Feature Extraction Methods Directly Based on Image Matrix: 2DPCA, (2D) ZPCA, DiagPCA, and DiagPCA-I-2DPCA

During the feature extraction phase, multiple algorithms including PCA, 2DPCA, (2D) 2PCA, DiagPCA, and DiagPCA-F-2DPCA were investigated. Unlike vector-based PCA feature extraction, 2DPCA, (2D) ZPCA, DiagPCA, and DiagPCA-I-2DPCA operate directly on image matrices, resulting in significantly lower computational complexity and faster feature extraction speeds than traditional PCA methods. These matrix-based approaches utilize covariance matrices computed directly from 2D image arrays rather than requiring vectorization, making them particularly efficient for high-dimensional image data processing.