Abstract
2DRP (two-dimensional random projection) is two-dimensional extension of one-dimensional RP (random projection) to keep biometric images from being reshaped to vectors before RP for recognition. We propose a novel method called (2D)(RP)-R-2 (two-directional two-dimensional random projection) for feature extraction of biometrics. (2D)(RP)-R-2 directly projects the image matrix from high-dimensional space to low-dimensional space to extract optimal projective vectors at row-direction and column-direction. (2D)(RP)-R-2, similar to RP, can also avoid the problems of singularity, SSS (small sample size) and over-fitting; furthermore it has much less storage and computational cost than RP. Besides, the variations of (2D)(RP)-R-2 combined with 2DPCA and 2DLDA are developed. Experimental results and comparison discussion among (2D)(RP)-R-2 and its variations on face and palmprint databases confirm the performance and effectiveness of (2D)(RP)-R-2 and its variations.