Table 10 Comparison of proposed system with traditional deep learning model in facial biometric Authentication.
From: Secure facial biometric authentication in smart cities using multimodal methodology
References | Algorithm used | Dataset | Accuracy |
|---|---|---|---|
Crihan et al.2 | Brakerski–Gentry–Vaikuntanathan algorithm | Face BGV | 96.80% |
Boddeti3 | Hormonic Algorithm | LFW | 96.74% |
Yang et al.4 | Random projection-based transformation | Dataset CD_one | 90.0% |
Yang et al.5 | CKKS algorithm | FaceNet | 96.71% |
Jaswal et al.6 | Backtracking search algorithm | Face dataset | 96.0% |
Win et al.7 | Linear Regression | Facial Expression | 97% |
Jindal et al.8 | Dimensional feature vector | LFW | 96.10% |
Sardar et al.9 | Cancelable feature vector | CASIA-FACE-v5 | 86.27% |
Gavisiddappa et al.10 | Support Vector Machine | CASIA | 97% |
Malarvizhi et al.11 | Adaptive Fuzzy Genetic Algorithm | Author Dataset | 96% |
Vidya et al.15 | Entropy Based Local Binary Pattern | CASIA | 91.17% |
Jagadiswary et al.16 | Fused Multimodal systems | Public database | 96.0% |
Proposed | CNN + ResNet-50 ElGamal encryption | CelebA | 97.1% |
