Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-2/W3, 31-34, 2014
https://doi.org/10.5194/isprsarchives-XL-2-W3-31-2014
© Author(s) 2014. This work is distributed under
the Creative Commons Attribution 3.0 License.
 
21 Oct 2014
DIMENSIONALITY REDUCTION OF HYPERSPECTRAL IMAGES BY COMBINATION OF NON-PARAMETRIC WEIGHTED FEATURE EXTRACTION (NWFE) AND MODIFIED NEIGHBORHOOD PRESERVING EMBEDDING (NPE)
T. Alipour Fard and H. Arefi Dept. of Geomatics and Surveying Eng., University of Tehran, Tehran, Iran
Keywords: Hyperspectral Imagery, Feature Extraction, LDA, NPE, Classification Abstract. This paper combine two conventional feature extraction methods (NWFE&NPE) in a novel framework and present a new semi-supervised feature extraction method called Adjusted Semi supervised Discriminant Analysis (ASEDA). The advantage of this method is dominating the Hughes phenomena, automatic selection of unlabelled pixels, extraction of more than L-1(L: number of classes) features and avoidance of singularity or near singularity of within-class scatter matrix. Experimental results on well-known hyperspectral dataset demonstrate that compared to conventional extraction algorithms the overall accuracy of the classification increased.
Conference paper (PDF, 1685 KB)


Citation: Alipour Fard, T. and Arefi, H.: DIMENSIONALITY REDUCTION OF HYPERSPECTRAL IMAGES BY COMBINATION OF NON-PARAMETRIC WEIGHTED FEATURE EXTRACTION (NWFE) AND MODIFIED NEIGHBORHOOD PRESERVING EMBEDDING (NPE), Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XL-2/W3, 31-34, https://doi.org/10.5194/isprsarchives-XL-2-W3-31-2014, 2014.

BibTeX EndNote Reference Manager XML