BIOMET: A Multimodal Biometric Authentication System for Person Identification and Verification using Fingerprint and Face Recognition

Abstract

This paper suggests the multimodal biometrics system for identity verification using two traits: face and fingerprint. The proposed system is intended to use for the training database includes a face and four fingerprint images for each individual. The final decision is made by first individual score of face and fingerprint compares with enrolled templates and then makes fusion at matching score level architecture. The enrolled templates are stored in database. Each subsystem computes its own matching score by using closeness of feature vector and template. The decision module decides the final score by combining individual score of each trait. Multimodal system is developed through fusion of face and fingerprint recognition. The result is significantly improved by using multimodal biometric authentication.

Cross section binary coding for fusion of finger vein and finger dorsal texture

“…In comparison, fusing multiple modalities is an preferred approach to overcome the drawbacks and obtain lower error rate. Nowadays, a number of combinations of modalities are presented such as hand shape and texture [2], fingerprint and palmvein [3], face and fingerprint [4], finger vein and fingerprint [5], finger vein and finger dorsal texture [6], [7]. In consideration of difficult forgery of FV and abrasion resistance of FDT, FV and FDT is appropriate for fusion to obtain high accuracy of personal authentication.…”