핵심 개념
A novel scheme for generating cancelable biometric templates using visual secret sharing and reverse Boolean XOR operation.
초록
The paper proposes three different methods (M1, M2, M3) for generating cancelable biometric templates using visual secret sharing.
M1 uses one original biometric image as the secret and n-1 randomly chosen gray images as cover images. M2 uses one original biometric image as the secret and n-1 randomly permuted versions of the original image as cover images. M3 uses both the secret image and the cover images as randomly permuted versions of the original biometric image.
The proposed methods involve the following steps:
- Generation of temporary shares by XORing the secret image with the cover images.
- Generation of noisy shares by XORing the temporary shares.
- Generation of the final secret shares by performing left bitwise reversal on the noisy shares.
The performance of the proposed methods is evaluated using various metrics like correlation coefficient, mean square error, mean absolute error, PSNR, SSIM, NPCR, and UACI. The results show that M3 generates the best quality cancelable templates, with the secret shares not revealing any information about the original biometric.
통계
The original biometric image has a dimension of 112x94 for the ORL face database and 320x240 for the IIT Delhi iris database.
인용구
"The major advantage of this technique over other two methods are (i) its Secret Shares do not reveal any partial and full information about the original Biometric image (ii) If anyhow an intruder accessed all Secret Shares, after applying reverse engineering process if Secret image S1 and n-1 Cover images are retrieved, which are again randomly permuted version of original Secret image (distorted). Hence it proofs the non-invertible property of Cancelable Biometric based application."