ForensicNet: A Deep Multimodal Biometric Framework for Identity Attribution in Digital Forensics Investigation

Abstract

Biometric identification is a vital feature in digital forensics, and unimodal systems of biometric identification, like face, voice, or fingerprint recognition, tend to experience poor performance under a contaminated situation or when complete. In this paper, a novel deep multimodal biometrics framework called ForensicNet is presented, which combines heterogeneous biometric modalities: face images, speech signals, and fingerprint patterns into a combined expression of robust forensic identity attribution. The architecture will be defined based on joint representation learning, deep fusion with an attention-based weighting layer, and an adaptive reliability module that recalibrates decisions when one or more biometric sources are partially unavailable. For evaluation, extensive experiments were performed on the three standard data sets: forensic face recognition, speaker verification, and fingerprint matching. The results suggest that ForensicNet achieves 19.3 percent higher identification accuracy than the unimodal baseline and conventional fusion baseline, a 22.7 percent lower equal error rate (EER), and 16.8 percent better robustness to missing modalities. Furthermore, ForensicNet can obtain these benefits while using 13.1 fewer computational overheads. Overall, the above results have proven ForensicNet to be a promising, scalable, reliable, and energy-saving forensic tool for practical law enforcement, border security, and digital identity verification solutions.