Discriminant projection embedding for face and palmprint recognition

In this paper, we propose a new supervised linear dimensionality reduction method called discriminant projection embedding (DPE). DPE can preserve within-class neighboring geometry and extract between-class relevant structures for classification effectively. The proposed method is applied to face and palmprint recognition and is examined using the AR and FERET face databases and the PolyU palmprint database. Experimental results show that DPE consistently outperforms other up-to-date supervised linear dimensionality reduction methods when the training sample size per class is small. This demonstrates the effectiveness and robustness of DPE.