Manifold Inspired Feature Extraction for Hyperspectral Image

摘要：

Feature extraction is an indispensable preprocessing step for the large data, high redundancy hyperspectral remote sensing image (HSI). In this paper, a manifold inspired method, e.g., Laplacian Eigenmap (LE) is introduced for hyperspectral image dimensional reduction. In order to overcome the shortcoming of conventional manifold learning which could not deal with large data, linearization procedure for LE is proposed based on multiple linear regression analysis. Experiment on hyperspectral dataset demonstrates that the proposed manifold inspired feature extraction (MIFE) could preserve the local geometry of the samples in the original feature space. The low dimensional feature image could achieve a better classification accuracy rate.

关键词： Hyperspectral Laplacian Eigenmap Feature extraction Classification

作者: Lei Huang Lefei Zhang Liping Zhang

作者单位: Hubei Ceomatics Information Center, Wuhan 430079 P.R. China State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan Uni Wuhan Regional Climate Center, Wuhan 430074, P.R.China

会议类型: 国际会议

会议名称: 2011 International Conference on Computer Science and Network Technology(2011计算机科学与网络技术国际会议 ICCSNT 2011)

会议地点: 哈尔滨

会议语种:英文

页码: 1955-1958

在线出版日期: 2011-12-24（万方平台首次上网日期，不代表论文的发表时间）