Robust two-dimensional principal component analysis via alternating optimization

To extract two-dimensional principal components from image samples while being insensitive to outliers, we propose a robust model for two-dimensional principal component analysis (robust 2D-PCA) by regularizing sparse penalty term. Moveover, we develop a novel iterative algorithm for robust 2D-PCA via alternating optimization, learning the projection matrices by bi-directional decomposition. To further speed up the iteration, we develop an alternating greedy approach, minimizing over the low-dimensional feature matrix and the sparse error matrix. Experimental results on dynamic background subtraction are evaluated to show the effectiveness of the proposed model, compared with conventional 2D-PCA and robust PCA algorithms.