An Adaptive Band Selection Algorithm for Dimension Reduction of Hyperspectral Images

摘要：

An adaptive band selection algorithm for dimension reduction of hyperspectral images is proposed. Considering the spatial correlation and spectral correlation, a selection rule, referring to spectral information and its correlation, is constructed for band selection. To test the efficiency of this algorithm, K-means algorithm for unsupervised classification was applied on images generated from the algorithm. The results showed that the proposed algorithm reduced the computation amount and improved the classification accuracy.

关键词： Hyperspetral Image Remote Sensing Adaptive Band Selection Dimension Reduction K-means

作者: Li Xijun Liu Jun

作者单位: School of Remote Sensing and Information Engineering, Wuhan University Wuhan 430079,China Computer C Information Dept, the General Air Force Hospital Beijing 100142, China

会议类型: 国际会议

会议名称: 2009图像分析与信号处理国际会议(2009 International Conference on Image Analysis and Signal Processing)

会议地点: 浙江台州

会议语种:英文

页码: 114-118

在线出版日期: 2009-04-11（万方平台首次上网日期，不代表论文的发表时间）