基于Subspace集成学习的稻田杂草识别研究  

Weeds Recognition in Paddy Fields Based on Subspace Ensemble Learning

作　　者：邓向武 梁松 许伊杰 龚坤松 DENG Xiangwu;LIANG Song;XU Yijie;GONG Kunsong(College of Electronic Information Engineering, Guangdong University of Petrochemical Technology, Maoming 525000, China)

机构地区：[1]广东石油化工学院电子信息工程学院,广东茂名525000

出　　处：《广东石油化工学院学报》2021年第4期40-44,共5页Journal of Guangdong University of Petrochemical Technology

基　　金：广东石油化工学院人才引进及博士启动项目(2019rc044);广东石油化工学院大学生创新创业培育计划项目(733766)。

摘　　要：针对稻田苗期杂草识别中单一分类方法存在的不足,提出了一种基于Subspace集成学习的稻田杂草识别方法。先提取杂草图像的颜色、纹理、形状特征作为稻田杂草的识别特征,再通过多个基分类器集合训练得到Subspace集成学习模型。结果表明,当基学习器个数为32和子空间维度为91时,Subspace集成学习模型的准确率达到91.41%,且基于Subspace集成学习算法的识别精度高于SVM和BP神经网络,解决了针对稻田杂草特征单一分类器识别率不高的问题。To compensate for the lack of traditional single classifier,a new approach of weeds recognition in paddy fields based on subspace ensemble learning is proposed.The color,texture and morphologic features of weed are extracted.The number of classification and subspace in Subspace Ensemble Learning are obtained through experiments,which are 32 and 91.The results indicate that accuracy of Subspace Ensemble Learning is higher than SVM and BP,which solves the problems of low identification rate with single classifier.

关 键 词：杂草识别 集成学习 子空间 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]