El-Rahiem Basma Abd, Amin Mohamed, Sedik Ahmed, Samie Fathi E Abd El, Iliyasu Abdullah M
Mathematics and Computer Science Department, Faculty of Science, Menoufia University, Shebin El-Koom, Egypt.
Department of the Robotics and Intelligent Machines, Kafrelsheikh University, Kafrelsheikh, 33511 Egypt.
J Ambient Intell Humaniz Comput. 2022;13(4):2177-2189. doi: 10.1007/s12652-021-03513-1. Epub 2021 Nov 1.
Today, biometrics are the preferred technologies for person identification, authentication, and verification cutting across different applications and industries. Sadly, this ubiquity has invigorated criminal efforts aimed at violating the integrity of these modalities. Our study presents a multi-biometric cancellable scheme (MBCS) that exploits the proven utility of deep learning models to fuse multi-exposure fingerprint, finger vein, and iris biometrics by using an Inspection V3 pre-trained model to generate an aggregate tamper-proof cancellable template. To validate our MBCS, we employed an extensive evaluation including visual, quantitative, and qualitative assessments as well as complexity analysis where average outcomes of 99.158%, 24.523 dB, 0.079, 0.909, 59.582 and 23.627 were recorded for NPCR, PSNR, SSIM, UIQ, SD and UACI respectively. These quantitative outcomes indicate that the proposed scheme compares favourably against state-of-the-art methods reported in the literature. To further improve the utility of the proposed MBCS, we are exploring its refinement to facilitate generation of cancellable templates for real-time biometric applications in person authentication at airports, banks, etc.
如今，生物识别技术是跨不同应用和行业进行人员识别、认证和验证的首选技术。遗憾的是，这种普遍性激发了犯罪分子旨在破坏这些模式完整性的企图。我们的研究提出了一种多生物特征可取消方案（MBCS），该方案利用深度学习模型已被证明的效用，通过使用预训练的Inspection V3模型融合多曝光指纹、指静脉和虹膜生物特征，以生成聚合的防篡改可取消模板。为了验证我们的MBCS，我们进行了广泛的评估，包括视觉、定量和定性评估以及复杂性分析，其中NPCR、PSNR、SSIM、UIQ、SD和UACI的平均结果分别记录为99.158%、24.523 dB、0.079、0.909、59.582和23.627。这些定量结果表明，所提出的方案与文献中报道的最新方法相比具有优势。为了进一步提高所提出的MBCS的实用性，我们正在探索对其进行改进，以便为机场、银行等场所的人员认证中的实时生物识别应用生成可取消模板。
