稻飞虱自动识别关键技术的研究
|
摘要
水稻是中国最主要的粮食作物,稻米是全国60%以上人口的主食,水稻生产在全国的农业生产和粮食安全中起着举足轻重的作用。稻飞虱类害虫属同翅目飞虱科,由于几种飞虱往往混合发生为害,因此稻飞虱只是一个统称。稻飞虱是水稻的主要害虫,主要包括白背飞虱、褐飞虱和灰飞虱,严重威胁着水稻生产。害虫的实时检测是进行病虫害综合防治的一种手段,只有准确的检测,才能做到有目的的防治,把害虫种群控制在经济损害水平以下,既不会因害虫造成损失,也不会因盲目防治造成浪费,加重对水稻和环境的污染。因此,只有研究有效的害虫自动检测技术,及时提供准确的害虫种类信息,才能为害虫的综合防治提供科学的决策依据。
目前农田害虫实时测报的现状是利用200W白炽灯诱虫,使用敌敌畏熏杀昆虫,植保人员晚上开灯,早上取回昆虫,进行人工分检、计数。毒死后的昆虫形态各异,足和触角的位置是随机的,也可能被折断而残缺,翅膀发生变形或缺损,另一方面,由于稻飞虱体形微小,色彩也不很艳丽,加之种类间对经济作物的为害程度差异很大,植保站工作人员有时用肉眼无法判断,只能借助放大镜、解剖镜甚至显微镜来观察,再借助检索表查出其种类。该方法识别效率低,对专家依赖性大,并且农药浸泡过的昆虫,散发毒气,危害测报人员身体健康。
当前国内外对昆虫自动识别技术的研究尚处在初期发展阶段,所进行的研究几乎都是在特定条件下进行的,研究的对象均为静态,许多昆虫分类样本来自于标准标本,或在实验室人工培养,与自然界昆虫在颜色、纹理、形状等方面存在着一定的差距,而在现实中,需要实时、动态地获取某个区域昆虫种群数量,去指导生产和实践,因此本文对如何采集主要针对稻飞虱的田间昆虫数字图像、稻飞虱的识别特征描述和昆虫分类模型等关键技术进行了研究。
组建了基于机器视觉的主要针对稻飞虱野外昆虫图像自动采集装置,获得了处于自然状态下昆虫数字图像。采集装置包括底座、采集工作台、拍摄系统和控制系统,采集工作台和拍摄系统安装在底座上。采集工作台由幕布驱动装置、采集工作台幕布及机架组成,采集工作台可以进行X向运动,采集工作台幕布可以实现Z向运动,采集工作台幕布为的确良白布,用160W自镇流荧光高压汞灯诱集稻飞虱爬附到采集工作台幕布上。拍摄系统由摄像机、拍摄光源、安装于摄像机上的显微变焦距镜头、摄像机支架、光源支架、摄像机工作台、光源工作台组成,拍摄光源配置于白色采集工作台幕布与摄像机之间,摄像机安装在摄像机支架上,上下及与采集工作台幕布之间的距离均可调,拍摄光源的上下及与摄像机之间的距离亦可单独调整,摄像机为彩色数字摄像机,拍摄光源采用环形冷光源。控制系统由计算机、微控制器、驱动器、图像采集卡组成,微控制器通过驱动器控制采集工作台X向运动和白色采集工作台幕布Z向运动,PC机利用摄像机和图像采集卡定时拍摄爬附着昆虫的采集工作台幕布,获取数字图像,PC机与微控制器相连,实现图像采集装置运动和图像自动拍摄协调进行。
区分稻飞虱的一个较稳定的特征是其背部的颜色和纹理,处理昆虫数字图像,提取疑似稻飞虱的单个昆虫虫体背部图像。取稻飞虱的蓝色分量B=140作为颜色阈值,进行图像二值化处理,设计形态学滤波器,去除足、触角和噪声等非目标区域,标记连通区域,计算各分割区域的面积,保留面积为(1398-3847)±50%像素的疑似稻飞虱区域,剔除形状大小与稻飞虱不相称的大部分昆虫,降低分类的工作量,再把图像分解成单个目标区域的二值化图像,与原始图像相与,得到信息完整的单个昆虫虫体背部图像,图像大小统一截为128×128像素。
利用傅里叶变换把昆虫背部区域图像从空间域变换到频域,用傅里叶频谱描述昆虫虫体背部颜色和纹理,提取描述昆虫虫体背部特征的l×l(l≤9)的二维傅里叶频谱窗口数据,窗口左上角始终为二维傅里叶频谱中心,构成p维识别昆虫的特征向量。根据四类昆虫虫体背部图像傅里叶频谱数据,计算每个特征在各类样本中的均值,81个特征的特征均值在4类样本中具有一定的差异,说明81个频谱特征在区分4类样本时是有效的；分析每个特征在各类样本中的方差,总体上81个频谱特征的波动程度不大,表明这些特征在表示各个类别时较为稳定；采用单因素方差分析法对81个频谱特征在各类样本中的显著性水平进行检验,只有7个不具有显著性差异的频谱特征,说明这些频谱特征在区分各类样本时是可行的,可以描述昆虫背部的颜色和纹理特征。
构建了基于支持向量机的昆虫分类模型。选取169张昆虫图像,其中白背飞虱、褐飞虱、灰飞虱三种稻飞虱图像分别为34张,共102张,其它昆虫图像有蚂蚁2张、露尾甲10张、水蝇2张、潜蝇19张、长蝽2张、盲蝽1张,共36张,三种叶蝉合计31张,用二维傅里叶频谱窗口数据构成p维描述昆虫虫体特征的特征向量,样本分成训练集和测试集两部分,采用标准的C-支持向量机,选用成对分类方法和径向基核函数,运用网格搜索的交叉验证方法选取最佳惩罚系数C和核函数参数σ,用训练集对分类模型进行训练,根据算法中使用的训练集,用被评价的分类算法求出决策函数,然后用测试集测试所得决策函数的准确率,得到不同傅里叶频谱窗口对训练集和测试集样本的测试结果,得到预测准确率基本上与四类昆虫虫体背部图像傅里叶频谱数据分析结论相符,表明设计的稻飞虱自动识别方案是可行的。
稻飞虱自动识别装置选用3×3二维傅里叶频谱窗口,即用9个特征向量来描述昆虫背部的颜色和纹理特征,建立基于支持向量机的昆虫分类模型,稻飞虱识别率达到90%以上,基本能反映水稻田稻飞虱的虫口密度。通过对田间昆虫数字图像采集、稻飞虱的识别特征描述和昆虫分类模型建立等关键技术的研究,探讨稻飞虱自动识别方法,有助于提高稻飞虱自动识别技术水平。
As the most important food crop, rice is the staple food for over60percent of Chinese population. Hence the production of rice plays a decisive part in agricultural production and food security all over the country. Rice plant hopper belongs to the family Delphacidae of Homoptera and is a general term for several kinds of plant hoppers, including Sogatella furcifera,Nilaparvata lugens and Laodelphax striatellus, which work together to damage rice. Rice plant hoppers are the main pests in paddy field and thus threaten the production of rice greatly. The real-time examination of pests is a way for integrated pest control. Only through accurate examination can we reach the aim, i.e. to control the number of insects, without either economic loss caused by pests, or waste and pollution of rice and environment due to excessive prevention. Therefore, it is obvious that only by study on effective automatic identification technology, can we get accurate information of pests in time and then can the scientific decision for integrated insect disease prevention be made.
Currently, the real-time detection and prediction of insects in paddy field relies on an identification method like this:the plant protector turns on a200w incandescent lamp at night to trap the insects which are soon killed by DDVP;in the next morning, insects are collected, sorted and counted by hand. Insects poisoned to death come in every shape, what's more, the location of feet and antennae is at random, and the feet, antennae and wings are likely to be broken. On the other hand, due to the tiny size and pale color of the rice plant hoppers and the sharp difference in the extent of damage to industrial crops, sometimes the insects can not be recognized by the naked eye. The plant protectors should observe them via magnifying glass, anatomical lens or even microscope, and later identify the categories in accordance with the identification key. The identification method is inefficient and depends too much on the experts, moreover, the poisonous gas given off by insects killed by insecticide will damage the staff's health.
The current study on the automatic identification technology for insects is still at the initial stage both at home and abroad. Most of the on-going studies have been conducted under specific circumstances, with the static subject of researches are static. The samples of insects for taxonomic studies are standard samples or samples artificially cultured in the laboratory, which differ more or less from insects in the nature in terms of color, texture and shape etc.However, the real-time and dynamic data of insects in a certain region are needed in the reality to guide the practice. Hence the paper did some research on some key techniques, i.e. how to collect the digital images of insects in the paddy field, esp. rice plant hoppers, how to describe the identification features of rice plant hoppers and how to establish the classification model for insects.
To acquire the digital images of insects, esp. rice plant hoppers, in a natural state, an automatic image acquisition device with machine vision has been designed. The acquisition equipment consists of control system, acquisition platform, camera system and a base where acquisition platform and camera system are fixed. The acquisition platform is composed of fixture, white Dacron curtain and curtain driving device. The acquisition platform can move in the X direction and the curtain can move in the Z direction. Rice plant hoppers can be trapped and adsorbed to the curtain by a160w self-ballasted high-pressure mercury vapor lamp. Camera system is composed of color digital camera, ring and cold light source, microscope zoom lens fixed on camera, camera stand, light source stand, camera platform and light sources platform. Light source is installed between the white curtain and camera, while the camera is installed on the camera stand. Both the light source and the camera can be adjusted upwards, downwards. What's more, the distance between the camera and the curtain is adjustable, while the distance between the camera and the light source can be adjusted separately. Control system is composed of computer, micro-controller, drive and image acquisition card. The micro-controller controls the acquisition platform to move in X direction and the white curtain in Z direction via the drive. The PC captures images from camera and image acquisition card which takes the picture of insects adsorbed on the curtain at regular intervals. And the connection of PC and micro-controller will coordinate the automation of camera shooting and the movement of image acquisition equipment.
The color and texture on the back of rice plant hoppers is a relatively stable feature to identify the insects. In the image processing, the image of the back of a single suspected rice plant hopper was extracted. First the paper chose the blue component of the image of rice plant hoppers (B=140) as the color threshold, binarized the image, and then worked out morphology-based filter to remove non-target areas, e.g. feet, antennae and noise. Later the paper marked the connected regions, calculated the size of segments, and selected those suspected rice plant hoppers whose size were similar to that of rice plant hoppers (1398-3847) and so as to reduce the taxonomic workload, it eliminated a majority of insects of which the shape and size were different from that of rice plant hoppers. Next the paper decomposed the images into binary images of a single target area, and captured images with complete information of single insects'back through the comparison with the original images. All the images are128by128pixels.
