A Multimodal Biometric Authentication System Using the Exponential Water Wave Optimization Algorithm

Abstract

The biometric system relies on a single biometric identifier which could not meet the desired performance required for personal identification. Hence, identification based on the multimodal biometric system is emerged in the research community to achieve the personal identification process more effective. Owing to the strong binding among user identity and biometric template, the user privacy is revealed and hence the security resulted in a major requirement in the biometric system. An authentication based multimodal biometric system is developed in this research by considering different modalities, such as fingerprint, finger vein, and face. Here, the bit string is generated from the biometric sample in such a way that the bit strings are fused by employing the proposed Exponential Water Wave Optimization (EWWO) algorithm based on the involvement of logic operations. However, the process of fusion is accomplished in such a way that it depends on the random selection of two logic operators by the developed optimization approach. Accordingly, the developed EWWO is derived by the combination of Exponentially Weighted Moving Average (EWMA) and Water Wave Optimization (WWO) respectively. The authentication mechanism is achieved by employing the biometric template with the encoder and decoder operation. Moreover, the proposed method achieved the performance for Equal Error rate (EER), False Acceptance Rate (FAR), and False Rejection Rate (FRR) with the value of 0.0717, 0.0745, and 0.0689, respectively.

Patterns Identification of Finger Outer Knuckles by Utilizing Local Directional Number

“…The FOK patterns may appear differently in each image due to rotations and translations, which makes it more difficult to match them precisely. Illumination contrast can also lead to poor image quality [17,18].…”