Robust 2DPCA with non-greedy ℓ₁-norm maximization for image analysis

2-D principal component analysis based on ℓ₁-norm (2DPCA-L1) is a recently developed approach for robust dimensionality reduction and feature extraction in image domain. Normally, a greedy strategy is applied due to the difficulty of directly solving the ℓ₁-norm maximization problem, which is, however, easy to get stuck in local solution. In this paper, we propose a robust 2DPCA with non-greedy ℓ₁-norm maximization in which all projection directions are optimized simultaneously. Experimental results on face and other datasets confirm the effectiveness of the proposed approach.