Tiny Transformers: Multimodal Digital Biometric Authentication model using Tiny Enhanced Dual Transformers with quality gated fusion network

Biometric authentication continues to be challenged by inconsistencies arising from modality-specific noise, low-quality input samples, and overfitting when trained on small-scale datasets. Most existing models rely on shallow fusion strategies or task-specific architectures that fail to generalize across domains, especially when modalities like iris and fingerprint differ in spatial structure and acquisition quality. To address these limitations, we propose a robust deep earning based multimodal authentication pipeline framework that uses both iris and finger print modalities for personal digital authentication. Our architecture integrates Tiny Vision Transformer backbones (ViT and Swin) with learned quality gated fusion technique and angular margin based metric learning employs ArcFace loss. This system employs comprehensive preprocessing pipeline for iris and fingerprint. For iris, we use Hough transform and contrast limited adaptive histogram equalization (CLAHE) based contrast enhancement. For fingerprint, Gabor filter is used with morphological thinning process. To handle the low quality images, laplacian sharpness metrics used which are computed and incorporated into gating network. This adaptively weights modality contribution during the feature fusion process. Two layer Multi Layer perceptron (MLP) output weights are normalized with softmax and score fusion is done. This novel tiny Vision Transformer (ViT) and swin transformer models are evaluated using the cosine annealing scheduler with leave one subject out (LOSO) cross validation. Our final gated fusion with ArcFace demonstrated with strong performance which achieves generalization, with ≈95% genuine acceptance rate at 1% false acceptance rate, AUC of ≈0.99 and ≈5% equal error rate (EER). This study demonstrates that adapting transformer-based backbones, using margin-based metric losses, and incorporating quality-gated fusion can yield interpretable and high-performing authentication systems, even under limited data scenarios.