ITM Web Conf.
Volume 7, 20163rd Annual International Conference on Information Technology and Applications (ITA 2016)
|Number of page(s)||8|
|Section||Session 1: Communication and Networking|
|Published online||21 November 2016|
A Smart phone Identification Method Based on Gesture
School of Electronic Science and Engineering, National University of Defense Technology, China
In order to promote the practicality of smart phone identification based on gesture, we introduce weighted morphological characteristics and early termination of authentication into dynamic time warping (DTW) algorithm, which based on characteristic moving data captured by in-built accelerometer and gyroscopes, and put forward an effective identification algorithm (ME-DTW) for smartphone. The algorithm controls the contribution made by the difference between the latitudes to the total Euclidean distance by smartphone morphological characteristics. It also introduces restricted areas touch trigger gesture acquisition scheme and authentication gesture length selection scheme based on normal distribution, which effectively improve the identification accuracy and efficiency. Experimental results show that: when others imitate gestures attack false acceptance rate tends to 0%, the personal identification false rejection rate remained at 3.29%, which can meet most practical security needs
© Owned by the authors, published by EDP Sciences, 2016
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.