotrichum orbiculare[J]. Journal of General Plant Pahtology.2005, 71:418-421.
54. L. Jia, X. Chen, F. Zhang, A. Buerkert. Optimum nitrogen fertilization of winter wheat based on color digital camera images[J]. Communications in Soil Science and Plant Analysis,2007,38 (11):1385-1394.
55. L. Jia; X. Chen, F. Zhang. Optimum nitrogen fertilization of winter wheat based on color digital camera images[J]. Communications in Soil Science and Plant Analysis,2007,38: 1385-1394.
56. L.H. Chen, T.Y. Wang. Artificial neural networks to classify mean shifts from multivariate x2 chart signals[J]. Computers & Industrial Engineering.2004,47 (2-3):195.-205.
57. Laura Grunenfelder, Larry K. Hiller, N. Richard Knowles. Color indices for the assessment of chlorophyll development and greening of fresh market potatoes[J]. Postharvest Biology and Technology.2006,40:73-81.
58. Lee Tarpley, et al, Reflectance indices with precision and accuracy in predicting cotton leaf nitrogen concentration[J].Crop Science,2000,40:1814-1819.
59. Lemaire, G., Khaity, M., Onillon, B.,Allirand. Dynamics of accumulation.and partitioning of N leaves, stems and roots of lucerne in adense canopy[J]. Annals of Botany.1992,70:429-435.
60. Liu, Y.,Tong, Y., Smith, E.A.. Leaf chlorophyll readings as an indicator for spinach yield and nutritional quality with different nitrogen fertilizer applications[J]. Journal of Plant Nutrition and Soil Science.2006,29:1207-1217.
61. Mark A. Hall. Correlation-based feature selection for machine learning[D]. Hamilton, NewZealand. The University of Waikato.1999.
62. Michael Flowers, Randall Weisz, Ronnie Heiniger, Field validation of. a remote sensing technique for early nitrogen application decisions in wheat[J]. Agronomy Journal,2003, 95:167-176.
.63. Michael Flowers, Randall Weisz, Ronnie Heiniger. Quantitative approaches for using color infrared photography for assessing in-season nitrogen status in winter wheat[J]. Agronomy Journal,2003,95,1189-1200
64. Michela Milano. Operations research/computer science interfaces series[M]. Springer.2003, 139-152.
65. Miguel Pagola, Ruben Ortiza, Ignacio Irigoyen, et al. New method to assess barley nitrogen nutrition status based on image colour analysis comparison with SPAD-502[J]. Computers and Electronics in Agriculture.2009,65:213-218.
66. N. Kwak, C.H. Choi. Input feature selection by mutual information based on Parzen window [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence.2002,24 (12):1667-1671.
67. N. Moroney, M. D. Fairchild, R. R. Hunt, et al. The CIECAM02 color appearance model[J]. IS&T/SIS Tenth Color Imaging Conference,2002.
68. Noura Ziadi, Marianne Brassard, Gilles Belanger, et al. Chlorophyll measurements and nitrogen nutrition index for the evaluation of corn nitrogen status[J]. Agronomy Journal.2008, 100(5):1264-1273
69. Oide M., Ninomiya S. Discrimination of soybean leaflet shape by neural newtorks with image input[J]. Computers and Electronics in Agriculture.2000,29:.59-72.
70. Peng S, Garcia F V, Laza R C, et al. Increased N-use efficiency using a chlorophyll meter on high-yielding irrigated rice[J].Field Crops Research.1996,47:243-252.
71. Pinar A. Grass chlorophyll and the reflectance red edge[J]. International Journal of Remote Sensing,1996,17(2):351-357.
72. R. Kawashima, M. Sugiura, T. Kato, et al. An algorithm for estimating chlorophyll content in leaves using a video camera[J]. Annals of Botany.1998,80:49-54,.
73. R. Kohavi, G.H. John. Wrappers for feature subset selection[J]. Arf(?)cial Intelligence.1997, 97 (1-2):273-324.
74. R. Li, Z. Wong. Mining classification rules using rough sets and neural etworks[J].European Journal of Operational Research.2004,157:439-448.
