摘要
应用计算机图像处理技术和支持向量机分类方法研究了玉米叶部病害的识别,以提高识别的准确性和效率。对采集到的玉米病害彩色图像采用矢量中值滤波法去除噪声,然后提取基于色度的玉米病害图像的彩色纹理特征,并用支持向量机的模式识别方法来识别玉米病害。实验结果表明:该模型对3种玉米病害的平均正确识别率为87．5％,即使在分类样本较少时,也具有良好的分类能力和泛化能力,适合于玉米病害的分类。
A new method of recognizing maize leaf disease by using computer image processing and Support Vector Machine (SVM) was studied to improve recognition accuracy and efficiency. At first, vector median filter was applied to remove noise of the color images of maize leaf disease, and texture features of Chromaticity Moments of image of maize disease were extracted. Classification method of SVM for recognition of maize disease was discussed. Experimentation results prove that the average accuracy of three maize disease recognized by SVM model was 87.5%, which is fit for classification of maize disease with excellent classification and generalization ability even in solving learning problem with small training set of sample.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2006年第z3期2123-2124,共2页
Chinese Journal of Scientific Instrument
基金
辽宁省自然科学基金(20052125)
辽宁省教育厅攻关计划(2005367)资助项目
关键词
玉米病害
图像处理
支持向量机
maize disease image processing support vector machine
