Files
SSNSC
Folders and files
Name | Name | Last commit date | ||
---|---|---|---|---|
parent directory.. | ||||
# SSNSC-for-HSIC This demo implements the method proposed in the paper given below [1]; [1] Kemal Gürkan Toker & Seniha Esen Yuksel (2022) Spectral-spatial nearest subspace classifier for hyperspectral image classification, International Journal of Remote Sensing, 43:6, 2106-2133, DOI: 10.1080/01431161.2022.2055986 Spectral-Spatial Nearest Subspace Classifier (SSNSC) method is a kind of representation-based method. The SSNSC method is proposed, inspired by the geometric interpretation of the Nearest Subspace Classifier (NSC) method. NSC is a simple classifier that works on the assumption that samples from the same class approximately lie on the same subspace. Based on this assumption, the NSC method analyzes the closeness between the test sample and the space spanned by the within-class training samples. Then, the label of the test sample is assigned to the closest class. However, NSC only considers spectral information and neglects spatial information. In addition to the assumption in the NSC method, we add another assumption that spatially adjacent pixels quite likely belong to the same class. By combining these two assumptions, we conclude that spatially adjacent pixels must approximately lie on the same subspace as well. Based on these assumptions, we propose the spectral-spatial nearest subspace classification (SSNSC) approach as a generic classification framework that performs classification by analyzing the closeness between the subspace spanned by the samples used for spatial information and the subspace spanned by the within-class training samples. Canonical Correlation Analysis (CCA) is used to measure the closeness between these two subspaces.