【摘要】 为提高遥感影像分类精度,采用基于混沌免疫算法(Chaos Immune Algorithm)的分类方法。利用混沌优化的遍历性,进行粗粒搜索,优化初始抗体群;通过选择算子、克隆算子、变异算子、抗体的循环补充等操作,得到全局最优的聚类中心,提高分类精度。实验表明该方法分类总精度、Kappa系数均优于传统分类方法。更多还原

【Abstract】 To improve the accuracy of remote sensing image classification,chaos immune glgorithm is proposed.The ergodic property of chaos phenomenon is used to optimize the initial antibody population,in order to accelerate the convergence of immune algorithm.Through the adjusted antibody affinity,selection operator is formed.By the selection operator,clone operator,mutation operator and recruited antibody,local optimums are avoid.It is demonstrated that chaos immune algorithm is superior to the two traditional algorithms,and its overall accuracy and Kappa coefficient reach 89.8% and 0.8725respectively.更多还原