The paper transferred the regional images of insects'back from spatial domain to frequency domain, described the color and texture of insects'back through Fourier spectrum, and then extracted lxl(1≤9)2-D Fourier spectrum window data. With the top left corner of the windows always serving as the center, the paper finally constructed p-dimension eigenvector to identify insects. According to the Fourier spectrum data of the images of the back of four categories insects, the paper calculated the mean of each feature in all the samples. There are certain differences among the means of the81features in four groups of samples, hence the effectiveness of the81spectrum features in identifying the four groups of samples. After the analysis of the variance of each feature in different samples, it turns out that the fluctuation of the81spectrum features is not fierce on the whole, and that means the features are relatively stable when presenting the detailed samples. The examination of the significance level of the81spectrum features in the four groups of samples with single factor analysis of variance shows that only seven spectrum features don't have a significant difference, which means these spectrum features can be applied to describe the color and texture of the back of insects and it is feasible to identify different samples by these spectrum features.
A model for classifying insects has been constructed based on support vector machine. All in all,169images of insects were selected, including34pictures of Sogatella furcifera,34pictures of Nilaparvata,34pictures of Laodelphax striatellus,31pictures of three kinds of leaf hoppers, and36pictures of other insects, i.e.2pictures of ant,10pictures of sap beetle,2pictures of shore fly,19pictures of rice stem maggot,2pictures of lygaeid,1picture of flea hopper. First the paper constructed a p-dimension eigenvector to describe the characteristics of the insects on the basis of data of2-D Fourier spectrum window, and then divided the samples into two parts, i.e. training set and test set. Later the paper utilized standard C-support vector machine, radial base kernel function and the one-against-one classification method, chose the best penalty coefficient C and kernel function parameter σ, and trained the classifier model with training set. Next, in accordance with training set used in the process of algorithm, the paper worked out a decision function via the taxonomic algorithm being assessed. Finally, depending on the accuracy of the decision function tested by test set, the paper got the different test results of training set and test set samples through different Fourier spectrum windows. The accuracy of the prediction is approximately in accordance with the result of Fourier spectrum data analysis of the images of the back of four categories of insects, which means the feasibility of the design of automatic identification for rice plant hoppers.
Automatic identification equipment for rice plant hoppers chooses3×32-D Fourier spectrum window, i.e.9eigenvectors are used to describe the color and texture of insects'back, to construct classification model for insects on the basis of support vector machine. With this equipment, the recognition rate of rice plant hoppers reaches above90%. Hence we can come to the conclusion that this equipment can basically reflect the density of rice plant hoppers in fields. To explore the automatic identification technology for rice plant hoppers through the study on some key techniques, i.e. the digital image acquisition of insects in the paddy field, the description of the identification features of rice plant hoppers and the establishment of the classification model for insects, contributes to raising the level of automatic identification technology for rise plant hoppers.
目前农田害虫实时测报的现状是利用200W白炽灯诱虫,使用敌敌畏熏杀昆虫,植保人员晚上开灯,早上取回昆虫,进行人工分检、计数。毒死后的昆虫形态各异,足和触角的位置是随机的,也可能被折断而残缺,翅膀发生变形或缺损,另一方面,由于稻飞虱体形微小,色彩也不很艳丽,加之种类间对经济作物的为害程度差异很大,植保站工作人员有时用肉眼无法判断,只能借助放大镜、解剖镜甚至显微镜来观察,再借助检索表查出其种类。该方法识别效率低,对专家依赖性大,并且农药浸泡过的昆虫,散发毒气,危害测报人员身体健康。
当前国内外对昆虫自动识别技术的研究尚处在初期发展阶段,所进行的研究几乎都是在特定条件下进行的,研究的对象均为静态,许多昆虫分类样本来自于标准标本,或在实验室人工培养,与自然界昆虫在颜色、纹理、形状等方面存在着一定的差距,而在现实中,需要实时、动态地获取某个区域昆虫种群数量,去指导生产和实践,因此本文对如何采集主要针对稻飞虱的田间昆虫数字图像、稻飞虱的识别特征描述和昆虫分类模型等关键技术进行了研究。
组建了基于机器视觉的主要针对稻飞虱野外昆虫图像自动采集装置,获得了处于自然状态下昆虫数字图像。采集装置包括底座、采集工作台、拍摄系统和控制系统,采集工作台和拍摄系统安装在底座上。采集工作台由幕布驱动装置、采集工作台幕布及机架组成,采集工作台可以进行X向运动,采集工作台幕布可以实现Z向运动,采集工作台幕布为的确良白布,用160W自镇流荧光高压汞灯诱集稻飞虱爬附到采集工作台幕布上。拍摄系统由摄像机、拍摄光源、安装于摄像机上的显微变焦距镜头、摄像机支架、光源支架、摄像机工作台、光源工作台组成,拍摄光源配置于白色采集工作台幕布与摄像机之间,摄像机安装在摄像机支架上,上下及与采集工作台幕布之间的距离均可调,拍摄光源的上下及与摄像机之间的距离亦可单独调整,摄像机为彩色数字摄像机,拍摄光源采用环形冷光源。控制系统由计算机、微控制器、驱动器、图像采集卡组成,微控制器通过驱动器控制采集工作台X向运动和白色采集工作台幕布Z向运动,PC机利用摄像机和图像采集卡定时拍摄爬附着昆虫的采集工作台幕布,获取数字图像,PC机与微控制器相连,实现图像采集装置运动和图像自动拍摄协调进行。
区分稻飞虱的一个较稳定的特征是其背部的颜色和纹理,处理昆虫数字图像,提取疑似稻飞虱的单个昆虫虫体背部图像。取稻飞虱的蓝色分量B=140作为颜色阈值,进行图像二值化处理,设计形态学滤波器,去除足、触角和噪声等非目标区域,标记连通区域,计算各分割区域的面积,保留面积为(1398-3847)±50%像素的疑似稻飞虱区域,剔除形状大小与稻飞虱不相称的大部分昆虫,降低分类的工作量,再把图像分解成单个目标区域的二值化图像,与原始图像相与,得到信息完整的单个昆虫虫体背部图像,图像大小统一截为128×128像素。
利用傅里叶变换把昆虫背部区域图像从空间域变换到频域,用傅里叶频谱描述昆虫虫体背部颜色和纹理,提取描述昆虫虫体背部特征的l×l(l≤9)的二维傅里叶频谱窗口数据,窗口左上角始终为二维傅里叶频谱中心,构成p维识别昆虫的特征向量。根据四类昆虫虫体背部图像傅里叶频谱数据,计算每个特征在各类样本中的均值,81个特征的特征均值在4类样本中具有一定的差异,说明81个频谱特征在区分4类样本时是有效的；分析每个特征在各类样本中的方差,总体上81个频谱特征的波动程度不大,表明这些特征在表示各个类别时较为稳定；采用单因素方差分析法对81个频谱特征在各类样本中的显著性水平进行检验,只有7个不具有显著性差异的频谱特征,说明这些频谱特征在区分各类样本时是可行的,可以描述昆虫背部的颜色和纹理特征。
构建了基于支持向量机的昆虫分类模型。选取169张昆虫图像,其中白背飞虱、褐飞虱、灰飞虱三种稻飞虱图像分别为34张,共102张,其它昆虫图像有蚂蚁2张、露尾甲10张、水蝇2张、潜蝇19张、长蝽2张、盲蝽1张,共36张,三种叶蝉合计31张,用二维傅里叶频谱窗口数据构成p维描述昆虫虫体特征的特征向量,样本分成训练集和测试集两部分,采用标准的C-支持向量机,选用成对分类方法和径向基核函数,运用网格搜索的交叉验证方法选取最佳惩罚系数C和核函数参数σ,用训练集对分类模型进行训练,根据算法中使用的训练集,用被评价的分类算法求出决策函数,然后用测试集测试所得决策函数的准确率,得到不同傅里叶频谱窗口对训练集和测试集样本的测试结果,得到预测准确率基本上与四类昆虫虫体背部图像傅里叶频谱数据分析结论相符,表明设计的稻飞虱自动识别方案是可行的。
稻飞虱自动识别装置选用3×3二维傅里叶频谱窗口,即用9个特征向量来描述昆虫背部的颜色和纹理特征,建立基于支持向量机的昆虫分类模型,稻飞虱识别率达到90%以上,基本能反映水稻田稻飞虱的虫口密度。通过对田间昆虫数字图像采集、稻飞虱的识别特征描述和昆虫分类模型建立等关键技术的研究,探讨稻飞虱自动识别方法,有助于提高稻飞虱自动识别技术水平。
As the most important food crop, rice is the staple food for over60percent of Chinese population. Hence the production of rice plays a decisive part in agricultural production and food security all over the country. Rice plant hopper belongs to the family Delphacidae of Homoptera and is a general term for several kinds of plant hoppers, including Sogatella furcifera,Nilaparvata lugens and Laodelphax striatellus, which work together to damage rice. Rice plant hoppers are the main pests in paddy field and thus threaten the production of rice greatly. The real-time examination of pests is a way for integrated pest control. Only through accurate examination can we reach the aim, i.e. to control the number of insects, without either economic loss caused by pests, or waste and pollution of rice and environment due to excessive prevention. Therefore, it is obvious that only by study on effective automatic identification technology, can we get accurate information of pests in time and then can the scientific decision for integrated insect disease prevention be made.
Currently, the real-time detection and prediction of insects in paddy field relies on an identification method like this:the plant protector turns on a200w incandescent lamp at night to trap the insects which are soon killed by DDVP;in the next morning, insects are collected, sorted and counted by hand. Insects poisoned to death come in every shape, what's more, the location of feet and antennae is at random, and the feet, antennae and wings are likely to be broken. On the other hand, due to the tiny size and pale color of the rice plant hoppers and the sharp difference in the extent of damage to industrial crops, sometimes the insects can not be recognized by the naked eye. The plant protectors should observe them via magnifying glass, anatomical lens or even microscope, and later identify the categories in accordance with the identification key. The identification method is inefficient and depends too much on the experts, moreover, the poisonous gas given off by insects killed by insecticide will damage the staff's health.
The current study on the automatic identification technology for insects is still at the initial stage both at home and abroad. Most of the on-going studies have been conducted under specific circumstances, with the static subject of researches are static. The samples of insects for taxonomic studies are standard samples or samples artificially cultured in the laboratory, which differ more or less from insects in the nature in terms of color, texture and shape etc.However, the real-time and dynamic data of insects in a certain region are needed in the reality to guide the practice. Hence the paper did some research on some key techniques, i.e. how to collect the digital images of insects in the paddy field, esp. rice plant hoppers, how to describe the identification features of rice plant hoppers and how to establish the classification model for insects.
