Automatic extraction and description of human gait models for recognition purposes
Computer Vision and Image Understanding
Android Application Development: Programming with the Google SDK
Android Application Development: Programming with the Google SDK
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
Improved Cycle Detection for Accelerometer Based Gait Authentication
IIH-MSP '10 Proceedings of the 2010 Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing
Hi-index | 0.00 |
Mobile devices are ubiquitous enough to be considered as a valid token for proof of claim to identity. Unfortunately, the small size of mobile devices also means that it is prone to being misplaced and stolen. Gait biometric on accelerometer equipped mobile devices can add another layer of security in the event of theft, as it would refute a fraudulent claim to identity. As an extra bonus, gait data can be collected without the knowledge of the person handling the mobile device. In this paper, we describe how mobile devices can be used unobtrusively for the purpose of person verification. Person verification is achieved by classification of accelerometer based gait data recorded by said mobile device. Use cases for this approach is presented in a framework; supported by proof of concept experimental results.