水稻稻瘟病图像识别预处理方法研究  

Study on Image Pre-Processing for Rice Blast Disease Identification

作　　者：路阳[1] 邵庆[1] 张楠[1] 许善祥[1] 刘德福[1] 

机构地区：[1]黑龙江八一农垦大学信息技术学院,大庆163319

出　　处：《黑龙江八一农垦大学学报》2011年第4期64-67,共4页journal of heilongjiang bayi agricultural university

基　　金：大庆市科学技术计划项目2009

摘　　要：为了实现计算机对水稻稻瘟病病害的自动识别,研究了水稻稻瘟病病斑图像的预处理和形状特征提取方法。试验中利用灰度变换、直方图均衡化及中值滤波法有效去除了噪声和增强了图像,利用拉氏算子对病斑图像进行边缘检测,准确提取了病斑的形状特征,实现了稻瘟病图像目标分割。这些研究为进一步的特征参数提取及最终病害确定打下基础。In order to identify the rice blast disease by using computer,the extract method of image preprocessing and feature extraction for rice disease identification was studied.Gray-scale,histogram equalization and transformation and median filter methods were utilized to effectively eliminates noise and enhance the image.The disease spots were accurately extracted by using Laplace 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：图像预处理 水稻 稻瘟病 特征提取 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]