To acquire the digital images of insects, esp. rice plant hoppers, in a natural state, an automatic image acquisition device with machine vision has been designed. The acquisition equipment consists of control system, acquisition platform, camera system and a base where acquisition platform and camera system are fixed. The acquisition platform is composed of fixture, white Dacron curtain and curtain driving device. The acquisition platform can move in the X direction and the curtain can move in the Z direction. Rice plant hoppers can be trapped and adsorbed to the curtain by a160w self-ballasted high-pressure mercury vapor lamp. Camera system is composed of color digital camera, ring and cold light source, microscope zoom lens fixed on camera, camera stand, light source stand, camera platform and light sources platform. Light source is installed between the white curtain and camera, while the camera is installed on the camera stand. Both the light source and the camera can be adjusted upwards, downwards. What's more, the distance between the camera and the curtain is adjustable, while the distance between the camera and the light source can be adjusted separately. Control system is composed of computer, micro-controller, drive and image acquisition card. The micro-controller controls the acquisition platform to move in X direction and the white curtain in Z direction via the drive. The PC captures images from camera and image acquisition card which takes the picture of insects adsorbed on the curtain at regular intervals. And the connection of PC and micro-controller will coordinate the automation of camera shooting and the movement of image acquisition equipment.
The color and texture on the back of rice plant hoppers is a relatively stable feature to identify the insects. In the image processing, the image of the back of a single suspected rice plant hopper was extracted. First the paper chose the blue component of the image of rice plant hoppers (B=140) as the color threshold, binarized the image, and then worked out morphology-based filter to remove non-target areas, e.g. feet, antennae and noise. Later the paper marked the connected regions, calculated the size of segments, and selected those suspected rice plant hoppers whose size were similar to that of rice plant hoppers (1398-3847) and so as to reduce the taxonomic workload, it eliminated a majority of insects of which the shape and size were different from that of rice plant hoppers. Next the paper decomposed the images into binary images of a single target area, and captured images with complete information of single insects'back through the comparison with the original images. All the images are128by128pixels.
The paper transferred the regional images of insects'back from spatial domain to frequency domain, described the color and texture of insects'back through Fourier spectrum, and then extracted lxl(1≤9)2-D Fourier spectrum window data. With the top left corner of the windows always serving as the center, the paper finally constructed p-dimension eigenvector to identify insects. According to the Fourier spectrum data of the images of the back of four categories insects, the paper calculated the mean of each feature in all the samples. There are certain differences among the means of the81features in four groups of samples, hence the effectiveness of the81spectrum features in identifying the four groups of samples. After the analysis of the variance of each feature in different samples, it turns out that the fluctuation of the81spectrum features is not fierce on the whole, and that means the features are relatively stable when presenting the detailed samples. The examination of the significance level of the81spectrum features in the four groups of samples with single factor analysis of variance shows that only seven spectrum features don't have a significant difference, which means these spectrum features can be applied to describe the color and texture of the back of insects and it is feasible to identify different samples by these spectrum features.
A model for classifying insects has been constructed based on support vector machine. All in all,169images of insects were selected, including34pictures of Sogatella furcifera,34pictures of Nilaparvata,34pictures of Laodelphax striatellus,31pictures of three kinds of leaf hoppers, and36pictures of other insects, i.e.2pictures of ant,10pictures of sap beetle,2pictures of shore fly,19pictures of rice stem maggot,2pictures of lygaeid,1picture of flea hopper. First the paper constructed a p-dimension eigenvector to describe the characteristics of the insects on the basis of data of2-D Fourier spectrum window, and then divided the samples into two parts, i.e. training set and test set. Later the paper utilized standard C-support vector machine, radial base kernel function and the one-against-one classification method, chose the best penalty coefficient C and kernel function parameter σ, and trained the classifier model with training set. Next, in accordance with training set used in the process of algorithm, the paper worked out a decision function via the taxonomic algorithm being assessed. Finally, depending on the accuracy of the decision function tested by test set, the paper got the different test results of training set and test set samples through different Fourier spectrum windows. The accuracy of the prediction is approximately in accordance with the result of Fourier spectrum data analysis of the images of the back of four categories of insects, which means the feasibility of the design of automatic identification for rice plant hoppers.
Automatic identification equipment for rice plant hoppers chooses3×32-D Fourier spectrum window, i.e.9eigenvectors are used to describe the color and texture of insects'back, to construct classification model for insects on the basis of support vector machine. With this equipment, the recognition rate of rice plant hoppers reaches above90%. Hence we can come to the conclusion that this equipment can basically reflect the density of rice plant hoppers in fields. To explore the automatic identification technology for rice plant hoppers through the study on some key techniques, i.e. the digital image acquisition of insects in the paddy field, the description of the identification features of rice plant hoppers and the establishment of the classification model for insects, contributes to raising the level of automatic identification technology for rise plant hoppers.
引文
[1]辛良杰,李秀彬.近年来我国南方双季稻区复种的变化及其政策启示[J].自然资源学报,2009,24(1)：58-65.
[2]胡忠孝.中国水稻生产形势分析[J].杂交水稻,2009,24(6)：1-7.
[3]丁锦华,苏建亚.农业昆虫学[M].北京：中国农业出版社,2002,6.
[4]刘玉彬,包绍永,林莉,李晓铭.灰飞虱传毒特性研究初报[J].植物保护,1990,16(1)：6-7.
[5]Heinrichs E. Management of Rice Inset Pests[J]. National IPM Network, Minnesota University,1998.
[6]http://www.cana.gov.cn.2010-7-22.
[7]王艳青.近年来中国水稻病虫害发生及趋势分析[J].中国农学通报,2006,22(2)：343-347.
[8]姜辉,林荣华,刘亮,瞿唯钢,陶传江.稻飞虱的危害及再猖獗机制[J].昆虫知识,2005,42(6)：612-615.
[9]王智,颜亨梅,吕志跃,王洪全.稻田蜘蛛优势种对叶蝉控制力分析[J].生命科学研究,2001,5(1)：76-79.
[10]祝增荣,程家安,商晗武.甲胺磷+澳氰菊酯对褐飞虱及其捕食性天敌种群动态的影响[J].植保技术推广,1998,18(4)：28-31.
[11]刘贤进,杜正文.不同药剂褐稻虱的田间种群毒理机制初探[J].昆虫学报,1995,38(4)：502-504.
[12]庄永林,沈晋良,陈峥.三唑磷对不同翅型稻褐飞虱繁殖力的影响[J].南京农业大学学报,1999.22(3)：21-24.
[13]蔡元呈,林永,许国忠.甲基异柳磷引起稻飞虱增殖原因探讨[J].植保技术与推广1998,18(5)：28-30.
[14]江幸福,罗礼智.昆虫迁飞的调控基础及展望[J].生态学报,2008,28(6)：2835-2842.
[15]刘泽文,韩召军,王荫长.褐飞虱抗有机磷品系的交互抗性及适合度研究[J].南京农业大学学报,2001,24(4)：37-40.
[16]林友伟,张晓梅,沈晋良.亚洲稻区灰飞虱抗药性研究进展[J].昆虫知识,2005,42(1)：28-30.
[17]李淑华.气候变化对水稻虫害的影响[J].灾害学,1995,10(2)：43-47.
[18]叶正襄,秦厚国,李华.温度、食料条件对白背飞虱种群增长的影响[J].植物保护学报,1994,21(3)：209-213.
[19]陈仕高,石登贵,谢雪梅,薄正国,刘光杰.重庆市秀山县稻飞虱发生特点及其原因分 析[J].昆虫知识,2003,40(2)：179-182.
[20]章烈辉,刘占山,肖启明,康听东,刘年喜.我国水稻病虫害综合防治技术研究现状及发展建议[J].中国稻米,2009,(1)：6-9.
[21]中华人民共和国国家标准.稻飞虱测报调查规范(GB/T15794-1995)[S].国家技术监督局,1995.
[22]赵树英.佳多频振式杀虫灯的开发与应用[J].中国森林病虫,2002,12(21)：6-8.
[23]王克如.基于图像识别的作物病虫草害诊断研究[D].北京：中国农业科学院,2005.
[24]张家兴.可持续农业中21世纪初的IPM[J].植物保护,1998,24(6)：38-40.
[25]张法全,基于机器视觉和小波分析的农田害虫识别系统[D].郑州：郑州大学,2003.
[26]Shaker N, Wolfe R R. Image Processing for Tomato Grading [C]. Trans of the ASAI,1990, 33(4):564-572.
[27]Tao Y, Heinemann P H, Varghese Z. Machine vision for color inspection of potatoes and apples [C]. Transaction of the A S A E,1995,38(5):1555-1561.
[28]Tang L, Tian L, Steward B L. Color image segmentation with genetic algorithm for in2field weed sensing[J]. Transaction of ASAE,2000,43(4):1019-1027.
[29]Shear S A, Holmes R G. Plant identification using clor cooccurrence matrices [C]. Transactions of the ASAE,1990,33(6):2037-2044.
[30]Ryu K H, Kim G, Ham J S. Development of a robotic transplanter for bedding plants[J].J Agric Eng Res,2001,78(2):141-146.
[31]蒋焕煜,彭永石,申川,应义斌.基于双目立体视觉技术的成熟番茄的识别与定位[J].农业工程学报,2008,24(8)：279-283.
[32]宋凯,孙晓艳,纪建伟.基于支持向量机的玉米叶部病害识别[J].农业工程学报,2007,(01)：97-101.
[33]王晓峰,黄德双,杜吉祥,张国军.叶片图像特征提取与识别技术的研究[J].计算机工程与应用,2006(3)：190-193.
[34]王勇,沈明霞,姬长英.采摘期成熟棉花不同部位颜色识别分析[J].农业工程学报,2007,23(4)：183-185.
[35]王勇,姬长英.田间早期成熟棉花识别研究[J].江西农业学报,2006,18(6)：141-143.
[36]王勇,沈明霞,姬长英.基于颜色信息和形状特征的棉桃识别方法[J].农业机械学报,2007,38(11)：77-79,87.
[37]王勇,沈明霞,姬长英.基于色差信息的田间成熟棉花识别[J].浙江农业学报,2007,]9(5)：385-388.
[38]http://4a.njau.edu.cn/eno/.
[39]丁锦华,张富满.东北飞虱志[M].北京：中国农业科技出版社,1994.
[40]John L S, Quentin W, Paul J, Shaun W, Donald H, David L. Accelerating taxonomic discovery through automated character extraction[J]. Zootaxa,2009,2217:43-55.
[41]李清西.计算机在昆虫分类中的新用途[J].昆虫分类学报,2000,22(2)：153-156.
[42]Daly H V, Hoelmer K Norman P, Allen T. Computer-assisted measurement and identification of honeybees(Hymenoptera: Apidae)[J]. Annals of the Entomological Society of America,1982,75:591-592.
[43]Vigneault C, Roger C, Boivin G. Study of the behavior of insects with the assistance of computer vision [J]. Resume des Rechereches Centre de Rechereche et de Development en Horticulture, Saint Jean sur Richelieu, Quebec,1994,23:52-53.
[44]Lucas P J J Noldus, Andrew J Spink, Ruud A J Tegelenbosch. Computerized video tracking, movement analysis and behavior recognition in insects [J]. Computers and Electronics in Agriculture,2002,35:201-227.
[45]Habib G, Nadipuram R P, John J E, et al. A neuro-fuzzy approach for insect classification[C]. World Automation Congress, Third International Symposium on Soft Computing for Industry, Maui, Hawaii,2000.
