Regularized Difference Criterion for Computing Discriminants for Dimensionality Reduction
Document Type
Article
Publication Date
10-1-2017
Abstract
Hyperspectral data classification has shown potential in many applications. However, a large number of spectral bands cause overfitting. Methods for reducing spectral bands, e.g., linear discriminant analysis, require matrix inversion. We propose a semidefinite programming for linear discriminants regularized difference (SLRD) criterion approach that does not require matrix inversion. The paper establishes a classification error bound and provides experimental results with ten methods over six hyperspectral datasets demonstrating the efficacy of the proposed SLRD technique.
DOI
10.1109/TAES.2017.2696236
Montclair State University Digital Commons Citation
Aved, Alex J.; Blasch, Erik P.; and Peng, Jing, "Regularized Difference Criterion for Computing Discriminants for Dimensionality Reduction" (2017). Department of Computer Science Faculty Scholarship and Creative Works. 512.
https://digitalcommons.montclair.edu/compusci-facpubs/512