Multi-Biometrics: Survey and Projection of a New Biometric System
Abdoul Kamal Assouma1, Tahirou Djara2, Abdou-Aziz Sobabe3
1Abdoul Kamal Assouma, Department of Computer Engineering and Telecommunications, Polytechnic School of Abomey-Calavi/ University of Abomey-Calavi, Abomey-Calavi, Benin.
2Tahirou Djara, Department of Computer Engineering and Telecommunications, Polytechnic School of Abomey-Calavi/ University of Abomey-Calavi, Abomey-Calavi, Benin.
3Abdou-Aziz Sobabe, Department of Computer Engineering and Telecommunications, Polytechnic School of Abomey-Calavi/ University of Abomey-Calavi, Abomey-Calavi, Benin.
Manuscript received on 16 January 2023 | Revised Manuscript received on 10 February 2023 | Manuscript Accepted on 15 February 2023 | Manuscript published on 28 February 2023 | PP: 80-87 | Volume-12 Issue-3, February 2023 | Retrieval Number: 100.1/ijeat.C40080212323 | DOI: 10.35940/ijeat.C4008.0212323
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Multi-biometric systems using feature-level fusion allow more accuracy and reliability in recognition performance than uni-biometric systems. However, in practice, this type of fusion is challenging to implement, especially when we encounter heterogeneous biometric modalities or incompatible features. The major challenge of feature fusion is to represent each modality with an excellent level of discrimination. Beyond pure biometric modalities, the use of metadata has been shown to enhance the performance of biometric systems. Given these findings, our work focuses on multi-origin biometrics, which allows the use of pure biometric modalities and metadata in a feature fusion strategy. The primary objective of this paper is to provide an overview of biometrics as presented in the literature, with a particular focus on multibiometrics, and to propose a model for a multi-origin biometric system utilising both pure biometric and soft biometric modalities in a feature-level fusion strategy. The curvelet transformation and order statistics are proposed, respectively, for extracting the features of pure biometric modalities and for selecting the relevant features of each modality to ensure a good level of discrimination among individuals. In this paper, we present an overview of biometrics, including its concepts, modalities, advantages, disadvantages, and implementation architectures. A focus has been placed on multi-biometrics, with the presentation of a harmonised process for feature fusion. For the experiments, we proposed a global model for feature fusion in a multi-origin system, utilising face and iris modalities as pure biometrics, and facial skin colour as metadata. This system and the results will be presented in future work.
Keywords: Features, Fusion, Hierarchical-Sequential, Multi-Origin.
Scope of the Article: Software Dependability, Reliability, Scalability