Abstract
In existing biometric authentication methods, the user must perform an authentication operation such as placing a finger in a scanner or facing a camera. With ear acoustic authentication, the acoustic characteristics of the ear canal can be used as biometric information. Therefore, a person wearing earphones does not need to perform any authentication operation. Existing studies which use the acoustic characteristics of the ear canal as biometric information only measure the characteristics of one ear. However, the acoustic characteristics of the human ear canal can be measured from both ears. Hence, we proposed a new method for acoustic authentication based on the ability to measure the acoustic characteristics of the ear canal from both ears. The acoustic characteristics of the ear canal of 52 subjects were measured. Comparing the acoustic characteristics of the left and right ear canals, a difference in the signal between the left and right ear was observed. To evaluate the authentication accuracy, we calculated the evaluation indices of biometric authentication, equal error rate (EER), and area under curve (AUC). The EER for bilateral ear acoustic authentication using signals from both ears was 0.39%, which was lower than that of a single ear. The AUC was 0.0016 higher for bilateral ear acoustic authentication. Therefore, the use of bilateral signals for ear acoustic authentication was proved to be effective in improving authentication accuracy.
Funder
Japan Society for the Promotion of Science
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Biometrics;Computer and Information Security Handbook;2025
2. Domain-adaptation method between acoustic-response data using different insert earphones;The Journal of the Acoustical Society of America;2024-04-01
3. Multibiometric classification for people based on artificial bee colony method and decision tree;PHYSICAL MESOMECHANICS OF CONDENSED MATTER: Physical Principles of Multiscale Structure Formation and the Mechanisms of Nonlinear Behavior: MESO2022;2023