ABSTRACT
Hyperspectral imaging is increasingly important in academia and various professions, facing challenges like redundant features, inter-class correlations, and the curse of dimensionality. Principal Component Analysis and its variants, such as Sparse-PCA and Segmented-PCA, reduce the dimensionality of hyperspectral data but interpreting PCA results is complex. Our SPCA-mRMR technique integrates Sparse-PCA with a greedy feature selection method, mRMR. This, combined with a Dual Branch CNN model, improves hyperspectral image analysis, especially with noisy or limited data. Optimization reduces computational costs and enhances classification accuracy. Evaluations show our method’s efficiency, using fewer variables without compromising accuracy, crucial for advancing HSI applications.
Disclosure statement
No potential conflict of interest was reported by the author(s).