|
|||||
|
|
| 基于SVM的温室黄瓜病害诊断研究 | |
| 引用本文： | 任东,于海业,乔晓军.基于SVM的温室黄瓜病害诊断研究[J].农机化研究,2007(3):25-27,31. |
| 作者姓名： | 任东 于海业 乔晓军 |
| 作者单位： | 1. 吉林大学,生物与农业工程学院,长春,130028;国家农业信息化工程技术研究中心,北京,100097 2. 吉林大学,生物与农业工程学院,长春,130028 3. 国家农业信息化工程技术研究中心,北京,100097 |
| 摘 要： | 针对温室黄瓜霜霉病、角斑病、白粉病这3种常见病害图像的特点,提出了将支持向量机方法应用于黄瓜这3种病害识别中.首先选择HIS颜色空间作为图像特征提取的空间,以避免光照强度对图像获取的影响,然后利用支持向量机分类方法进行病害的识别.实验分析表明,HIS颜色系统基本上消除了图像获取时,光照强度对图像的影响;支持向量机分类方法在病害分类时训练样本较少,具有良好的分类能力和泛化能力.不同分类核函数的比较结果是径向基核函数的SVM方法对黄瓜这3种病害的识别率达到了90%以上,最适于黄瓜3大病害的分类识别. |
| 关 键 词： | 计算机应用 纹理图像 理论研究 植物病害 支持向量机 径向基核函数 温室 黄瓜病害 诊断研究 Support Vector Machine Based Greenhouse Recognition Disease Cucumber 分类识别 识别率 分类方法 径向基核函数 比较结果 泛化能力 分类能力 训练样本 类时 颜色系统 分析表 |
| 文章编号： | 1003-188X（2007）03-0025-03 |
| 收稿时间： | 2006-09-06 |
| 修稿时间： | 2006-09-06 |
Research on Cucumber Disease Recognition in Greenhouse Based on Support Vector Machine |
|
| REN Dong,YU Hai-ye,QIAO Xiao-jun.Research on Cucumber Disease Recognition in Greenhouse Based on Support Vector Machine[J].Journal of Agricultural Mechanization Research,2007(3):25-27,31. | |
| Authors: | REN Dong YU Hai-ye QIAO Xiao-jun |
| Institution: | 1.Schools of Biological and Agricultural Engineering, Jilin University, Changchun 130028, China; 2. Environment Controlling Institute, National Engineering Research Centre for Information Technology in Agriculture, Beijing 100097, China |
| Abstract: | According to the features of cucumber three kinds of disease, recognition of disease using support vector machine (SVM) was introduced. At first, this extracts features of HIS color system for avoiding effect of illumination intensity. Then the paper put forward the classification method of SVM for recognition of Cucumber. Experimentation with cucumber disease was conducted and the results proved that HIS color system basically avoid effect of illumination intensity, and the SVM method has excellent classification and generalization ability in solving learning problem with small training set of sample, and is fit for classification of plant disease. The comparison of different kernel functions for SVM shows that RBF kernel function is most suitable for recognition of cucumber three kinds of primary diseases sort. |
| Keywords: | computer application cucumber diseases theoretical research support vector machine greenhouse RBF |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |