LAUSR

In recent years, biometric authentication technology for smartphones has become widespread, with the mainstream methods being fingerprint authentication and face recognition. However, fingerprint authentication cannot be used when hands are wet, and face recognition cannot be used when a person is wearing a mask. Like the face and fingers, the ear as a biometric contains features that enable human identification and has been the subject of research on personal authentication. Authentication systems based on the acoustic transfer function of the pinna (PRTF: Pinna Related Transfer Function) have been investigated. However, the authentication accuracy decreases due to the positional fluctuation across each measurement. In this paper, we propose multimodal personal authentication on smartphones using PRTF. The pinna image and positional sensor information are used with the PRTF, and the effectiveness of the authentication method is examined. Half total error rate (HTER) of 9.3% for single-modal authentication using only PRTF was improved to 1.6% for multimodal authentication using images and sensor data. We demonstrate that the proposed authentication system can compensate for the positional changes in each measurement and improve the robustness.