MULTIMODAL BIOMETRIC IDENTIFICATION SYSTEM USING THUMBPRINT AND FACIAL RECOGNITION
Abstract
To address the vulnerabilities of unimodal biometrics, this study presents a robust identification system fusing fingerprint and facial data. The system employs a minutiae-based approach for fingerprints and a DeepFace convolutional neural network for facial recognition. Matching scores from both modalities are normalized and fused at the score-level using a weighted sum. Implemented in Python, the system was evaluated on a custom dataset, achieving a superior 98.5% accuracy. A significant improvement over individual modalities while also substantially lowering False Acceptance and False Rejection Rates. This demonstrates that the multimodal fusion creates a highly secure and dependable solution for critical access control.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.