An efficient post-processing approach for dimensionality reduction methods for face recognition

In this paper we propose a new post-processing approach for dimensionality reduction methods based on multidimensional ensemble empirical mode decomposition (MEEMD). In the proposed method, the features are decomposed into different components and then we maximize the dependency and the dispersion between classes thanks to Gaussian filter and Butterworth filter. The performance of the proposed algorithm is demonstrated in experiments by several dimensionality reduction techniques on two public databases.