Most of the existing Block 2DPCA algorithms are based on Frobenius norm, which makes them sensitive to outliers. In this paper, we propose a new improved Block 2DPCA algorithm with L1-norm, which is robust to outliers. The experimental results of FERET face database indicated that the recognition performance of new algorithm is superior to Block 2DPCA, more robust than Block 2DPCA.
展开▼