A Score-Fusion Method Based on the Sine Cosine Algorithm for Enhanced Multimodal Biometric Authentication.

Area of Science:

• Computer Science
• Biometrics
• Artificial Intelligence

Background:

• Multimodal biometric systems enhance security by integrating multiple identification modalities.
• Score fusion techniques are crucial for optimizing performance by combining individual modality scores.
• Existing methods face challenges in adaptive parameter selection for effective score fusion.

Purpose of the Study:

• To propose a novel score fusion method for multimodal biometric authentication systems.
• To leverage the Sine Cosine Algorithm (SCA) for optimizing score fusion parameters.
• To evaluate the proposed method's performance against existing techniques.

Main Methods:

• Feature extraction from multiple biometric sources (iris, face).
• Normalization and aggregation of intra/inter scores using statistical methods (mean, max, min, median, summation, Tanh).
• Optimization of fusion parameters using the Sine Cosine Algorithm (SCA).

Main Results:

• The proposed SCA-based score fusion method achieved an Equal Error Rate (EER) of 1.003% when fusing left iris, right iris, and face data.
• Demonstrated significant performance improvement, up to 85.89%, over unimodal systems.
• Outperformed existing optimization-based score fusion methods under identical experimental conditions.

Conclusions:

• The Sine Cosine Algorithm (SCA) is effective for adaptive score fusion in multimodal biometric systems.
• The proposed method offers a robust and accurate approach to biometric authentication.
• This research validates the benefits of SCA for optimizing multimodal biometric performance.