Modular 2DPCA is an extension of 2DPCA algorithm. The recognition performance of modular 2DPCA is more robust than that of 2DPCA.In this paper

the defects of modular 2DPCA about computing the total scatter matrix of training samples and selecting eigenvectors are analyzed. An improved modular 2DPCA algorithm is presented. Experiments show that the improved modular 2DPCA algorithm can select better eigenvectors and extract facial features more effectively.