On the effect of synthetic morphological feature vectors on hyperspectral image classification performance (Yapay biçimbilimsel özniteliklerin hiperspektral görüntü sınıflandırma başarımının üzerindeki etkisi)

Davari, Amir Abbas and Aptoula, Erhan and Yanıkoğlu, Berrin (2015) On the effect of synthetic morphological feature vectors on hyperspectral image classification performance (Yapay biçimbilimsel özniteliklerin hiperspektral görüntü sınıflandırma başarımının üzerindeki etkisi). In: 23th Signal Processing and Communications Applications Conference (SIU 2015), Malatya, Turkey

[thumbnail of SIU_2015_amir.pdf] PDF
SIU_2015_amir.pdf

Download (367kB)

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.
Item Type: Papers in Conference Proceedings
Divisions: Faculty of Engineering and Natural Sciences > Academic programs > Computer Science & Eng.
Faculty of Engineering and Natural Sciences
Depositing User: Berrin Yanıkoğlu
Date Deposited: 08 Dec 2015 16:16
Last Modified: 26 Apr 2022 09:19
URI: https://research.sabanciuniv.edu/id/eprint/27616

Actions (login required)

View Item
View Item