75. Rafael C. Gonzalez, Richard E. Woods. Digital image processing eecond edition [M]. Publishing House of Electronics Industry. Beijing.2007.
76. Railyan V Y. Red edge structure of canopy reflectance spectra of triticale[J]. Remote Sensing Environment,1993,46(2):173-182.
77. Rasmus Houborg, Martha Anderson, Craig Daughtry, Utility of an image-based canopy reflectance modeling tool for remote estimation of LAI and leaf chlorophyll content at thefield scale[J]. Remote Sensing of Environment 2009,113:259-274.
78. Ray T S. Landmark eigenshpae analysis:homologous contours:leaf shpae in syngonium (Araceae) [J]. American Journal of Botany.1992,79:69-76.
79. Roth G. W., Fox R.H., Marshall H. G..Plant Tissue test for predicting nitrogen fertilizer requirement of winter wheat[J]. Agronomy Journal.1989,81(3):502-507.
80. S.L. Osborne, J. S. Schepers, D. D. Francis, et al. Detection of phosphorus and nitrogen deficiencies in corn using spectral radiance measurements[J]. Agronomy Journal,2002.94 (6), .1215-1221.
81.S.S.R. Abidi, K.M. Hoe, A. Goh, Analyzing data clusters:A rough set approach to extract cluster-defining symbolic rules[M]. LNCS 2189, in:Proceedings of the IDA,2001.
82. Scharpf, P.C. and Lory, J.A. Calibrating corn color from aerial photographs to predict sidedress nitrogen need[J]. Agronomy Journal,2002,94:397-404.
83. Seaife M.A. and K.L.Stevens. Monitoring sap nitratein vegetable crops:coneeniration of test strips with eectrode and effeets of time of day and leaf position[J]. Communications in soil science and plant analysis,1983,14(9):761-771.
84. Shannon L. Osborne; James S. Schepers, Mike R. Schlemmer, Detecting nitrogen.and phosphorus stress in corn using multi-spectral imagery[J]. Communications in Soil Science and Plant Analysis,2004,35:505-516.
85. Shibayama. Estimating grain yield of maturing rice canopies using high spectral resolution reflectance measurements[J], Remote Sensing Environment,1991,36(1):45-53.
86. Shibayama.Sessonal visible near-infrared and mid-infrared spectra of rice canopies in relation to LAI and aboveground dry Phytomass[J].Remote Sensing Environment,1989,27(2): 119-127.
87. Shibayamsa, M, and Akiyama, T.A.. Spectroradiometer for field use.VII. radiometric estimation of nitrogen levels in field rice canopies [J]. Japanese Journal of Crop Science,1986, 55(4):439-455.
88. Shigeto Kawashima, Makoto Nakatani. An algorithm for estimating chlorophyll content in leaves using a video camera[J]. Annals of Botany.1998,81:49-54.
89. Soderkvisti O. Computer vision classification of leaves from swedish tree [D]. Linkoping: Linkoping University,2001.
90. Tei, F., p. Benincasa and M.Guidueei. Critical nitrogen concentration in processing tomato[J]. European Journal of Agronomy,2002b,18:45-55.
91. Wengang Zhou, Chunguang Zhou, Guixia Liu, et al. Feature selection for microarray data analysis using mutual information and rough set theory[J]. Artificial Intelligence Applications and Innovations,2007,204:492-499.
92. Wester Veld, S M, Mckeown A W, et al. Chlorophyll and nitrate meters as nitrogen monitoring tools for selected vegetables in southern Ontario[J]. Acta Hort.,2002, 627(8): 259-266.
93. X. Hu. Using rough sets theory and database operations to construct a good ensemble of classifiers for datamining applications[J]. Proceedings of ICDM.2001:.233-240.
94. X.L. Li, Z.L. Du, T. Wang, et al. Audio feature selection based on rough set[J]. International Journal of Information Technology.2005,11 (6):117-123.
95. Yang C.C., Prasher S.O., Landry, J., et al. Development of an image processing system and a fuzzy algorithm for site-specific herbicide applications[J]. Precision Agriculture,2003; 4,5-18.
96. Z. Marzuki, F. Ahmad. Data mining discretization methods and.performances[J]. Proceedings of the International Conference on Electrical engineering informatics,:2007,.6: 535-537.
