Smart glasses have become more prevalent as they provide an increasing number of applications for users. They store various types of private information or can access it via connections established with other devices. Therefore, there is a growing need for user identification on smart glasses. In this paper, we introduce a low-power and minimally-obtrusive system called SonicID, designed to authenticate users on glasses. SonicID extracts unique biometric information from users by scanning their faces with ultrasonic waves and utilizes this information to distinguish between different users, powered by a customized binary classifier with the ResNet-18 architecture. SonicID can authenticate users within 0.12 seconds, with an energy consumption of 19.8 mAs per trial. A user study involving 24 participants confirms that SonicID achieves a true positive rate of 96.5%, a false positive rate of 4.1%, and a balanced accuracy of 96.2% using just 4 minutes of training data collected for each new user. This performance is relatively consistent across different remounting sessions and days. Given this promising performance, we further discuss the potential applications of SonicID and methods to improve its performance in the future.

翻译：随着智能眼镜为用户提供的应用日益增多，其普及度也不断提升。智能眼镜存储着各类私人信息，或可通过与其他设备建立的连接访问此类信息。因此，对智能眼镜进行用户身份识别的需求日益增长。本文提出一种名为SonicID的低功耗、低侵扰系统，旨在实现眼镜上的用户身份认证。SonicID通过超声波扫描用户面部提取独特的生物特征信息，并利用基于ResNet-18架构定制的二分类器，运用该信息区分不同用户。SonicID可在0.12秒内完成用户认证，单次尝试能耗为19.8毫安秒。一项包含24名参与者的用户研究表明，仅使用为每位新用户采集的4分钟训练数据，SonicID即可实现96.5%的真阳性率、4.1%的假阳性率及96.2%的平衡准确率。该性能在不同重新佩戴场景及不同日期间保持相对稳定。基于这一优异性能，我们进一步探讨了SonicID的潜在应用场景及未来性能优化方法。