[46]Adsvakulchai S, Baimai V, Prachyabrued W, et al. Morphometric Study Using Wing Image Analysis for Identification of the Bactrocera dorsalis Complex(Diptera:Tephritidae)[J]. Journal of Biology,1998,3. (URL:http://www.epress.com/w3jbio/vol3/Adsavakulchai/index.html)
[47]White R J, Winokur L. Quantitative description discrimination of butterfly wing patterns using moment invariant analysis[J]. Bulletin of Entomological Research,2003,93:361-374.
[48]Zayas I Y, Flinn P W. Detection of insects in bulk wheat samples with machine vision[J]. Transaction of the ASAE,1998,41(3):883-888.
[49]Karunakaran C, Jayas D S. Detection of interal wheat seed infestation by Rhyzopertha dominica using X-ray imaging[J]. Journal of Stored Products Research,2004,40:507-516.
[50]Ridway C, Davies E R, Chambers J. Imaging for the high-speed detection of pest insects and contaminants in cereal grain in transit[C]. ASAE Meeting paper No,01-3056, California, USA,2001:1-7.
[51]Ridway C, Davies E R, Chambers J, et al. Rapid machine vision method for the detecting of insects and other particulate bio-contaminants of bulk grain in transit[J]. Biosystems Engineering,2002,83(1):21-30.
[52]Davies E R Bateman M, Mason D R, et al. Design of efficient line segment detectors for cereal grain inspection [J]. Pattern Recognition Letters,2003,24:413-428.
[53]Becerra J M, Valdecasas A G. Landmark Superimposition for Taxonomic Identification[J]. Biological Journal of the Linnean Society,2003,81:267-274.
[54]Moraes E M, Manfrin M H, Laus A C, et al. Wing Shape Heritability and Morphological Divergence of the Sibling Species Drosophila mercatorum and Drosophila paranaensis[J]. Heredity,2004,92:466-473.
[55]Pretorius E. Using Geometric Morphometrics to Investigate Wing Dimorphism in Males and Females of Hymenoptera- a Case Study Based on the Genus Techysphex Kohl(Hymenoptera: Sphecidae:Larrinae)[J]. Journal of Entomology,2005,44:113-121.
[56]Weeks P J D, O'Neill M A, Gaston K J, et al. Automating Insect Identification:Exploring the Limitations of a Prototype System [J]. Applied Entomology,1999,123:1-8.
[57]Pajak M. Identification of British Bombus and Megabombus Using DAISY[D]. B. A.3rd year Honours Project,2000,Oxford.
[58]Watson A T, O'Neill M A, Kitching I J. A Qualitative Study Investigating Automated Identification of Living Macrolepidoptera using the Digital Automated Identification System (DAISY)[J]. Systematic Biology,2003,1(3):287-300.
[59]O'Neill M A. DAISY:a Practical Tool for Semi-automated Species Identification. pp6 [URL:http://www.fao.org./AG/agp/agps/C-CAB/Castudies/pdf/3-001.pdf].
[60]http://129.49.19.42/morph/index.html.
[61]http://www.infonnatik.uni-bonn.de/projects/ABIS/
[62]Arbuckle T, Schroder S, Steinhage V, et al. Biodiversity Informatics in Action: Identification and Monitoring of Bee Species using ABIS Sustainability in the Information Society[C]. Informatics for Environmental Protection,2001,1:425-430.
[63]Houle D, Mezey J, Galpern P, et al. Automated measurement of Drosophila wings[J]. BMC Evolutionary biology,2003,3pp13. [http://ww.biomedcentral.com/1471-2148/3/25].
[64]Gilchrist A S, Crisafulli D C A. Using Variation in Wing Shape to Distinguish Between Wild and Mass-reared Individuals of Queensland Fruit Fly, Bactrocera tryoni[J]. Netherlands Entomological Society,2006,119:175-178.
[65]Nagy S, Hayde M, Panzenbock B, et, al. Toxopert-I:knowledgebased automatic interpretation of serological tests for toxoplasmosis [J]. Computer Method Program Biomed, 1997,53:119-133.
[66]Shankar P, Walji M, Ali A, et, al. Decision support systems to identify different species of malarial parasites [J]. AMIA Annu Symp Proc,2003,1:1006.
[67]Macleod N. Automated Taxon Identification in Systematics:Theory, Approaches and Applications[M]. London:CRC press,2007.
[68]Wheeler Q D. Invertebrate systematics or spineless taxonomy[J]. Zootaxa,2007,1688:11- 18.
[69]Deans A R, Kawada R. Alobevania, a new genus of neotropical ensige wasps(Hymenoptera: Evaniidae), with three new species:integrating taxonomy with the World Wide Web[J]. Zootaxa,2008,1787:28-44.
[70]Pyle R L, Earle J L, Greene B D. Five new species of the damselfish genus Chromis (Perciformes:Labroidei:Pomacentridae)from deep coral reefs in the tropical western Pacific[J]. Zootaxa,2008,1671:3-31.
[71]Johnson N F, Masner L, Musetti L, Noort S, Rajmohana K, Darling D C, Guidotti A, Polaszek A. Revision of world species of the genus Heptascelio Kieffer(Hymenoptera: Platygastroidea, Platygastridae). Zootaxa,2008,1776:1-51.
[72]Liu J D. The_Expert System for Identification of Tortricinae(Lepidoptera) Using Image Analysis of Venation [J]. Entomologica Sinca,1996,3(1):1-8.
[73]Liu J D. How to Construct the Expert System for Species Identification Using Venation of Tortricinae(Lepidoptera) [J]. Entomologica Sinca,1996,3(2):133-137.
[74]沈佐锐,于新文.昆虫数学形态学研究及其应用展望[J].昆虫学报,1998,41(增刊)：140-148.
[75]于新文,沈佐锐.图像分割算法在棉铃虫图像处理中的应用[J].中国农业大学学报,2001,6(5)：69-75.
[76]赵汗青,沈佐锐,于新文.数学形态特征应用于昆虫自动鉴别的研究[J].中国农业大学学报,2002,7(3)：38-42.
[77]赵汗青,沈佐锐,于新文.数学形态特征应用于昆虫自动鉴别的研究Ⅰ在目阶元上的应用研究[J].昆虫学报,2003,46(1)：45-50.
[78]于新文,沈佐锐,高灵旺等.图像几何形状特征的提取技术研究[J].中国农业大学学报,2003,8(3)：47-50.
[79]左西年,刘来福,王心丽等.基于Tensor Voting (?)勺蚁蛉翅脉修补[J].北京师范大学学报(自然科学版).2005,41(2)：135-138
[80]张红梅,范艳峰,田耕.基于数字图像处理技术的储粮害虫分类识别研究[J].河南工业大学学报,2005,26(2)：19-22.
[81]张红涛,毛罕平,邱道尹.储粮害虫图像识别中的特征提取[J].农业工程学报,2009,25(2)：126-130.
[82]邱道尹,张成花,张红涛等.神经网络在储粮害虫识别中的应用[J].农业工程学报,2003,19(1)：142-144.
[83]胡玉霞,张红涛.基于模拟退火算法-支持向量机的储粮害虫识别分类[J].农业机械学报,2008,39(9)：108-111.
[84]方明,周龙.基于BP神经网络的储粮害虫分类识别研究[J].武汉工业学院学报,2009,28(4)：70-73.
[85]马骏,王建华.一种基于数学形态学的植物病虫识别方法[J].深圳大学学报理工版,2004,21(1)：72-75.
[86]唐强,基于图像模式识别技术的昆虫识别研究[D].昆明：昆明理工大学,2006.
[87]周秀明.基于图像识别的森林害虫分类方法研究[D].哈尔滨：东北林业大学,2007.
[88]刘斌,杨永跃,陈伟.基于机器视觉的蟋蟀体态测量[J].工业控制计算机.2008,21(4)：42-43.
[89]毛文华,郑永军,苑严伟,张小超.基于色度和形态特征的蝗虫信息提取技术[J].农业机械学报,2008,39(9)：104-107.
[90]王剑.基于神经网络的水道三化螟识别系统的设计与实现[D].北京：中国农业科学院,2006.
[91]周曼,周明全.基于BP神经网络的水稻害虫自动识别[J].北京师范大学学报(自然科学版),2008,44(2)：165-167.
[92]姚玉霞,陈桂芬,侯元村,于合龙.水稻病虫害诊治智能化专家系统[J].吉林大学学报,2003,21(4)：378-381.
[93]杨宏伟,张云.计算机视觉技术在昆虫识别中的应用进展[J].生物信息学,2005,3(3)：133-136.
[94]陈月华,杨方.基于计算机视觉的害虫识别技术研究进展[J]农机化研究,2008,1：209-211.
[95]李健,陈长明.基于计算机视觉的农作物害虫自动检测研究综述[J].微型电脑应用,2009,25(12)：62-64.
[96]管泽鑫,姚青,杨保军,胡洁,唐健.数字图像处理技术在农作物病虫草识别中的应用[J].中国农业科学,2009,42(7)：2349-2358.
[97]徐鹏,陈乃中,杨定,自动识别技术在昆虫分类鉴别中的应用[J].昆虫知识,2010,47(2)：256-262.
[98]何振毅,陆永忠.病媒昆虫分类技术的研究进展[J].中国国境卫生检疫杂志,2006,29(3)：190-193.
[99]Houle D, Mezey J, Galpen P, Carter A. Automated measurement if Drosophila wings[J]. BMC Evolutionary Biology,2003,3:25.
[100]Gaston K, O'Neil M. Automated species identification:why not? Philosophical Transactions of the Royal Society,2004,359:655-667.
[1]张五一,赵强松,王东云.机器视觉的现状及发展趋势[J].中原工学院学报,2008,19(1)：9-15.
[2]李福建,张元培.机器视觉系统组成研究[J].自动化博览,2004,(02)：61-63.
[3]张纪明.基于PC的机器视觉系统研究[J].可编程控制器与工厂自动化,2006,(11)：107-109.
[4]张建生,赵燕伟,郭建江,胡圣尧.数控系统应用及开发[M].北京：科学出版社,2006.
[5]吴振彪.机电综合设计指导[M].北京：中国人民大学出版社,2000.
[6]机械设计手册编委会编著.机械设计手册[M].北京：机械工业出版社,2004.
[7]朱思洪.机电一体化技术[M].北京：中国农业出版社,2005.
[8]南京工艺装备制造有限公司产品手册.
[9]杨玲玲.水稻飞虱自动识别技术的研究[D].南京：南京农业大学,2008.
[10]刘立春.昆虫趋光行为的初步观察[J].南京农学院学报,1982,(2)：52-59.
[11]刘立春,朱白平,徐炜民,蔡平元,黄建.高效双波诱虫灯田问试验及应用效果[J].昆虫知识,2005,42(2)：202-206.
