计算机应用研究2012，Vol.29Issue(7)：2790-2792,2795,4.DOI:10.3969/j.issn.1001-3695.2012.07.107
改进的波段选择混合核函数遥感图像分类算法
Algorithm of remote sensing image classification improved by bands selection and hybrid kernel functions
摘要
Abstract
As the multi-band of remote sensing image is not easy to imaging, ila redundancy image information is not suitable for image classification, what's more, ihe traditional LMBP algorithm has. large iteration number and classification imprecise problems. This paper improved the formula of the OIF index number and separability distance, separated to chose the best band combination, and then used the LMBP algorithm refinement of hybrid kernel function to classify. The simulation results show that the improved method can analyze information of the bands more comprehensive and objective, comparing with the traditional algorithm,the network training iterations are significantly reduced,the classification accuracy and Kappa coefficient can be increased by 5% and 6. 625% , the classification of remote sensing image more effectively.关键词
指数/可分性距离/波段选择/混合核函数/LMBP算法/遥感图像分类Key words
index number/ separability distance/ bands selection/ hybrid kernel function/ LMBP algorithm/ remote sen-sing image classification分类
信息技术与安全科学引用本文复制引用
徐倩,何建农..改进的波段选择混合核函数遥感图像分类算法[J].计算机应用研究,2012,29(7):2790-2792,2795,4.基金项目
国家自然科学基金资助项目(50877010) （50877010）
