A multi-spectral palmprint fuzzy commitment based on deep hashing code with discriminative bit selection

Original Source Here


Direct usage of original biometric features/templates definitely leads to serious privacy leakage. In biometric cryptosystems, a biometric key is generated and then strictly protected with a one-way function. However, it is highly difficult to balance the template size and accuracy. Palmprint has many remarkable strengths, so it is considered as a promising biometric modality. In our previous work, deep hashing network (DHN) was leveraged to extract discriminative deep hashing code (DHC) of palmprint. In this paper, a palmprint fuzzy commitment (FC) is proposed based on DHC. A palmprint FC is proposed based on DHC. The DHC has high accuracy, small size, strong robustness, and is free from shift-matching for dislocation problems, so the proposed palmprint FC can satisfactorily balance the accuracy, storage cost and computational complexity. In addition, the DHCs of multi-spectral palmprints are concatenated and the bits are selected according to discrimination power analysis, so the accuracy is further improved. The sufficient experimental results show that, when B, N and R spectrums are fused and only 292 bits are selected, EER can be 0.0001%.


Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot

%d bloggers like this: