水稻病害图像预处理及其特征提取方法研究  

Study on the Method of Image Pre-processing and Feature Extraction for Rice Diseases

作　　者：路阳[1] 关海鸥[1] 赵斌[1] 杨立[1] 

机构地区：[1]黑龙江八一农垦大学信息技术学院,黑龙江大庆163319

出　　处：《农机化研究》2011年第8期27-30,共4页Journal of Agricultural Mechanization Research

基　　金：黑龙江省教育厅科学技术研究项目(11551321);大庆市科学技术计划项目(2009)

摘　　要：采用计算机数字图像处理技术对水稻病害进行智能识别,并以叶鞘腐败病为例,研究了水稻病害智能识别图像预处理和特征提取的方法。试验中,利用灰度变换和中值滤波法有效去除了噪声,增强了图像;利用不同算子对病害进行边缘检测,准确地提取了病斑的几何特征,实现了病害图像目标分割。这一研究成果为特征参数的提取及最终病害确定打下基础。Using computer digital image processing technology,rice diseases were identified intelligently,and taking sheath rot disease of rice as an example,the method of imagepre-processing and feature extraction for rice disease identification was studied.Gray-scale transformation and median filter methods were utilized to effectively eliminates noise and enhance the image.Geometric features of the disease spots were accurately extracted by using different operators to detect the edge of disease,then,achieve disease object segmentation.These studies are useful for further feature extraction and lay the foundation for determining the final disease.

关 键 词：水稻病害 图像预处理 边缘检测 特征提取 目标分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] S126[自动化与计算机技术—计算机科学与技术]