Design and Implementation of a Multi-Modal Biometric System for Company Access Control
This paper is about the design, implementation, and deployment of a multi-modal biometric system to grant access to a company structure and to internal zones in the company itself. Face and iris have been chosen as biometric traits. Face is feasible for non-intrusive checking with a minimum cooperat...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-05-01
|
| Series: | Algorithms |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1999-4893/10/2/61 |
| _version_ | 1819199610900447232 |
|---|---|
| author | Elisabetta Stefani Carlo Ferrari |
| author_facet | Elisabetta Stefani Carlo Ferrari |
| author_sort | Elisabetta Stefani |
| collection | DOAJ |
| description | This paper is about the design, implementation, and deployment of a multi-modal biometric system to grant access to a company structure and to internal zones in the company itself. Face and iris have been chosen as biometric traits. Face is feasible for non-intrusive checking with a minimum cooperation from the subject, while iris supports very accurate recognition procedure at a higher grade of invasivity. The recognition of the face trait is based on the Local Binary Patterns histograms, and the Daughman’s method is implemented for the analysis of the iris data. The recognition process may require either the acquisition of the user’s face only or the serial acquisition of both the user’s face and iris, depending on the confidence level of the decision with respect to the set of security levels and requirements, stated in a formal way in the Service Level Agreement at a negotiation phase. The quality of the decision depends on the setting of proper different thresholds in the decision modules for the two biometric traits. Any time the quality of the decision is not good enough, the system activates proper rules, which ask for new acquisitions (and decisions), possibly with different threshold values, resulting in a system not with a fixed and predefined behaviour, but one which complies with the actual acquisition context. Rules are formalized as deduction rules and grouped together to represent “response behaviors” according to the previous analysis. Therefore, there are different possible working flows, since the actual response of the recognition process depends on the output of the decision making modules that compose the system. Finally, the deployment phase is described, together with the results from the testing, based on the AT&T Face Database and the UBIRIS database. |
| first_indexed | 2024-12-23T03:19:05Z |
| format | Article |
| id | doaj.art-3aed0737a07c40a79a7679efcf95236e |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-12-23T03:19:05Z |
| publishDate | 2017-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-3aed0737a07c40a79a7679efcf95236e2022-12-21T18:02:03ZengMDPI AGAlgorithms1999-48932017-05-011026110.3390/a10020061a10020061Design and Implementation of a Multi-Modal Biometric System for Company Access ControlElisabetta Stefani0Carlo Ferrari1Department of Information Engineering, The University of Padova, Via Gradenigo 6a, 35131 Padova PD, ItalyDepartment of Information Engineering, The University of Padova, Via Gradenigo 6a, 35131 Padova PD, ItalyThis paper is about the design, implementation, and deployment of a multi-modal biometric system to grant access to a company structure and to internal zones in the company itself. Face and iris have been chosen as biometric traits. Face is feasible for non-intrusive checking with a minimum cooperation from the subject, while iris supports very accurate recognition procedure at a higher grade of invasivity. The recognition of the face trait is based on the Local Binary Patterns histograms, and the Daughman’s method is implemented for the analysis of the iris data. The recognition process may require either the acquisition of the user’s face only or the serial acquisition of both the user’s face and iris, depending on the confidence level of the decision with respect to the set of security levels and requirements, stated in a formal way in the Service Level Agreement at a negotiation phase. The quality of the decision depends on the setting of proper different thresholds in the decision modules for the two biometric traits. Any time the quality of the decision is not good enough, the system activates proper rules, which ask for new acquisitions (and decisions), possibly with different threshold values, resulting in a system not with a fixed and predefined behaviour, but one which complies with the actual acquisition context. Rules are formalized as deduction rules and grouped together to represent “response behaviors” according to the previous analysis. Therefore, there are different possible working flows, since the actual response of the recognition process depends on the output of the decision making modules that compose the system. Finally, the deployment phase is described, together with the results from the testing, based on the AT&T Face Database and the UBIRIS database.http://www.mdpi.com/1999-4893/10/2/61data securityadaptive multi-modal biometric systembiometric identifiersface recognitioniris recognition |
| spellingShingle | Elisabetta Stefani Carlo Ferrari Design and Implementation of a Multi-Modal Biometric System for Company Access Control Algorithms data security adaptive multi-modal biometric system biometric identifiers face recognition iris recognition |
| title | Design and Implementation of a Multi-Modal Biometric System for Company Access Control |
| title_full | Design and Implementation of a Multi-Modal Biometric System for Company Access Control |
| title_fullStr | Design and Implementation of a Multi-Modal Biometric System for Company Access Control |
| title_full_unstemmed | Design and Implementation of a Multi-Modal Biometric System for Company Access Control |
| title_short | Design and Implementation of a Multi-Modal Biometric System for Company Access Control |
| title_sort | design and implementation of a multi modal biometric system for company access control |
| topic | data security adaptive multi-modal biometric system biometric identifiers face recognition iris recognition |
| url | http://www.mdpi.com/1999-4893/10/2/61 |
| work_keys_str_mv | AT elisabettastefani designandimplementationofamultimodalbiometricsystemforcompanyaccesscontrol AT carloferrari designandimplementationofamultimodalbiometricsystemforcompanyaccesscontrol |