97. Z. Pawlak, J. Grzymala-Busse, R. Slowinski, et al, Rough sets.communications of the ACM[J].1995,38 (11):89-95.
98.艾天成,李方敏,周治安,等.作物叶片叶绿素含量与SPAD值相关性研究[J].湖北农学院学报,2000,20(1)：6-8.
99.蔡剑,邹薇,曹卫星 等.施氮水平对啤酒大麦叶片光合、SPAD和叶绿素荧光特性的影响[J].麦类作物学报,2007,27(1)：97-101
100.曹昊.BP神经网络在城镇基准地价评估中的应用及其成果网络发布研究[D].浙江大学硕士论文.2005.5
101.陈防,鲁剑巍SPAD-502叶绿素计在作物营养快速诊断上的应用初探[J].湖北农业科学,1996(2)：31-34.
102.陈佳娟,纪寿文,李娟,等.采用计算机视觉进行棉花虫害程度的自动测定[J].农业工程学报,2001,17(2)：157-160.
103.程一松,胡春胜,郝二波,等.氮素胁迫下的冬小麦高光谱特征提取与分析[J].资源科学,2003,25(1):86-93.
104.崔继林,易琼华.单季晚稻群体叶色“黑黄”变化的生理特点及其在高产形成中的作用[C].陈永康水稻高产经验研究(第1集).上海科技出版社.1964,30-42
105.房一鸣.用分类树算法进行上市公司评级的实证研究[D].对外经济贸易大学硕士论文,2006.4
106.冯伟,姚霞,朱艳,等.基于高光谱遥感的小麦叶片含氮量监测模型研究[J].麦类作物学报,2008,28(5)：851-860
107.何火娇,杨红云,唐建军,等.基于图像处理的水稻叶片三维可视化研究[J].江西农业大学学报,2008,30(1)：149-153
108.黄娟琴.杭州市区湿地资源遥感调查与监测研究[D].浙江大学硕士论文,2005.5
109.黄志开.彩色图像特征提取与植物分类研究[D].中国科学技术大学博士论文,2006.11
110.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田间杂草的研究[J].农业工程学报,2001,17(2)：154-156.
111.冀高.基于数字图像处理的棉花群体特征提取[D].北京邮电大学硕士论文,2007.2
112.贾良良,陈新平,作物氮营养诊断的无损测试技术[J].世界农业,2001,6：36-37.
113.姜雪.基于高分辨率遥感影像的矿区土地利用／土地覆盖信息提取技术研究[D].首都师范大学硕士论文,2007.6
114.金军,徐大勇,胡曙云,等.叶绿素仪穗肥诊断及其在水稻优质栽培中的应用[J].耕作与栽培,2003,2：14-16.
115.景娟娟,王纪华,王锦地,等.不同氮素营养条件下的冬小麦生理及光谱特性[J].遥感信息,2003,2：28-31.
116.雷泽湘,艾天成.草莓叶片叶绿素含量、含氮量与SPAD值间的关系[J].湖北农学院学报,2001,21(2)：138-140.
117.李合生.植物生理生化实验原理和技术[M].高等教育出版社.2000
118.李井会.不同氮肥运筹下马铃薯氮素利用特性及营养诊断的研究[D].吉林农业大学硕士论文.2006.6
119.李小正.基于机器视觉的棉花叶部特征图像识别的研究[D].北京邮电大学硕士论文.2007.2
120.李志宏,刘宏斌,张福锁.应用叶绿素仪诊断冬小麦氮营养状况的研究[J].植物营养与肥料学报,2003,9(4)：401-405.
121.刘国栋,刘更另.论缓解我国钾资源短缺问题的新对策[J].中国农业科学,1995,28(1)；25-32.
122.刘顺忠.数理统计理论、方法、应用和软件计算[M].武汉：华中科技大学出版社,2005：165.
123.刘艳菊,朱永官,丁辉,等.不同氮肥水平下SPAD读数与菠菜硝态氮含量关系的初步研究[J].农业环境科学学报,2004,23(3)：484-487.
