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

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.