Personal feature extraction via grip force sensors mounted on a mobile phone: authenticating the user during key-operation

Authors:
Toshiki Iso;Tsutomu Horikoshi;Masakatsu Tsukamoto;Takeshi Higuchi
Affiliations:
Research Laboratories, NTTDOCOMO, Hikari-no-oka, Yokosuka, Kanagawa, Japan;Research Laboratories, NTTDOCOMO, Hikari-no-oka, Yokosuka, Kanagawa, Japan;NTTDOCOMO, Hikari-no-oka, Yokosuka, Kanagawa, Japan;NTTDOCOMO, Hikari-no-oka, Yokosuka, Kanagawa, Japan
Venue:
Proceedings of the 11th International Conference on Mobile and Ubiquitous Multimedia
Year:
2012

Citing 7
Cited 0

Typing Patterns: A Key to User Identification

IEEE Security and Privacy
Gait analyzer based on a cell phone with a single three-axis accelerometer

Proceedings of the 8th conference on Human-computer interaction with mobile devices and services
Image Feature Extraction Using Gradient Local Auto-Correlations

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Hand grip pattern recognition for mobile user interfaces

IAAI'06 Proceedings of the 18th conference on Innovative applications of artificial intelligence - Volume 2
Characteristics of pressure-based input for mobile devices

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Unobtrusive User-Authentication on Mobile Phones Using Biometric Gait Recognition

IIH-MSP '10 Proceedings of the 2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing
A new metric for probability distributions

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose an algorithm for authenticating the user of a mobile phone from the outputs of pressure sensors during key-operations such as button-pushes. While not intended to replace password identification, it does help in providing the service which is suitable for a user without any his/her specific action. For example, during user's entering key strokes. if a service cloud can recognize user-authentication by analyzing key strokes, then, it can find the optimal services based on the user preference. Our algorithm is based on a statistic probabilistic model based approach; it calculates the probability distribution of the temporal differential values of pressure by Kalman filtering. The captured sensory data is compared to predicted sensory data based on the probability distribution to judge whether the person making the key-operation is the registered owner or not. We implement the proposed system and subject it to feasibility experiments with 10 subjects; its user-authentication accuracy is quite good with a FAR-FRR error rate of only 10[%].