[12]周强,徐瑞清,程小桐.昆虫的生物光电效应与虫害治理应用[J].现代生物医学进展,2006,6(4)：70-72.
[13]Janesic J R, Elliot S T, Collins A S, et al. Scientific Charge-Coupled Devices[J]. Optical Engineering,1986,26(8):692-714.
[14]韩冰,林明星,丁凤华.机器视觉技术及其应用分析[J].农业装备与车辆工程,2008,(10)：24-27.
[15]俞晓磊,赵志敏,陈远,郭林峰,汪东华.基于机器视觉的梳棉机棉结在线检测[J].传感器与微系统,2008,27(7)：96-98.
[1]丁克坚,檀根甲,胡官保,李高峰.水稻主要病害诊断、预测、防治专家系统的研究[J].安徽农业大学学报,1998,25(2)：133-137.
[2]范艳峰,甄彤.谷物害虫检测与分类识别技术的研究及应用[J].计算机工程,2005,31(12)：187-189,213.
[3]刘金桥,吴金强.机器视觉系统发展及其应用[J].机械工程与自动化,2010,(1)：215-216.
[4]何立民.单片机应用系统设计[M].北京：北京航空航天大学出版社,1996.
[5]张友德,赵志英,涂时亮.单片微型机原理、应用与实验[M].上海：复旦大学出版社,1999.
[6]周明安,朱光忠,宋晓华,肖俊建.步进电机驱动技术发展及现状[J].机电工程技术,2005,34(2)：16-17.
[7]陈兴文,刘燕.基于单片机的步进电动机细分驱动器设计[J].电机与控制应用,2009,36(7)：30-33.
[8]Bailey S Y. Servomotor and Stepper: Key Elements of Control Design[J]. Control Engineering,2003,(6):36-50.
[9]郑阿奇,丁有和Visual C++教程[M].北京：清华大学出版社,2005.
[10]李朝青.PC机与单片机串行通信技术[M].北京：北京航空航天大学出版社,2000.
[1]边肇棋,张学工.模式识别[M].北京：清华大学出版社,2007.
[2]罗希平,田捷,诸葛婴,王靖,戴汝为.图像分割方法综述[J].模式识别与人工智能,1999,12(3)：300-312.
[3]陈武凡.小波分析及其在图像处理中的应用[M].北京：科学出版社,2002.
[4]Pal N R, Pal S K.A review on image segmentation techniques[J]. Pattern Recognition,1993, 26(9):1277-1294.
[5]林开颜,吴军辉,徐立鸿.彩色图像分割方法综述[J].中国图像图形学报,2005,10(1)：1-10.
[6]陈冬岚,刘京南,余玲玲.几种图像分割阈值选取方法的比较与研究[J].机械制造与自动化,2003,(1)：77-80.
[7]乐宋进,武和雷,胡泳芬.图像分割方法的研究现状与展望[J].南昌水专学报,2004,23(2)：15-21.
[8]杨晖,曲秀杰.图像分割方法综述[J].电脑开发与应用,2005,18(3)：21-23.
[9]Hance G A, Umbaugh S E, Moss R H, et al. Unsupervised color image segmentation with application to skin tumor borders[J]. IEEE Engineering in Medicine and Biology,1996, 15(1):104-111.
[10]Ohta Y, Kanade T, Sakai T. Color information for region segmentation[J]. Computer Graphics and Image Processing,1980,13(3):222-241.
[11]Gonzalez R C, Woods R E数字图像处理[M].北京：电子工业出版社,2003.
[12]王玲,王萍,陈兵林,刘善军,姬长英.基于颜色阈值的田间籽棉图像分割技术[J].作物学报,2010,36(3)：502-507.
[13]Ahmad I S, Reid J F. Evaluation of color representations for maize image[J]. Agricultural Engineerng Research,1996,63:185-196.
[14]贾永红.数字图像处理[M].武汉：武汉大学出版社,2003.
[15]陈杨,陈荣娟,郭颖辉Matlab6.X图形编程与图像处理[M].西安：西安电子科技大学出版社,2002.
[16]Lin Zhenxian, Song Guoxiang, Xue Wen. Comparisom and Improvement of Several Methods on Wavelet Image Denoising[J]. Journal of Xidian University,2004,31(4):626-629.
[17]张建伟.基于计算机视觉技术的微小昆虫自动计数研究[D].中国农业大学,2003.
[i8]况菲,王耀南,余洪山,万琴.一种基于学习向量量化神经网络的图像分割方法[J].计算机工程与应用,2005,(14)：34-36.
[19]Huang C L. Parallel image segmentation using modified Hopfield mldel[J]. Pattern Recognition Letters,1993,13(5):345-353.
[20]杭后俊.基于扫描线算法的多边形区域填充图案[J].计算机时代,2009,(3)：22-23,26.
[21]Pfitzmann B. Trials of Traced Traitor[C]. Springer LNCS 1174,1996,49-63.
[22]Han J W, Kamber M. Data Mining: Concepts and Techniques[M]. Morgan Kaufmann Publishers, Inc,2001.
[23]姚敏,郁晓红,易文晟,江志伟.数字图像处理[M].北京：机械工业出版社,2006.
[24]徐贵力,毛罕平.利用傅里叶变换提取图像纹理特征新方法[J].光电工程,2004,33(11)：55-58.
[25]朱小燕,王松.傅里叶变换在粘连文字图像切分中的应用[J].计算机学报,1999,22(12)：1246-1252.
[26]王金满,曲艳杰,李坚.傅里叶变换图像方法在材解剖特征研究上的应用[J].四川农业大学学报,1998,16(1)：177-181.
[27]周云龙,范振儒,苏耀雷.基于图像傅里叶变换纹理特征和概率神经网络的气固化床流型识别[J].化工自动化及仪表,2009,36(2)：38-42.
[28]多化琼,王喜明,范俊雄.利用傅立叶变换研究铁杉木材管胞横截面尺寸[J].北京林业大学学报,2009,31(5)：108-111.
[29]Zhou F F, Shi J Q. Texture feature based on local fourier transform[C]. IEEE International Conference on ImageProcessing,2001,17(2):610-613.
[30]Castalman K R. Digital Image Processing[M]. Pretice hall,1998.
[31]Li Wen-xin, David Zhang, XU Zhuo-qun. Recongnition Based on Fourier Transform [J]. Journall of Software,2002,13(5):879-886.
[32]Tsai Du-Ming, Huang Tse-Yun. Automated sureface inspection for statistical textures[J]. Image and Vision Computing,2003,21(4):307-323.
[33]Yoko M, Yoji I, Minoru F. Transerse shape analysis of xylem ground tissues by Fourier transform image analysis I:Trial for statistical expression of cell arrangements with fluctuation[J]. Journal of Wood Science,2005,51(3):201-208.
[34]Yoko M, Minoru F. Transverse shape analysis of xylem ground tissues by Fourier transform image analysis Ⅱ:Cell wall direction and reconstruction of cell shapes[J]. Journal of Wood Science,2005,51(3):209-217.
[35]Yoko M, Minoru F. Transverse shape analysis of xylem ground tissues by The Fourier transform image analysis Ⅲ:Shape reconstruction of earlywood tracheids in 22 species and some parameters for normalizing cell shapes[J].Journal of the Japan Wood Research Society,2005,51 (4):218-226.
[36]盛骤,谢式千,潘承毅.概率论与数理统计(第三版)[M].北京：高等教育出版社,2005：270-282.
[1]Vapnik V N. The Nature of Statistical Learning Theory[M]. New York:Springer-Verlag, 1995.
[2]Sklansky J, Wassel G N. Pattern Classifiers and Trainable Machines[M]. New York: Spring-Verlag,1982.
[3]Muller K R, Ratsch G, Ratsch G. An Introduction to Kernel Based Learning Algorithms[J]. IEEE Transactions on Neural Networks,2001,12 (2):181-201.
[4]Burges C J. A Tutorial on Support Vector Machines for Pattern Recognition[J]. Knowledge Discovery and Data Mining,1998,2(2):121-167.
[5]Scholkopf B, Burges C. Input Space Versus Feature Space in Kernel Based Methods[J]. IEEE Transactions on Neural Networks,1999,10(5):1000-1017.
[6]Vapnik V N, Lemer A. Patern Recognition Using Generalized Portrait Method[J]. Automation and Remote Control,1963,24:79-92.
[7]Vapnik V N, Chervoknenkis A Y. The Necessary and Sufficient Conditions for consistency in the Empirical Risk Minimization Method[J]. Pattern Recognition and Image Analysis, 1991,1(3):283-305.
[8]Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[J]. IEEE Transactions on Neural Networks,1999,10(5):1055-1064.
[9]Cristianini N, Shawa-Taylor J. An Introduction of Support Vector Machines and Other Kernel-based Learning Methods[M]. Cambridge University Press,2000.
[10]邵惠鹤.支持向量机理论及其应用[J].自动化博览,2003,(1)：94-99.
[11]Rowley H A, Baluja S, Kaasade T. Neural Network Based Face Detection[C]. IEEE Trans. Pattern Anal.1998:23-38.
[12]许建华,张学工,李衍达.支持向量机的新发展[J].控制与决策,2004,19(5)：81-84.
[13]邓乃扬,田英杰.支持向量机—理论、算法与拓展[M].北京：科学出版社,2009.
[14]Chapelle O. Choosing kernel parameters for support vector machines[J]. Machine Learning, 2002,46(1):131-159.
[15]Boser B, Guyon, Vapnik V N. a training algorithm for optimal margin classifiers[C]. Fifth Annual Workshop on Computational Learning Theory, Pittsburgh ACM,1992:144-152.
[16]付麦霞,廉飞宇,张元.基于视频和SVM的储粮害虫检测与识别[J].计算机与数字工程,2008,36(11)：111-115.
[17]Hsu C W, Lin C J.A comparison of methods for multi-class support vector machines[J]. IEEE Transactions on Neural Networks,2002,13(2):415-425.
[18]Weston J, Watkins C. Multi-class support vector machines[J]. Technical Report,1998, CSD-TR-98-04:1-9.
[19]Huang W, Robert M. Face detection and precise eyes location[C]. in Proc.15th Int. Conf. Pattern Recognition, Barcelona, Spain, Sep.3-7,2000, vol.4, pp.722-727.
[20]Hunke M, Waibel A. Face locating and tracking for human computer interaction[C]. in 28th Asilomar Conference on Signals, Systems and Computers, Monterey, CA,1994.
[21]Jing Z, Mariani R. Glasses detection and extraction by deformable contour[J]. in Proceedings of the 15th International Conference on Pattern Recognition[J],2000, Vol. Ⅱp. 4B.
[22]Kim H C, Pang S N, He H M, et al. Constructing support vector machine ensemble[J] Pattern Recognition,2003,36(12):2757-2767.
[23]张铃,张钹.支持向量机理论与基于规划的神经网络学习算法[J].计算机学报,2001,24(2)：113-118.
[24]Dietterich T G, Bakiri G. Solving multi-class learning problems via error-correcting output codes[J]. Journal of Artificial Intelligence Research,1995,2:263-286.
