A Gabor-Block-Based Kernel Discriminative Common Vector Approach Using Cosine Kernels for Human Face Recognition

Table 6

Comparison of recognition accuracy of various methods with the proposed method.

Method	Highest recognition accuracy
GDA	78.04%
Elastic graph matching (EGM) [9]	80.00%
DCT-LDA	80.87%
GWT	81.1%
DCT-GDA	82.84%,
GWT-LDA	84.1%
DCT-KDCV	85.13%
Gabor fusion KDCV	91.22%
Proposed approach	94.25%