Face Recognition Using 2D DCT with PCA
Jianke Zhu, Mang I Vai, Peng Un Mak · 2003
This paper introduces a more efficient way to implement eigenfaces (PCA) which has now become a de facto and a common performance benchmark in face recognition. The method of combining 2D DCT with PCA decreases the dimensionality of eigenvectors, and increases the perormance at the same time. Without any preprocessing step, the best recognition rate of our approach is 84.%, and outperforms the conventional eigenfaces method.