[25]Crammer K, Singer Y. On the learnability and design of output codes for multiclass problems[J]. Computational Learning Theory,2000:35-46.
[26]任东.基于支持向量机的植物病害识别研究[D].长春：吉林大学,2007.
[27]徐海样.基于支持向量机方法的图像分割与目标分类[D].武汉：华中科技大学,2005.
[28]Hsu w H, Lin C J. A comparison of methods for multi-class support vector machines[J]. IEEE Transactions on Neural networks,2002,13(2):415-425.
[29]Muller K R, Mika S, Ratsch G, Tsuda K, Scholkopf B. An introduction to kernel-based learning algorithm[J]. IEEE Transactions on Neural Networks,2001,12(2):181-201.
[30]Cortes C, Vapnik V. Support-vector network[J]. Machine Learning,1995,20:273-297.
[31]吴涛.核函数的性质、方法及其在障碍检测中的应用[D].长沙：国防科学技术大学,2003.
[32]Cortes C, Vapnik V. Support vector networks [J]. Machine Learning,1995,20:273-297.
[33]Genton M G. Classes of kernels for machine learning:a statistics perspective [J]. Journal of Machine Learning Research,2001,2:299-312.
[34]江龙建.基于计算机视觉和神经网络的牛肉大理石花纹自动分级技术的研究[D].南京.南京农业大学,2003.
[35]李盼池,许少华.支持向量在模式识别中的核函数特性分析[J].计算机工程与设计,2005,26(2)：302-304.
[36]Burges C J C. A tutorial on support vector machines for pattern recognition [J]. Data Mining and Knowledge Discovery,1998,2(2):1-47.
[37]Chin-Chung Chang, Chin-Jen Lin. LIBSVM:a Library for Support Vector Machines.2010, 3.
[38]Vladimir C, Yunqian M. Practical Selection of SVM Parameters and Noise Estimation for SVM Regression[J]. Neural Networks,2004,17(1):113-126.
[39]闫国华,朱永生.支持向量机回归的参数选择方法[J].计算机工程,2009,35(13)：218-220.
[40]林升梁,刘志.基于RBF核函数的支持向量机参数选择[J].浙江工业大学学报,2007,35(2)：163-167.
[2]胡忠孝.中国水稻生产形势分析[J].杂交水稻,2009,24(6)：1-7.
[3]丁锦华,苏建亚.农业昆虫学[M].北京：中国农业出版社,2002,6.
[4]刘玉彬,包绍永,林莉,李晓铭.灰飞虱传毒特性研究初报[J].植物保护,1990,16(1)：6-7.
[5]Heinrichs E. Management of Rice Inset Pests[J]. National IPM Network, Minnesota University,1998.
[6]http://www.cana.gov.cn.2010-7-22.
[7]王艳青.近年来中国水稻病虫害发生及趋势分析[J].中国农学通报,2006,22(2)：343-347.
[8]姜辉,林荣华,刘亮,瞿唯钢,陶传江.稻飞虱的危害及再猖獗机制[J].昆虫知识,2005,42(6)：612-615.
[9]王智,颜亨梅,吕志跃,王洪全.稻田蜘蛛优势种对叶蝉控制力分析[J].生命科学研究,2001,5(1)：76-79.
[10]祝增荣,程家安,商晗武.甲胺磷+澳氰菊酯对褐飞虱及其捕食性天敌种群动态的影响[J].植保技术推广,1998,18(4)：28-31.
[11]刘贤进,杜正文.不同药剂褐稻虱的田间种群毒理机制初探[J].昆虫学报,1995,38(4)：502-504.
[12]庄永林,沈晋良,陈峥.三唑磷对不同翅型稻褐飞虱繁殖力的影响[J].南京农业大学学报,1999.22(3)：21-24.
[13]蔡元呈,林永,许国忠.甲基异柳磷引起稻飞虱增殖原因探讨[J].植保技术与推广1998,18(5)：28-30.
[14]江幸福,罗礼智.昆虫迁飞的调控基础及展望[J].生态学报,2008,28(6)：2835-2842.
[15]刘泽文,韩召军,王荫长.褐飞虱抗有机磷品系的交互抗性及适合度研究[J].南京农业大学学报,2001,24(4)：37-40.
[16]林友伟,张晓梅,沈晋良.亚洲稻区灰飞虱抗药性研究进展[J].昆虫知识,2005,42(1)：28-30.
[17]李淑华.气候变化对水稻虫害的影响[J].灾害学,1995,10(2)：43-47.
[18]叶正襄,秦厚国,李华.温度、食料条件对白背飞虱种群增长的影响[J].植物保护学报,1994,21(3)：209-213.
[19]陈仕高,石登贵,谢雪梅,薄正国,刘光杰.重庆市秀山县稻飞虱发生特点及其原因分 析[J].昆虫知识,2003,40(2)：179-182.
[20]章烈辉,刘占山,肖启明,康听东,刘年喜.我国水稻病虫害综合防治技术研究现状及发展建议[J].中国稻米,2009,(1)：6-9.
[21]中华人民共和国国家标准.稻飞虱测报调查规范(GB/T15794-1995)[S].国家技术监督局,1995.
[22]赵树英.佳多频振式杀虫灯的开发与应用[J].中国森林病虫,2002,12(21)：6-8.
[23]王克如.基于图像识别的作物病虫草害诊断研究[D].北京：中国农业科学院,2005.
[24]张家兴.可持续农业中21世纪初的IPM[J].植物保护,1998,24(6)：38-40.
[25]张法全,基于机器视觉和小波分析的农田害虫识别系统[D].郑州：郑州大学,2003.
[26]Shaker N, Wolfe R R. Image Processing for Tomato Grading [C]. Trans of the ASAI,1990, 33(4):564-572.
[27]Tao Y, Heinemann P H, Varghese Z. Machine vision for color inspection of potatoes and apples [C]. Transaction of the A S A E,1995,38(5):1555-1561.
[28]Tang L, Tian L, Steward B L. Color image segmentation with genetic algorithm for in2field weed sensing[J]. Transaction of ASAE,2000,43(4):1019-1027.
[29]Shear S A, Holmes R G. Plant identification using clor cooccurrence matrices [C]. Transactions of the ASAE,1990,33(6):2037-2044.
[30]Ryu K H, Kim G, Ham J S. Development of a robotic transplanter for bedding plants[J].J Agric Eng Res,2001,78(2):141-146.
[31]蒋焕煜,彭永石,申川,应义斌.基于双目立体视觉技术的成熟番茄的识别与定位[J].农业工程学报,2008,24(8)：279-283.
[32]宋凯,孙晓艳,纪建伟.基于支持向量机的玉米叶部病害识别[J].农业工程学报,2007,(01)：97-101.
[33]王晓峰,黄德双,杜吉祥,张国军.叶片图像特征提取与识别技术的研究[J].计算机工程与应用,2006(3)：190-193.
[34]王勇,沈明霞,姬长英.采摘期成熟棉花不同部位颜色识别分析[J].农业工程学报,2007,23(4)：183-185.
[35]王勇,姬长英.田间早期成熟棉花识别研究[J].江西农业学报,2006,18(6)：141-143.
[36]王勇,沈明霞,姬长英.基于颜色信息和形状特征的棉桃识别方法[J].农业机械学报,2007,38(11)：77-79,87.
[37]王勇,沈明霞,姬长英.基于色差信息的田间成熟棉花识别[J].浙江农业学报,2007,]9(5)：385-388.
[38]http://4a.njau.edu.cn/eno/.
[39]丁锦华,张富满.东北飞虱志[M].北京：中国农业科技出版社,1994.
[40]John L S, Quentin W, Paul J, Shaun W, Donald H, David L. Accelerating taxonomic discovery through automated character extraction[J]. Zootaxa,2009,2217:43-55.
[41]李清西.计算机在昆虫分类中的新用途[J].昆虫分类学报,2000,22(2)：153-156.
[42]Daly H V, Hoelmer K Norman P, Allen T. Computer-assisted measurement and identification of honeybees(Hymenoptera: Apidae)[J]. Annals of the Entomological Society of America,1982,75:591-592.
[43]Vigneault C, Roger C, Boivin G. Study of the behavior of insects with the assistance of computer vision [J]. Resume des Rechereches Centre de Rechereche et de Development en Horticulture, Saint Jean sur Richelieu, Quebec,1994,23:52-53.
[44]Lucas P J J Noldus, Andrew J Spink, Ruud A J Tegelenbosch. Computerized video tracking, movement analysis and behavior recognition in insects [J]. Computers and Electronics in Agriculture,2002,35:201-227.
[45]Habib G, Nadipuram R P, John J E, et al. A neuro-fuzzy approach for insect classification[C]. World Automation Congress, Third International Symposium on Soft Computing for Industry, Maui, Hawaii,2000.
[46]Adsvakulchai S, Baimai V, Prachyabrued W, et al. Morphometric Study Using Wing Image Analysis for Identification of the Bactrocera dorsalis Complex(Diptera:Tephritidae)[J]. Journal of Biology,1998,3. (URL:http://www.epress.com/w3jbio/vol3/Adsavakulchai/index.html)
[47]White R J, Winokur L. Quantitative description discrimination of butterfly wing patterns using moment invariant analysis[J]. Bulletin of Entomological Research,2003,93:361-374.
[48]Zayas I Y, Flinn P W. Detection of insects in bulk wheat samples with machine vision[J]. Transaction of the ASAE,1998,41(3):883-888.
[49]Karunakaran C, Jayas D S. Detection of interal wheat seed infestation by Rhyzopertha dominica using X-ray imaging[J]. Journal of Stored Products Research,2004,40:507-516.
[50]Ridway C, Davies E R, Chambers J. Imaging for the high-speed detection of pest insects and contaminants in cereal grain in transit[C]. ASAE Meeting paper No,01-3056, California, USA,2001:1-7.
[51]Ridway C, Davies E R, Chambers J, et al. Rapid machine vision method for the detecting of insects and other particulate bio-contaminants of bulk grain in transit[J]. Biosystems Engineering,2002,83(1):21-30.
[52]Davies E R Bateman M, Mason D R, et al. Design of efficient line segment detectors for cereal grain inspection [J]. Pattern Recognition Letters,2003,24:413-428.
[53]Becerra J M, Valdecasas A G. Landmark Superimposition for Taxonomic Identification[J]. Biological Journal of the Linnean Society,2003,81:267-274.
[54]Moraes E M, Manfrin M H, Laus A C, et al. Wing Shape Heritability and Morphological Divergence of the Sibling Species Drosophila mercatorum and Drosophila paranaensis[J]. Heredity,2004,92:466-473.
[55]Pretorius E. Using Geometric Morphometrics to Investigate Wing Dimorphism in Males and Females of Hymenoptera- a Case Study Based on the Genus Techysphex Kohl(Hymenoptera: Sphecidae:Larrinae)[J]. Journal of Entomology,2005,44:113-121.
