基于特征优化和LSSVM的棉田杂草识别-农业机械学报.PDF

20 10 年 11月 农 业 机 械 学 报 第41卷 第 11期 DOI:10.3969/ j.issn.1000鄄1298.2010.11.033 基于特征优化和LS SVM 的棉田杂草识别* 1,2 1 1 1 李先锋 摇 朱伟兴摇 纪摇 滨摇 刘摇 波 (1.江苏大学电气信息工程学院,镇江212013;2.盐城工学院信息工程学院,盐城224051) 摇 摇 揖摘要铱摇 为了提高杂草识别的精度和效率,提出了一种基于特征优化和最小二乘支持向量机(LS SVM)技术 的棉田杂草识别方法。 在对原始图像灰度化、滤波去噪和阈值分割等处理的基础上,提取植物叶片的6个几何特 征和7个Hu不变矩,用粒子群优化(PSO)算法对形状特征进行优化选择,缩减LS SVM训练样本数据,然后用训 练好的分类器进行杂草识别。 实验结果表明,该方法在有效缩减形状特征的同时,能够保持高于原始特征集的识 别率,平均正确识别率达到95郾8%。 关键词:棉花摇 杂草识别摇 特征选择摇 粒子群优化算法摇 最小二乘支持向量机 中图分类号:TP391郾41 文献标识码:A 文章编号:1000鄄1298(2010)11鄄0168鄄05 Weed Identification Based on Features Optimization and LS SVM in the Cotton Field 1,2 1 1 1 Li Xianfeng 摇 Zhu Weixing 摇 Ji Bin 摇 Liu Bo (1.School of Electronic Information Engineering,Jiangsu University,Zhenjiang 212013,China 2.School of Information Engineering,Yancheng Institute of Technology,Yancheng 224051,China) Abstract In order to improve the accuracy and efficiency of weed identification,a method for cotton鄄weed recognition was proposed by using the combination technique of features optimization and least squares support vector machine (LS SVM). After a series of image processing such as graying,filtering and threshold segmenting,six geometric shape features and seven Hu moment invariants were extracted from the single plant leaf. Then,using particle swarm optimization (PSO) algorithm,the extracted features were optimized in order to reduce the size of the training data sets. Finally,the weed was identified by using the trained classifier. The experimental r