基于非负稀疏图的高光谱数据降维.pdfVIP

第35 卷第5 期 电 子 与 信 息 学 报 Vol.35No.5 2013 年5 月 Journal of Electronics Information Technology May 2013 基于非负稀疏图的高光谱数据降维 高 阳 王雪松* 程玉虎 (中国矿业大学信息与电气工程学院 徐州 221116) 摘 要：为减少因大量的光谱信息带来的计算复杂及数据冗余带来的高光谱数据分类性能降低，该文提出一种非负 稀疏图降维算法。首先，构建超完备块字典对高维高光谱数据进行非负稀疏表示。然后，根据块非负稀疏表示，分 别构建内部非负稀疏图和惩罚非负稀疏图，基于单调递减函数定义边的权重以体现样本间的相似程度。最后，通过 同时最大化异类和最小化同类非负稀疏重构样本间的距离，得到从高维到低维的最优映射关系，从而实现对高维高 光谱数据的降维。AVIRIS 92AV3C 高光谱数据上的实验结果表明，所提算法能以较少的训练样本获得较高的整体 分类精度和Kappa 系数。 关键词：高光谱；降维；非负稀疏图；整体分类精度；Kappa 系数 中图分类号：TP751.1 文献标识码： A 文章编号：1009-5896(2013)05-1177-08 DOI: 10.3724/SP.J.1146.2012.01082 Dimensionality Reduction of Hyperspectral Data Using Non-negative Sparsity Graph Gao Yang Wang Xue-song Cheng Yu-hu (School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou 221116, China) Abstract: In order to reduce the computation complexity resulted from large number of spectral information and to reduce the decline of classification performance resulted from data redundancy, a dimensionality reduction algorithm called non-negative sparse graph is proposed. At first, an over-complete block dictionary is constructed to realize the non-negative sparse representation of high-dimensional hyperspectral data. Then, according to the non-negative sparse representation, an inner non-negative sparsity graph and a penalty non-negative sparsity graph are built where the weights of edges are defined by a monotone decreasing function to embody the similarity degree of samples. At last, an optimal mapping from the high-dimensional space to a lo