Multi biometric system

A Multi biometric system based on hybrid deep learning classifier and optimization algorithm for Fingerprint-Iris-Face


  •   The proposed system will incorporate a hybrid deep learning classifier for each biometric modality, resulting in improved recognition accuracy.
  •   An optimization algorithm will be employed to dynamically adjust feature combinations and decision thresholds, optimizing the multi-biometric system's performance based on input data characteristics.
  •   Fusion at the score level will be performed, combining confidence scores from each biometric modality using a fusion algorithm, resulting in reduced false acceptance and rejection rates.
  •   Anti-spoofing measures specifically designed for each modality will be integrated into the system, enhancing its resilience against spoof attacks and ensuring robustness.
  •   The proposed system will be evaluated using a comprehensive dataset, comparing its performance with existing single-modal systems and fusion techniques, demonstrating its superiority in terms of recognition accuracy, anti-spoofing capabilities, and efficiency.
  • Description

Multi-biometric systems have become increasingly popular in biometrics as they improve security and accuracy in identity verification. The research introduces a new method for a multi-biometric system that combines fingerprint, iris, and face biometric modalities. This approach uses a hybrid deep learning classifier and optimization algorithm that is specifically designed for this purpose. The goal is to develop a system that is reliable and efficient by combining the advantages of different modalities. This will enhance the accuracy of recognition and decrease the risk of spoof attacks.