Abstract:
Most existing cancelable biometric frameworks are based on one-dimensional (ID) vectors rather than two-dimensional (2D) images or feature matrices. 2D cancelable biometr...Show MoreMetadata
Abstract:
Most existing cancelable biometric frameworks are based on one-dimensional (ID) vectors rather than two-dimensional (2D) images or feature matrices. 2D cancelable biometrics, generated directly from images of feature matrices, were proposed based on two-directional two-dimensional fusion sparse random projection ((2D)2FSRP) and two-directional two-dimensional plus sparse random projection ((2D)2PSRP), so the storage and computational costs are both reduced. (2D)2FSRP methods play complementary advantages of 2D sparse random projection (2DSRP) and two-dimensional principal component analysis (2DPCA) or two-dimensional linear discriminant analysis (2DLDA), but they do not have ideal performance when all users have different tokens, so (2D)2PSRP methods were proposed to generate 2D cancelable face and palmprint. 2D cancelable face and palmprint schemes, which satisfactorily meet the requirements of cancelable biometrie, were determined by the experimental results and analysis.
Date of Conference: 15-17 July 2012
Date Added to IEEE Xplore: 06 September 2012
ISBN Information: