Bilateral Ear Acoustic Authentication: A Biometric Authentication System Using Both Ears and a Special Earphone
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...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/6/3167 |
| _version_ | 1797472889821200384 |
|---|---|
| author | Masaki Yasuhara Isao Nambu Shohei Yano |
| author_facet | Masaki Yasuhara Isao Nambu Shohei Yano |
| author_sort | Masaki Yasuhara |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T20:07:35Z |
| format | Article |
| id | doaj.art-4177b456af2344278781d04c27eeb1db |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:07:35Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4177b456af2344278781d04c27eeb1db2023-11-24T00:24:51ZengMDPI AGApplied Sciences2076-34172022-03-01126316710.3390/app12063167Bilateral Ear Acoustic Authentication: A Biometric Authentication System Using Both Ears and a Special EarphoneMasaki Yasuhara0Isao Nambu1Shohei Yano2Department of Science of Technology Innovation, Nagaoka University of Technology 1603-1, Kamitomioka Nagaoka, Niigata 940-2188, JapanGraduate School of Engineering, Nagaoka University of Technology 1603-1, Kamitomioka Nagaoka, Niigata 940-2188, JapanDepartment of Electrical and Electronic Systems Engineering, National Institute of Technology, Nagaoka College 888, Nishikatakai Nagaoka, Niigata 940-8532, JapanIn 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.https://www.mdpi.com/2076-3417/12/6/3167biometric authenticationear authenticationear canalimpulse responsesupport vector machineequal error rate |
| spellingShingle | Masaki Yasuhara Isao Nambu Shohei Yano Bilateral Ear Acoustic Authentication: A Biometric Authentication System Using Both Ears and a Special Earphone Applied Sciences biometric authentication ear authentication ear canal impulse response support vector machine equal error rate |
| title | Bilateral Ear Acoustic Authentication: A Biometric Authentication System Using Both Ears and a Special Earphone |
| title_full | Bilateral Ear Acoustic Authentication: A Biometric Authentication System Using Both Ears and a Special Earphone |
| title_fullStr | Bilateral Ear Acoustic Authentication: A Biometric Authentication System Using Both Ears and a Special Earphone |
| title_full_unstemmed | Bilateral Ear Acoustic Authentication: A Biometric Authentication System Using Both Ears and a Special Earphone |
| title_short | Bilateral Ear Acoustic Authentication: A Biometric Authentication System Using Both Ears and a Special Earphone |
| title_sort | bilateral ear acoustic authentication a biometric authentication system using both ears and a special earphone |
| topic | biometric authentication ear authentication ear canal impulse response support vector machine equal error rate |
| url | https://www.mdpi.com/2076-3417/12/6/3167 |
| work_keys_str_mv | AT masakiyasuhara bilateralearacousticauthenticationabiometricauthenticationsystemusingbothearsandaspecialearphone AT isaonambu bilateralearacousticauthenticationabiometricauthenticationsystemusingbothearsandaspecialearphone AT shoheiyano bilateralearacousticauthenticationabiometricauthenticationsystemusingbothearsandaspecialearphone |