Multi-modal Biometric Authentication System Using Cnn

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Prathamesh Shrinivas Shukla
Format: Recurso digital
Veröffentlicht: Zenodo 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866901687545888768
author Prathamesh Shrinivas Shukla
author_facet Prathamesh Shrinivas Shukla
contents In practical applications, unimodal biometric systems rely on evidence from a single source of information for authentication. However, these systems encounter challenges, including noise in the sensed data arising from factors such as the repeated use of fingerprint sensors and intra-class variation. For instance, the reliability of a fingerprint-based system may be compromised due to variations in the sensed data caused by repeated sensor use. To address these limitations, the adoption of a multi-modal biometric authentication system becomes pivotal. This approach enhances the robustness and reliability of the authentication process by incorporating multiple biometric traits. The utilization of multiple modalities ensures that the system is better equipped to discern the presence of a live user at the data acquisition point, thereby mitigating the impact of potential challenges associated with unimodal systems. Common examples of multimodal biometrics involve the fusion of different biometric modalities, such as face and fingerprint or iris and fingerprint. By integrating diverse biometric sources, a multimodal approach leverages the strengths of each modality, contributing to a more resilient and effective authentication system in real-world scenarios.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18172514
institution Zenodo
language
publishDate 2024
publisher Zenodo
record_format zenodo
spellingShingle Multi-modal Biometric Authentication System Using Cnn
Prathamesh Shrinivas Shukla
Multi-modal Biometric Authentication System; Convolution Neural Network; Face Recognition; Fingerprint Recognition
In practical applications, unimodal biometric systems rely on evidence from a single source of information for authentication. However, these systems encounter challenges, including noise in the sensed data arising from factors such as the repeated use of fingerprint sensors and intra-class variation. For instance, the reliability of a fingerprint-based system may be compromised due to variations in the sensed data caused by repeated sensor use. To address these limitations, the adoption of a multi-modal biometric authentication system becomes pivotal. This approach enhances the robustness and reliability of the authentication process by incorporating multiple biometric traits. The utilization of multiple modalities ensures that the system is better equipped to discern the presence of a live user at the data acquisition point, thereby mitigating the impact of potential challenges associated with unimodal systems. Common examples of multimodal biometrics involve the fusion of different biometric modalities, such as face and fingerprint or iris and fingerprint. By integrating diverse biometric sources, a multimodal approach leverages the strengths of each modality, contributing to a more resilient and effective authentication system in real-world scenarios.
title Multi-modal Biometric Authentication System Using Cnn
topic Multi-modal Biometric Authentication System; Convolution Neural Network; Face Recognition; Fingerprint Recognition
url https://doi.org/10.5281/zenodo.18172514