Presentation 2014-03-14
Convenience-oriented Hybrid Biometric Identification using Aerial Signature
Kentaro Yamamoto, Eiji Kamioka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Personal authentication has been regarded as an important research domain from the viewpoint of security and privacy protection in the advanced information society. In this paper, an aerial signature based hybrid biometric identification system using Kinect, which is a simple and robust authentication method in a desktop environment, will be proposed and its effectiveness will be discussed. In this system, the user can execute his/her authentication by just making pre-registered gestures in front of the identification equipment without carrying any devices. Aerial gestures do not leave the information in a tangible way, therefore the characteristics such as the form, gesture speed and brushstrokes cannot be easily imitated by other people. The feature amount is extracted base on the information obtained from Kinect, processed, and used to perform Artificial Neural Network for calculating the authentication accuracy. The evaluation result shows the average authentication accuracy of 99.3% which is satisfactory for the first step of this work.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Biometrics / Kinect / Natural User Interface / Artificial Neural Network
Paper # MoNA2013-81
Date of Issue

Conference Information
Committee MoNA
Conference Date 2014/3/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Mobile Network and Applications(MoNA)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Convenience-oriented Hybrid Biometric Identification using Aerial Signature
Sub Title (in English)
Keyword(1) Biometrics
Keyword(2) Kinect
Keyword(3) Natural User Interface
Keyword(4) Artificial Neural Network
1st Author's Name Kentaro Yamamoto
1st Author's Affiliation Graduate School of Engineering and Science, Shibaura Institute of Technology()
2nd Author's Name Eiji Kamioka
2nd Author's Affiliation Graduate School of Engineering and Science, Shibaura Institute of Technology
Date 2014-03-14
Paper # MoNA2013-81
Volume (vol) vol.113
Number (no) 495
Page pp.pp.-
#Pages 6
Date of Issue