基于机器学习的烟草蛙眼病赤星病识别

Recognition of Tobacco Frog Eye Alternaria Based on Machine Learning

文章以常见的烟草蛙眼病与赤星病为研究对象,利用图像处理方法分割出病斑,并提取了病斑的颜色、纹理和形态学特征,构建原始特征空间,利用模拟退火算法进行特征优化,选取最优特征组合。利用ABC-SVM技术进行两种病害的判别,识别率达到97%,有效判别出蛙眼病与赤星病,为指导采取合理的烟草病害防治措施提供科学依据。

China is the world’s largest tobacco producer and consumer.Tobacco is an important economic crop and economic sources for China.Tobacco often infected many diseases due to improper control during its growth,and it will make huge economic losses.The common tobacco frog eye disease and brown spot disease were studied In this paper.The image processing method were used to segment the lesions,and selected the color,texture and morphological features of the lesions to construct the original feature space,used the simulated annealing algorithm to optimize the features.The ABC-SVM technology were used to recognize two disease,and the recognition rate reached 97%.The two diseases of frog eye disease and brown spot disease were effectively identified,and provided a scientific basis for guiding reasonable tobacco disease prevention and control measures.