Abstract: Biometrics has developed to be one of the most relevant technologies used in Information Technology (IT) security. Uni - Biometric systems have issues such as noisy data, non-universality, spoof attacks and unacceptable error rate. These issues can be solved by making use of multimodal biometric systems. Multimodal biometric systems utilize two or more individual traits, like face, iris, retina and fingerprint. It has higher recognition accuracy than uni-modal methods. In this system, two uni-modal biometrics, fingerprint and face are used as multi-biometrics. Decision-level fusion of these two modalities can enhance the overall performance of biometric systems. In this context, the aim of this paper is to provide a comprehensive review of the state-of-the-art methods and techniques for face and fingerprint decision-level fusion. The paper discusses the challenges and benefits of fusing these two modalities, along with a critical analysis of the existing methods. Various decision-level fusion approaches, including score-level fusion, feature-level fusion, and classifier-level fusion, are described in detail. The paper also discusses the performance evaluation of face and fingerprint decision-level fusion systems and provides insights into the future research directions in this area. The findings of this review suggest that decision-level fusion of face and fingerprint biometric modalities is a promising approach for enhancing the overall performance of biometric systems.
Keywords: Fingerprint-recognition, Face-recognition, Multimodal Biometrics, Python, OpenCV
|
DOI:
10.17148/IJARCCE.2023.12476
