基于手机加速度传感器的静态手势身份认证方法

摘要

Aiming at disadvantages of the existing ID authentication methods on smart mobile-phone,ID authentication method based on physiological tremor is proposed. To achieve the authentication,the physiological tremor of the upper limb is used as biological feature,when a user holds a mobile device with a specific static posture,tremor data is recorded from the embedded accelerometer of the device,after signal preprocessing,power spectral density( PSD)is obtained and act as ID template,then similarity between the test signal and the template is calculated by dynamic time warping algorithm( DTW ),and the authentication result is obtained from the similarities. Experimental results show that both the equal error rate( EER)and the half total error rate( HTER)are below 8%,which means a good performance of the algorithm.%针对智能手机上现有传统身份认证方法的缺点，提出一种基于人体生理震颤的静态手势身份认证方法。该方法在用户按特定静态姿势手持智能手机时，由手机内置的加速度传感器记录因持手机而产生的上肢肌肉震颤，经过信号预处理，得到信号的功率谱密度（ PSD）作为身份模板。通过动态时间规整（ DTW）算法计算待认证信号的PSD和模板之间的相似度，得到认证结果。实验结果表明：该方法的等错误率（ EER）和半错误率（ HTER）均在8%以下，验证了本方法的有效性。