Investigation of feature dimension reduction based DCT/SVM for face recognition

We examine the problem of how to discriminate between objects of more than two classes using psilaminimum informationpsila. This paper presents an efficient face recognition system, based on discrete cosine transform (DCT) and support vector machines (SVM). The idea is to reduce dimensionality of face space. DCT is used to extract pertinent information which represent low frequency in each block. Then the extracted DCT coefficients are used as features for the classification process, which is performed using SVM. The proposed approach was thoroughly tested, using ORL face databases. The obtained results are very encouraging, outperforming traditional methods like PCA, LDA or DCT based MLP in recognition systems.