The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-4/W18
https://doi.org/10.5194/isprs-archives-XLII-4-W18-315-2019
https://doi.org/10.5194/isprs-archives-XLII-4-W18-315-2019
18 Oct 2019
 | 18 Oct 2019

SPATIAL-SPECTRAL MORPHOLOGICAL FEATURE EXTRACTION FOR HYPERSPECTRAL IMAGES CLASSIFICATION

M. Dowlatshah, H. Ghassemian, and M. Imani

Keywords: Hyperspectral, Feature Extraction, Spatial Features, Spectral Features, Morphology Profiles

Abstract. Remote sensing image classification is a method for labeling pixels to show the Land cover types. The ambiguity in the classification process can be reduced if the spatial dependencies, which exist among the adjacent pixels, are intelligently incorporated into the feature extraction process. One of the methods for spatial feature extraction is applying morphological filters. The basic idea of the morphological filters is comparison of structures within the image with a reference form called structural element. Four types of important morphological filters are included (dilation, erosion, opening, and closing) in this work. Opening morphological filter is used to extract spatial features where this filter is implemented by applying two successive sequences dilation and erosion operators. This filter removes the light areas smaller than the structural element in binary images; and in the gray level images, the areas smaller than the structural element and brighter than the neighboring regions are removed. Differential morphology filters are other important morphological filters, which are also used in this work. In the proposed method, the principal component analysis is used to reduce the data dimensions and an SVM classifier is applied to classify the hyperspectral data. The proposed method provides better classification results than the conventional morphological profile about 2%-5% for the University of Pavia and Pavia Center datasets. The results represent the good performance of the proposed method by using a small number of training samples.