Toward Posture Recognition with Touch Screen Biometrics

Touch screen data from smartphones can be used to extract behavioral biometric features and enhance user experience of touch screen applications based on user's current environment, such as body postures. In this paper we propose a new method for selecting biometric features in order to recognize body postures when performing simple swipes on the touch screens of smartphones. We performed a controlled experiment in which participants performed the swipes in six different postures (standing and five variants of sitting postures). From the experimental data we extracted features describing the swipe movements and performed feature selection with our method, which leverages the t-test statistic to compare the similarity of values in each pair of postures for each feature. The results show that several touch pressure-related features that were extracted significantly contribute to body posture recognition of a user.

[1]  Cheng-Jung Tsai,et al.  A graphical-based password keystroke dynamic authentication system for touch screen handheld mobile devices , 2012, J. Syst. Softw..

[2]  Tao Feng,et al.  Continuous mobile authentication using touchscreen gestures , 2012, 2012 IEEE Conference on Technologies for Homeland Security (HST).

[3]  Daniela Chudá,et al.  Multifactor authentication based on keystroke dynamics , 2009, CompSysTech '09.

[4]  Ranveer Chandra,et al.  Proceedings of the 19th annual international conference on Mobile computing & networking , 2013, MOBICOM 2013.

[5]  Dawn Xiaodong Song,et al.  Touchalytics: On the Applicability of Touchscreen Input as a Behavioral Biometric for Continuous Authentication , 2012, IEEE Transactions on Information Forensics and Security.

[6]  Alex X. Liu,et al.  Secure unlocking of mobile touch screen devices by simple gestures: you can see it but you can not do it , 2013, MobiCom.

[7]  Blake D. Bryant,et al.  IEEE Transactions on Information Forensics and Security , 2018 .

[8]  Deron Liang,et al.  A New Non-Intrusive Authentication Method Based on the Orientation Sensor for Smartphone Users , 2012, 2012 IEEE Sixth International Conference on Software Security and Reliability.

[9]  Shumin Zhai,et al.  Touch behavior with different postures on soft smartphone keyboards , 2012, Mobile HCI.

[10]  Roger Wattenhofer,et al.  A personal touch: recognizing users based on touch screen behavior , 2012, PhoneSense '12.

[11]  Jun Yang,et al.  SenGuard: Passive user identification on smartphones using multiple sensors , 2011, 2011 IEEE 7th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob).

[12]  Ramesh Govindan,et al.  Proceedings of the Third International Workshop on Sensing Applications on Mobile Phones , 2012 .

[13]  Daniela Chudá,et al.  Mouse Clicks Can Recognize Web Page Visitors! , 2015, WWW.

[14]  Tao Feng,et al.  TIPS: context-aware implicit user identification using touch screen in uncontrolled environments , 2014, HotMobile.

[15]  Shwetak N. Patel,et al.  GripSense: using built-in sensors to detect hand posture and pressure on commodity mobile phones , 2012, UIST.