124.吕雄杰.土壤水分与水稻氮素状况光谱特征研究[D].南京农业大学硕士论文,2004.6
125.罗鹏.基于3S技术的兰溪市低丘红壤资源调查及开发利用潜力评价[D].浙江大学硕士论文,2006.6
126.马瑞升.微型无人机航空遥感系统及其影像几何纠正研究[D].南京农业大学硕士论文,2004.6
127.毛罕平,徐贵力,等.番茄缺素叶片的图像特征提取和优化选择研究[J].农业工程学报,2003,19(2)：133-136.
128.孟军,陈温福,徐正进.水稻株型与冠层三维结构计算机模拟初报[J].中国农学通报,2005,21(6)：403-406.
129.牛铮,陈永华,隋洪智,等.叶片化学组分成像光谱遥感探测机理分析[J].遥感学报,2000,4(2)：125-130.
130.潘瑞帜,董愚得.植物生理学[M].高等教育出版社.1995.
131.邵新庆,冯全,邵世禄,等.基于叶片图像的植物鉴别技术研究进展[J].甘肃农业大学学报,2010,45(2)：156-160
132.石伟勇著.植物营养诊断与施肥[M].中国农业出版社.2005.
133.石媛媛,邓劲松,王珂,等.利用计算机视觉和光谱分割技术进行水稻叶片钾胁迫特征提取与诊断研究[J].光谱学与光谱分析.2010.30(1)：214-219.
134.宋述尧,王秀峰.数字图像技术在黄瓜氮素营养诊断上的应用研究[J].吉林农业大学学报,2008,30(4)：460-465.
135.宋绪忠,赵永军,张金凤,等.茶树叶片叶绿素含量与夜色值相关性研究[J].山东林业科技,2002,6：10-12.
136.孙伟艳.模式分类中特征选择问题的研究[D].哈尔滨理工大学硕士论文,2009.3
137.谭永生.像素级中高分辨率遥感影像融合研究[D].浙江大学硕士论文,2007.5
138.唐延林,黄敬峰.农业高光谱遥感研究的现状与发展趋势[J].遥感技术与应用,2002,16(4)：248-250.
139.唐延林,王人潮,张金恒,等.高光谱与叶绿素计快速测定大麦氮素营养状况研究[J].麦类作物学报,2003,23(1)：63-66.
140.陶勤南,方萍,吴良欢.水稻氮素营养的叶色诊断研究[J].土壤,1990,22(4)：190-193,197
141.田勇超,曹卫星,王绍华,等.不同水、氮条件下水稻不同叶位水、氮含量及光合速率的变化特征.作物学报,2004,30(11)：1129-1134.
142.王洪春.单季晚稻高产中叶色黑黄变化的生理基础探讨[C],陈永康水稻高产经验研究(第1集).上海科技出版社,1964,43-55.
143.王娟,雷咏雯,张永帅,等.应用数字图像分析技术进行棉花氮素营养诊断的研究[J].中国生态农业学报,2008,16(1)：145-149.
144.王娟.应用图像分析技术进行棉花氮素营养诊断的研究[D].石河子大学硕士论文,2006.6
145.王康,沈荣开,唐友生.用叶绿素测值(SPAD)评估夏玉米氮素状况的试验研究[J].灌溉排水,2002,21(4)：1-3,12.
146.王珂,沈掌泉,Abou-Ismailo,等.不同钾营养水平的水稻冠层和叶片光谱特征研究初报[J].科技通报,1997,13(4)：211-214.
147.王路,张蕾,周彦军,等.基于LVQ神经网络大植物种类识别[J].吉林大学学报(理学版),2007,45(3)：42-426.
148.王人潮,陈铭臻.水稻遥感估产的农学机理研究[J].浙江农业大学学报,1993,19(增刊)：7-29.
149.王绍华,曹卫星,王强盛,等.水稻叶色分布特点与氮素营养诊断[J].中国农业科学,2002,35(12)：1461-1466.
150.王绍华,刘胜环,王强盛,等.水稻产量形成与叶片含氮量及夜色的关系[J].南京农业大学学报,2005,25(4)：1-5.
151.王树文.计算机视觉技术在农产品自动检测与分级中的研究—番茄的表面缺陷自动检测与分类.东北农业大学硕士学位论文,2002.