[56]Weeks P J D, O'Neill M A, Gaston K J, et al. Automating Insect Identification:Exploring the Limitations of a Prototype System [J]. Applied Entomology,1999,123:1-8.
[57]Pajak M. Identification of British Bombus and Megabombus Using DAISY[D]. B. A.3rd year Honours Project,2000,Oxford.
[58]Watson A T, O'Neill M A, Kitching I J. A Qualitative Study Investigating Automated Identification of Living Macrolepidoptera using the Digital Automated Identification System (DAISY)[J]. Systematic Biology,2003,1(3):287-300.
[59]O'Neill M A. DAISY:a Practical Tool for Semi-automated Species Identification. pp6 [URL:http://www.fao.org./AG/agp/agps/C-CAB/Castudies/pdf/3-001.pdf].
[60]http://129.49.19.42/morph/index.html.
[61]http://www.infonnatik.uni-bonn.de/projects/ABIS/
[62]Arbuckle T, Schroder S, Steinhage V, et al. Biodiversity Informatics in Action: Identification and Monitoring of Bee Species using ABIS Sustainability in the Information Society[C]. Informatics for Environmental Protection,2001,1:425-430.
[63]Houle D, Mezey J, Galpern P, et al. Automated measurement of Drosophila wings[J]. BMC Evolutionary biology,2003,3pp13. [http://ww.biomedcentral.com/1471-2148/3/25].
[64]Gilchrist A S, Crisafulli D C A. Using Variation in Wing Shape to Distinguish Between Wild and Mass-reared Individuals of Queensland Fruit Fly, Bactrocera tryoni[J]. Netherlands Entomological Society,2006,119:175-178.
[65]Nagy S, Hayde M, Panzenbock B, et, al. Toxopert-I:knowledgebased automatic interpretation of serological tests for toxoplasmosis [J]. Computer Method Program Biomed, 1997,53:119-133.
[66]Shankar P, Walji M, Ali A, et, al. Decision support systems to identify different species of malarial parasites [J]. AMIA Annu Symp Proc,2003,1:1006.
[67]Macleod N. Automated Taxon Identification in Systematics:Theory, Approaches and Applications[M]. London:CRC press,2007.
[68]Wheeler Q D. Invertebrate systematics or spineless taxonomy[J]. Zootaxa,2007,1688:11- 18.
[69]Deans A R, Kawada R. Alobevania, a new genus of neotropical ensige wasps(Hymenoptera: Evaniidae), with three new species:integrating taxonomy with the World Wide Web[J]. Zootaxa,2008,1787:28-44.
[70]Pyle R L, Earle J L, Greene B D. Five new species of the damselfish genus Chromis (Perciformes:Labroidei:Pomacentridae)from deep coral reefs in the tropical western Pacific[J]. Zootaxa,2008,1671:3-31.
[71]Johnson N F, Masner L, Musetti L, Noort S, Rajmohana K, Darling D C, Guidotti A, Polaszek A. Revision of world species of the genus Heptascelio Kieffer(Hymenoptera: Platygastroidea, Platygastridae). Zootaxa,2008,1776:1-51.
[72]Liu J D. The_Expert System for Identification of Tortricinae(Lepidoptera) Using Image Analysis of Venation [J]. Entomologica Sinca,1996,3(1):1-8.
[73]Liu J D. How to Construct the Expert System for Species Identification Using Venation of Tortricinae(Lepidoptera) [J]. Entomologica Sinca,1996,3(2):133-137.
[74]沈佐锐,于新文.昆虫数学形态学研究及其应用展望[J].昆虫学报,1998,41(增刊)：140-148.
[75]于新文,沈佐锐.图像分割算法在棉铃虫图像处理中的应用[J].中国农业大学学报,2001,6(5)：69-75.
[76]赵汗青,沈佐锐,于新文.数学形态特征应用于昆虫自动鉴别的研究[J].中国农业大学学报,2002,7(3)：38-42.
[77]赵汗青,沈佐锐,于新文.数学形态特征应用于昆虫自动鉴别的研究Ⅰ在目阶元上的应用研究[J].昆虫学报,2003,46(1)：45-50.
[78]于新文,沈佐锐,高灵旺等.图像几何形状特征的提取技术研究[J].中国农业大学学报,2003,8(3)：47-50.
[79]左西年,刘来福,王心丽等.基于Tensor Voting (?)勺蚁蛉翅脉修补[J].北京师范大学学报(自然科学版).2005,41(2)：135-138
[80]张红梅,范艳峰,田耕.基于数字图像处理技术的储粮害虫分类识别研究[J].河南工业大学学报,2005,26(2)：19-22.
[81]张红涛,毛罕平,邱道尹.储粮害虫图像识别中的特征提取[J].农业工程学报,2009,25(2)：126-130.
[82]邱道尹,张成花,张红涛等.神经网络在储粮害虫识别中的应用[J].农业工程学报,2003,19(1)：142-144.
[83]胡玉霞,张红涛.基于模拟退火算法-支持向量机的储粮害虫识别分类[J].农业机械学报,2008,39(9)：108-111.
[84]方明,周龙.基于BP神经网络的储粮害虫分类识别研究[J].武汉工业学院学报,2009,28(4)：70-73.
[85]马骏,王建华.一种基于数学形态学的植物病虫识别方法[J].深圳大学学报理工版,2004,21(1)：72-75.
[86]唐强,基于图像模式识别技术的昆虫识别研究[D].昆明：昆明理工大学,2006.
[87]周秀明.基于图像识别的森林害虫分类方法研究[D].哈尔滨：东北林业大学,2007.
[88]刘斌,杨永跃,陈伟.基于机器视觉的蟋蟀体态测量[J].工业控制计算机.2008,21(4)：42-43.
[89]毛文华,郑永军,苑严伟,张小超.基于色度和形态特征的蝗虫信息提取技术[J].农业机械学报,2008,39(9)：104-107.
[90]王剑.基于神经网络的水道三化螟识别系统的设计与实现[D].北京：中国农业科学院,2006.
[91]周曼,周明全.基于BP神经网络的水稻害虫自动识别[J].北京师范大学学报(自然科学版),2008,44(2)：165-167.
[92]姚玉霞,陈桂芬,侯元村,于合龙.水稻病虫害诊治智能化专家系统[J].吉林大学学报,2003,21(4)：378-381.
[93]杨宏伟,张云.计算机视觉技术在昆虫识别中的应用进展[J].生物信息学,2005,3(3)：133-136.
[94]陈月华,杨方.基于计算机视觉的害虫识别技术研究进展[J]农机化研究,2008,1：209-211.
[95]李健,陈长明.基于计算机视觉的农作物害虫自动检测研究综述[J].微型电脑应用,2009,25(12)：62-64.
[96]管泽鑫,姚青,杨保军,胡洁,唐健.数字图像处理技术在农作物病虫草识别中的应用[J].中国农业科学,2009,42(7)：2349-2358.
[97]徐鹏,陈乃中,杨定,自动识别技术在昆虫分类鉴别中的应用[J].昆虫知识,2010,47(2)：256-262.
[98]何振毅,陆永忠.病媒昆虫分类技术的研究进展[J].中国国境卫生检疫杂志,2006,29(3)：190-193.
[99]Houle D, Mezey J, Galpen P, Carter A. Automated measurement if Drosophila wings[J]. BMC Evolutionary Biology,2003,3:25.
[100]Gaston K, O'Neil M. Automated species identification:why not? Philosophical Transactions of the Royal Society,2004,359:655-667.
[1]张五一,赵强松,王东云.机器视觉的现状及发展趋势[J].中原工学院学报,2008,19(1)：9-15.
[2]李福建,张元培.机器视觉系统组成研究[J].自动化博览,2004,(02)：61-63.
[3]张纪明.基于PC的机器视觉系统研究[J].可编程控制器与工厂自动化,2006,(11)：107-109.
[4]张建生,赵燕伟,郭建江,胡圣尧.数控系统应用及开发[M].北京：科学出版社,2006.
[5]吴振彪.机电综合设计指导[M].北京：中国人民大学出版社,2000.
[6]机械设计手册编委会编著.机械设计手册[M].北京：机械工业出版社,2004.
[7]朱思洪.机电一体化技术[M].北京：中国农业出版社,2005.
[8]南京工艺装备制造有限公司产品手册.
[9]杨玲玲.水稻飞虱自动识别技术的研究[D].南京：南京农业大学,2008.
[10]刘立春.昆虫趋光行为的初步观察[J].南京农学院学报,1982,(2)：52-59.
[11]刘立春,朱白平,徐炜民,蔡平元,黄建.高效双波诱虫灯田问试验及应用效果[J].昆虫知识,2005,42(2)：202-206.
[12]周强,徐瑞清,程小桐.昆虫的生物光电效应与虫害治理应用[J].现代生物医学进展,2006,6(4)：70-72.
[13]Janesic J R, Elliot S T, Collins A S, et al. Scientific Charge-Coupled Devices[J]. Optical Engineering,1986,26(8):692-714.
[14]韩冰,林明星,丁凤华.机器视觉技术及其应用分析[J].农业装备与车辆工程,2008,(10)：24-27.
[15]俞晓磊,赵志敏,陈远,郭林峰,汪东华.基于机器视觉的梳棉机棉结在线检测[J].传感器与微系统,2008,27(7)：96-98.
[1]丁克坚,檀根甲,胡官保,李高峰.水稻主要病害诊断、预测、防治专家系统的研究[J].安徽农业大学学报,1998,25(2)：133-137.
[2]范艳峰,甄彤.谷物害虫检测与分类识别技术的研究及应用[J].计算机工程,2005,31(12)：187-189,213.
[3]刘金桥,吴金强.机器视觉系统发展及其应用[J].机械工程与自动化,2010,(1)：215-216.
[4]何立民.单片机应用系统设计[M].北京：北京航空航天大学出版社,1996.
[5]张友德,赵志英,涂时亮.单片微型机原理、应用与实验[M].上海：复旦大学出版社,1999.
[6]周明安,朱光忠,宋晓华,肖俊建.步进电机驱动技术发展及现状[J].机电工程技术,2005,34(2)：16-17.
[7]陈兴文,刘燕.基于单片机的步进电动机细分驱动器设计[J].电机与控制应用,2009,36(7)：30-33.
[8]Bailey S Y. Servomotor and Stepper: Key Elements of Control Design[J]. Control Engineering,2003,(6):36-50.
[9]郑阿奇,丁有和Visual C++教程[M].北京：清华大学出版社,2005.
[10]李朝青.PC机与单片机串行通信技术[M].北京：北京航空航天大学出版社,2000.
[1]边肇棋,张学工.模式识别[M].北京：清华大学出版社,2007.
[2]罗希平,田捷,诸葛婴,王靖,戴汝为.图像分割方法综述[J].模式识别与人工智能,1999,12(3)：300-312.
[3]陈武凡.小波分析及其在图像处理中的应用[M].北京：科学出版社,2002.
