一种基于人工免疫网络的遥感图像分类算法  

An Algorithm for Remote Sensing Image Classification Based on Artificial Immune Network

作　　者：许仕珍[1] 吴云东[1] 

机构地区：[1]解放军信息工程大学测绘学院,河南郑州450052

出　　处：《海洋测绘》2008年第4期34-36,共3页Hydrographic Surveying and Charting

摘　　要：提出了一种基于人工免疫网络的遥感图像分类算法。该算法通过借鉴生物免疫网络的分类和泛化能力,训练出能反映训练数据分布特性的网络细胞,然后使用这些网络细胞进行分类。实验结果表明,基于人工免疫网络的遥感图像分类算法具有较好的分类性能,其分类总精度、kappa系数均优于一些传统分类算法。A novel supervised classification algorithm artificial immune network is proposed. The algorithm is able for remote sensing image classification based on to gain network cells representing training data by taking classification and generation capability of immune system as inspiration. Then the algorithm uses these network cells as a criterion for classification. It is demonstrated that the algorithm proposed in this paper is superior to the two traditional algorithms, and its overall accuracy and Kappa coefficient are higher than those algorithms＇.

关 键 词：人工免疫系统 人工免疫网络 监督分类 遥感图像分类 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]