Title :
On the effect of synthetic morphological feature vectors on hyperspectral image classification performance
Author :
Davari, Amir Abbas ; Aptoula, Erchan ; Yanikoglu, Berrin
Author_Institution :
Dept. of Comput. Sci. & Eng., Sabanci Univ., Istanbul, Turkey
Abstract :
This paper studies the effect of synthetic feature vectors on the classification performance of hyperspectral remote sensing images. As feature vectors, it has been chosen to employ morphological attribute profiles, that have proven themselves in this field. At this early stage of our work, the relatively simple Bootstrapping algorithm has been used for synthetic feature vector generation. Based on experiments conducted on multiple hyperspectral datasets, it has been observed that synthetic feature vectors contribute considerably to classification performance in the case of limited training dataset sizes.
Keywords :
geophysical image processing; image classification; remote sensing; bootstrapping algorithm; hyperspectral image classification; hyperspectral remote sensing image; limited training dataset size; synthetic feature vector generation; synthetic morphological feature vector; Accuracy; Feature extraction; Hyperspectral imaging; Standards; Training; bootstrap; classification; extended morphological attribute profile; hyperspectral image; remote sensing; resampling;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2015 23th
Conference_Location :
Malatya
DOI :
10.1109/SIU.2015.7129909