152.王晓峰,黄德双,杜吉祥,等.叶片图像特征提取与识别技术的研究.计算机工程与应用,2006,3：190-193.
153.王晓静,张炎,李磐,等.地面数字图像技术在棉花氮素营养诊断中的初步研究[J].棉花学报,2007,19(2)：106-113.
154.王新辉.面向对象的高分辨率影像香榧分布信息提取研究[D].浙江大学硕士论文,2008.5
155.王秀峰.应用数字图像技术进行黄瓜和番茄氮素营养诊断的研究[D].吉林农业大学硕士论文,2005.6
156.邬飞波,许馥华,金珠群.利用叶绿素计对短季棉氮素营养诊断的初步研究[J].作物学报,1999,25(4)：483-488.
157.吴富宁.图象处理技术在冬小麦氮营养诊断中的应用[D].中国农业大学硕士论文,2004.6
158.吴良欢,陶勤南.水稻叶绿素计诊断追氮法研究[J].浙江农业大学学报,1999,25(2)：135-138.
159.肖焱波,贾良良,陈新平.应用数字图像分析技术进行冬小麦拔节期氮营养诊断[J].中国农学通报,2008,24,(8)：448-453
160.谢华,沈荣开,徐成剑,等.水、氮效应与叶绿素关系试验研究[J].中国农村水利电力,2003,8：40-43.
161.徐贵力,毛罕平,李萍萍.缺素叶片彩色图像颜色特征提取的研究[J].农业工程学报,2002,4：150-153.
162.徐豪.不同尺度田块信息遥感获取研究[D].浙江大学硕士论文,2007.5
163.徐师华,王修兰,吴毅明.不同光质(光谱)对作物生长发育的影响[J].生态农业研究,2003,8(1)：18-20.
164.薛利红,曹卫星,罗卫红,等.基于冠层反射光谱的水稻群体叶片氮素状况检测[J].中国农业科学,2003,36(7)：807-812.
165.薛利红,曹卫星,罗卫红,等.小麦叶片氮素状况与光谱特性的相关性研究[J].植物生态学报,2004,28(2)：172-177.
166.薛利红,罗卫红,曹卫星,等.作物水分和氮素光谱诊断研究进展[J].遥感学报,2003,7(1)：73-80.
167.杨长明,杨林章,韦朝领,等.不同品种水稻群体冠层光谱特征比较研究[J].应用生态学报,2002,13(6)：689-692.
168.杨相恒.氮、磷交互作用下小麦氮素营养丰缺的光谱诊断与估测[J].遥感信息,1992,4：28-34.
169.杨香凤.基于粗糙集的港口竞争力评价模型的构建与应用[D].江西财经大学硕士论文,2006.10
170.张宏名.农田作物光谱特征及应用[J].光谱学与光谱分析,1994,14(5)：25-30.
171.张金恒,王珂.基于鲜叶光谱估测氮素营养的新植被指数[J].农业工程学报,2008,24(3)：158-161.
172.张霞,刘良云,赵春江,等.利用高光谱遥感图像估算小麦氮含量[J].遥感学报,2003,7(3)：176-782.
173.张选怀,吴明山.水稻施用钾肥的效应[M].磷肥与复肥,2003,18(5)：63-68.
174.张玉森,姚霞,曹卫星,等.应用近红外光谱预测水稻叶片氮含量[J].应用生态学报,2010,36(4)：704-712.
175.张元.基于多光谱机器视觉的油菜氮素营养检测方法研究[D].江苏大学硕士论文,2009.6
176.章仲楚.面向对象的杭州西溪湿地遥感方法研究[D].浙江大学硕士论文,2007.11.
177.赵德华,李建龙,宋子健,等.不同施氮水平下棉花群体反射光谱的差异性分析[J].作物学报,2004,30(11)：1169-1172.
178.周冬琴,朱艳,田永超,等.以冠层反射光谱监测水稻叶片氮积累量的研究[J].作物学报,2006,32(9)：1316-1322.
179.祝锦霞,邓劲松,王珂,等.基于数字图像技术和水稻静态扫描叶片的氮素营养诊断研究[J].光谱学与光谱分析,2009.29(8)：2171-2175.