Оn the issue of assessing the effectiveness of biometric systems
DOI:
https://doi.org/10.30837/pt.2023.1.03Abstract
The current scientific task of quantitative assessment of the effectiveness of existing and developing biometric systems is considered. Known works on the comparative analysis of biometric systems, as a rule, discuss their characteristics and principles of operation. However, there is no data on the quantitative assessment of the effectiveness of biometric systems, of which there are quite a few on the market. In the proposed work, an attempt is made to eliminate this shortcoming. The development is based on a systematic approach, namely the efficiency/cost criterion. When evaluating efficiency, the main characteristics of biometric systems are used — errors of the first and second kind, the estimates of which are given and analyzed in the scientific literature. At the same time, it is possible to take into account various consequences caused by errors of the first and second kind. For this, a special coefficient is introduced. For the first time, a quantitative comparative analysis of biometric systems used in modern access control and management systems, namely dactyloscopy, 2D and 3D facial geometry, and voice, was carried out. According to the results of research, dactyloscopy (fingerprints) turned out to be the most effective. The 2D face geometry, which is quite widely used in mod-ern access control and management systems, has the worst performance indicators ac-cording to the developed criterion. In order to increase the efficiency of voice systems, it is proposed to reduce the probability of false recognition by an order of magnitude, for example, due to accounting for the phase data of the processed signals. The developed criterion is characterized by simplicity, correctness, physical clarity, completeness of accounting of the main characteristics of reliability and reliability, and can also be used to assess the current state of known biometric systems, as well as to determine the main directions of their improvement. The obtained results can be used both at the stage of development and selection of biometric systems.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