[4]Pal N R, Pal S K.A review on image segmentation techniques[J]. Pattern Recognition,1993, 26(9):1277-1294.
[5]林开颜,吴军辉,徐立鸿.彩色图像分割方法综述[J].中国图像图形学报,2005,10(1)：1-10.
[6]陈冬岚,刘京南,余玲玲.几种图像分割阈值选取方法的比较与研究[J].机械制造与自动化,2003,(1)：77-80.
[7]乐宋进,武和雷,胡泳芬.图像分割方法的研究现状与展望[J].南昌水专学报,2004,23(2)：15-21.
[8]杨晖,曲秀杰.图像分割方法综述[J].电脑开发与应用,2005,18(3)：21-23.
[9]Hance G A, Umbaugh S E, Moss R H, et al. Unsupervised color image segmentation with application to skin tumor borders[J]. IEEE Engineering in Medicine and Biology,1996, 15(1):104-111.
[10]Ohta Y, Kanade T, Sakai T. Color information for region segmentation[J]. Computer Graphics and Image Processing,1980,13(3):222-241.
[11]Gonzalez R C, Woods R E数字图像处理[M].北京：电子工业出版社,2003.
[12]王玲,王萍,陈兵林,刘善军,姬长英.基于颜色阈值的田间籽棉图像分割技术[J].作物学报,2010,36(3)：502-507.
[13]Ahmad I S, Reid J F. Evaluation of color representations for maize image[J]. Agricultural Engineerng Research,1996,63:185-196.
[14]贾永红.数字图像处理[M].武汉：武汉大学出版社,2003.
[15]陈杨,陈荣娟,郭颖辉Matlab6.X图形编程与图像处理[M].西安：西安电子科技大学出版社,2002.
[16]Lin Zhenxian, Song Guoxiang, Xue Wen. Comparisom and Improvement of Several Methods on Wavelet Image Denoising[J]. Journal of Xidian University,2004,31(4):626-629.
[17]张建伟.基于计算机视觉技术的微小昆虫自动计数研究[D].中国农业大学,2003.
[i8]况菲,王耀南,余洪山,万琴.一种基于学习向量量化神经网络的图像分割方法[J].计算机工程与应用,2005,(14)：34-36.
[19]Huang C L. Parallel image segmentation using modified Hopfield mldel[J]. Pattern Recognition Letters,1993,13(5):345-353.
[20]杭后俊.基于扫描线算法的多边形区域填充图案[J].计算机时代,2009,(3)：22-23,26.
[21]Pfitzmann B. Trials of Traced Traitor[C]. Springer LNCS 1174,1996,49-63.
[22]Han J W, Kamber M. Data Mining: Concepts and Techniques[M]. Morgan Kaufmann Publishers, Inc,2001.
[23]姚敏,郁晓红,易文晟,江志伟.数字图像处理[M].北京：机械工业出版社,2006.
[24]徐贵力,毛罕平.利用傅里叶变换提取图像纹理特征新方法[J].光电工程,2004,33(11)：55-58.
[25]朱小燕,王松.傅里叶变换在粘连文字图像切分中的应用[J].计算机学报,1999,22(12)：1246-1252.
[26]王金满,曲艳杰,李坚.傅里叶变换图像方法在材解剖特征研究上的应用[J].四川农业大学学报,1998,16(1)：177-181.
[27]周云龙,范振儒,苏耀雷.基于图像傅里叶变换纹理特征和概率神经网络的气固化床流型识别[J].化工自动化及仪表,2009,36(2)：38-42.
[28]多化琼,王喜明,范俊雄.利用傅立叶变换研究铁杉木材管胞横截面尺寸[J].北京林业大学学报,2009,31(5)：108-111.
[29]Zhou F F, Shi J Q. Texture feature based on local fourier transform[C]. IEEE International Conference on ImageProcessing,2001,17(2):610-613.
[30]Castalman K R. Digital Image Processing[M]. Pretice hall,1998.
[31]Li Wen-xin, David Zhang, XU Zhuo-qun. Recongnition Based on Fourier Transform [J]. Journall of Software,2002,13(5):879-886.
[32]Tsai Du-Ming, Huang Tse-Yun. Automated sureface inspection for statistical textures[J]. Image and Vision Computing,2003,21(4):307-323.
[33]Yoko M, Yoji I, Minoru F. Transerse shape analysis of xylem ground tissues by Fourier transform image analysis I:Trial for statistical expression of cell arrangements with fluctuation[J]. Journal of Wood Science,2005,51(3):201-208.
[34]Yoko M, Minoru F. Transverse shape analysis of xylem ground tissues by Fourier transform image analysis Ⅱ:Cell wall direction and reconstruction of cell shapes[J]. Journal of Wood Science,2005,51(3):209-217.
[35]Yoko M, Minoru F. Transverse shape analysis of xylem ground tissues by The Fourier transform image analysis Ⅲ:Shape reconstruction of earlywood tracheids in 22 species and some parameters for normalizing cell shapes[J].Journal of the Japan Wood Research Society,2005,51 (4):218-226.
[36]盛骤,谢式千,潘承毅.概率论与数理统计(第三版)[M].北京：高等教育出版社,2005：270-282.
[1]Vapnik V N. The Nature of Statistical Learning Theory[M]. New York:Springer-Verlag, 1995.
[2]Sklansky J, Wassel G N. Pattern Classifiers and Trainable Machines[M]. New York: Spring-Verlag,1982.
[3]Muller K R, Ratsch G, Ratsch G. An Introduction to Kernel Based Learning Algorithms[J]. IEEE Transactions on Neural Networks,2001,12 (2):181-201.
[4]Burges C J. A Tutorial on Support Vector Machines for Pattern Recognition[J]. Knowledge Discovery and Data Mining,1998,2(2):121-167.
[5]Scholkopf B, Burges C. Input Space Versus Feature Space in Kernel Based Methods[J]. IEEE Transactions on Neural Networks,1999,10(5):1000-1017.
[6]Vapnik V N, Lemer A. Patern Recognition Using Generalized Portrait Method[J]. Automation and Remote Control,1963,24:79-92.
[7]Vapnik V N, Chervoknenkis A Y. The Necessary and Sufficient Conditions for consistency in the Empirical Risk Minimization Method[J]. Pattern Recognition and Image Analysis, 1991,1(3):283-305.
[8]Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[J]. IEEE Transactions on Neural Networks,1999,10(5):1055-1064.
[9]Cristianini N, Shawa-Taylor J. An Introduction of Support Vector Machines and Other Kernel-based Learning Methods[M]. Cambridge University Press,2000.
[10]邵惠鹤.支持向量机理论及其应用[J].自动化博览,2003,(1)：94-99.
[11]Rowley H A, Baluja S, Kaasade T. Neural Network Based Face Detection[C]. IEEE Trans. Pattern Anal.1998:23-38.
[12]许建华,张学工,李衍达.支持向量机的新发展[J].控制与决策,2004,19(5)：81-84.
[13]邓乃扬,田英杰.支持向量机—理论、算法与拓展[M].北京：科学出版社,2009.
[14]Chapelle O. Choosing kernel parameters for support vector machines[J]. Machine Learning, 2002,46(1):131-159.
[15]Boser B, Guyon, Vapnik V N. a training algorithm for optimal margin classifiers[C]. Fifth Annual Workshop on Computational Learning Theory, Pittsburgh ACM,1992:144-152.
[16]付麦霞,廉飞宇,张元.基于视频和SVM的储粮害虫检测与识别[J].计算机与数字工程,2008,36(11)：111-115.
[17]Hsu C W, Lin C J.A comparison of methods for multi-class support vector machines[J]. IEEE Transactions on Neural Networks,2002,13(2):415-425.
[18]Weston J, Watkins C. Multi-class support vector machines[J]. Technical Report,1998, CSD-TR-98-04:1-9.
[19]Huang W, Robert M. Face detection and precise eyes location[C]. in Proc.15th Int. Conf. Pattern Recognition, Barcelona, Spain, Sep.3-7,2000, vol.4, pp.722-727.
[20]Hunke M, Waibel A. Face locating and tracking for human computer interaction[C]. in 28th Asilomar Conference on Signals, Systems and Computers, Monterey, CA,1994.
[21]Jing Z, Mariani R. Glasses detection and extraction by deformable contour[J]. in Proceedings of the 15th International Conference on Pattern Recognition[J],2000, Vol. Ⅱp. 4B.
[22]Kim H C, Pang S N, He H M, et al. Constructing support vector machine ensemble[J] Pattern Recognition,2003,36(12):2757-2767.
[23]张铃,张钹.支持向量机理论与基于规划的神经网络学习算法[J].计算机学报,2001,24(2)：113-118.
[24]Dietterich T G, Bakiri G. Solving multi-class learning problems via error-correcting output codes[J]. Journal of Artificial Intelligence Research,1995,2:263-286.
[25]Crammer K, Singer Y. On the learnability and design of output codes for multiclass problems[J]. Computational Learning Theory,2000:35-46.
[26]任东.基于支持向量机的植物病害识别研究[D].长春：吉林大学,2007.
[27]徐海样.基于支持向量机方法的图像分割与目标分类[D].武汉：华中科技大学,2005.
[28]Hsu w H, Lin C J. A comparison of methods for multi-class support vector machines[J]. IEEE Transactions on Neural networks,2002,13(2):415-425.
[29]Muller K R, Mika S, Ratsch G, Tsuda K, Scholkopf B. An introduction to kernel-based learning algorithm[J]. IEEE Transactions on Neural Networks,2001,12(2):181-201.
[30]Cortes C, Vapnik V. Support-vector network[J]. Machine Learning,1995,20:273-297.
[31]吴涛.核函数的性质、方法及其在障碍检测中的应用[D].长沙：国防科学技术大学,2003.
[32]Cortes C, Vapnik V. Support vector networks [J]. Machine Learning,1995,20:273-297.
[33]Genton M G. Classes of kernels for machine learning:a statistics perspective [J]. Journal of Machine Learning Research,2001,2:299-312.
[34]江龙建.基于计算机视觉和神经网络的牛肉大理石花纹自动分级技术的研究[D].南京.南京农业大学,2003.
[35]李盼池,许少华.支持向量在模式识别中的核函数特性分析[J].计算机工程与设计,2005,26(2)：302-304.
[36]Burges C J C. A tutorial on support vector machines for pattern recognition [J]. Data Mining and Knowledge Discovery,1998,2(2):1-47.
[37]Chin-Chung Chang, Chin-Jen Lin. LIBSVM:a Library for Support Vector Machines.2010, 3.
[38]Vladimir C, Yunqian M. Practical Selection of SVM Parameters and Noise Estimation for SVM Regression[J]. Neural Networks,2004,17(1):113-126.
[39]闫国华,朱永生.支持向量机回归的参数选择方法[J].计算机工程,2009,35(13)：218-220.
[40]林升梁,刘志.基于RBF核函数的支持向量机参数选择[J].浙江工业大学学报,2007,35(2)：163-167.