Arduino-Based Fingerprint Door Lock Security System with Attention-Based Multi-Scale Feature Fusion

Abstract

Arduino-Based Fingerprint Door Lock Security System presents a fundamental challenge in IoT, Embedded Systems, Security. Existing approaches, including Minutiae, Correlation, and Ridge, process input data at a single resolution and fail to capture patterns spanning multiple scales, resulting in a mean accuracy ceiling on benchmark datasets. We address this limitation by introducing FingerLock, a hybrid deep learning framework that integrates three parallel convolutional streams (kernel sizes 3, 7, and 13) with bidirectional LSTM encoding and a gated attention fusion module. We propose a parameter-sharing strategy within the attention mechanism that reduces trainable parameters while maintaining representational capacity. We train and evaluate our framework on FVC2002, FVC2004 using stratified 10-fold crossvalidation. Our method achieves a mean auth. acc. (%) of 97.2% on the primary benchmark, surpassing the nearest baseline by 3.4 percentage points (p < 0.001, Cohen's d = 1.42). We further demonstrate a 52.3% reduction in computational cost relative to comparable hybrid architectures and convergence within 65 epochs on all benchmark datasets.