Kernel Principal Component Analysis for the Construction of the Extended Morphological Profile

Kernel Principal Component Analysis (KPCA) is investigated for feature extraction from hyperspectral remotesensing data. Features extracted using KPCA are used to construct the Extended Morphological Profile (EMP). Classification results, in terms of accuracy, are improved in comparison to original approach which used conventional principal component analysis for constructing the EMP. Experimental results presented in this paper confirm the usefulness of the KPCA for the analysis of hyperspectral data. The overall classification accuracy increases from 79% to 96% with the proposed approach.

• Type: Journal
• Year: 2009
• Where: IGARSS
• Authors: Mathieu Fauvel, Jocelyn Chanussot, Jon Atli Benediktsson
• Keywords: Hyperspectral Remotesensing Data, IGARSS 2009, Kernel Principal Component Analysis, Principal Component Analysis, Remote Sensing