TAPSTROKE: A novel intelligent authentication system using tap frequencies
作者：
Highlights：
• This paper deals with a novel touchstroke authentication by frequency vs time features.
• Touch times of tap-password are converted into signal and transformed by STFT.
• STFT is manipulated to reach for more precise spectrograms by two window functions.
• Classification is made by one-class SVM.
• We achieved two of the lowest EERs as 1.40%. and 2.01% by manipulated STFT.
摘要
•This paper deals with a novel touchstroke authentication by frequency vs time features.•Touch times of tap-password are converted into signal and transformed by STFT.•STFT is manipulated to reach for more precise spectrograms by two window functions.•Classification is made by one-class SVM.•We achieved two of the lowest EERs as 1.40%. and 2.01% by manipulated STFT.
论文关键词：Tapstroke,Keystroke,Authentication,Biometrics,Frequency,Short time Fourier transformation,Support vector machines
论文评审过程：Received 22 November 2018, Revised 29 May 2019, Accepted 25 June 2019, Available online 26 June 2019, Version of Record 4 July 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.057
