A method of aircraft image target recognition based on modified PCA features and SVM
A method of aircraft image target recognition based on modified PCA features and SVM
复制标题
DOI：
10.1109/icemi.2009.5274100
复制
发表时间：
2009-10
期刊：
影响因子：
--
通讯作者：
Donghe Wang;Xin He;Zhonghui Wei;Huilong Yu
中科院分区：
文献类型：
--
作者：
Donghe Wang;Xin He;Zhonghui Wei;Huilong Yu
自动目标识别（ATR）是图像应用中的一个重要课题.本文重点介绍了ATR系统中的两个关键子程序：模糊度约简和分类器。在对原始特征进行预处理后，利用Hebbian规则训练的自组织神经网络进行主成分特征提取。然后采用基于有向无环图支持向量机（DAGSVM）的分类器对两类以上的飞机目标进行识别。实验结果表明，该方法具有较好的子集特征和较高的识别率。
Automatic target recognition(ATR) is an important task in image application. This paper concentrates on two key subroutines of ATR system: Dimensionality reduction and Classifier. After pretreatment on original features a self-organizing neural network trained with the Hebbian rule is used to extract the principal component features. Then a classifier based on Directed Acyclic Graph Support Vector Machines(DAGSVM) is adopted to recognize more than two types of aircraft targets. The experiment results show the proposed method achieves better subset features and higher recognition rate.