Incremental approach to robust learning of eigenspaces

The standard PCA approach to visual learning of representations is intrinsically non-robust and usually performed in a batch mode, which is inadmissible in a real-world on-line scenario. In this paper we propose a novel method for robust and incremental learning of eigenspaces. The method sequentially updates the representation using the previously acquired knowledge for determining consistencies and discarding inconsistencies in the input images. We show the experimental results, which demonstrate the advantages and disadvantages of the proposed approach.