Presentation 2012-05-21
Gesture Extraction Algorithm for Individual Identification
Kentaro Yamamoto, Eiji Kamioka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, a simple and secure authentication method, which correctly extracts a user's gesture from acceleration sensor data and performs a pattern matching with it, will be proposed. Such a gesture-based identification technique is considered as a biometric authentication with behavioral characteristics. One of the significant drawbacks of using the behavioral characteristics is the low authentication accuracy. Therefore, if the accuracy is improved, the approach could be utilized for a flexible authentication system since the passcode can be changed with a different gesture. The proposed method introduces a moving average technique and focuses on jerks, which are differential values of accelaration, in order to determine the thresholds for correctly extracting a gesture. This approach will enable high accuracy biometric systems with behavioral characteristcs.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Moving Average / Jerk / Biometrics / Behavioral Characteristics / Pattern Matching
Paper # MoMuC2012-4
Date of Issue

Conference Information
Committee MoMuC
Conference Date 2012/5/14(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 Multimedia Communications(MoMuC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Gesture Extraction Algorithm for Individual Identification
Sub Title (in English)
Keyword(1) Moving Average
Keyword(2) Jerk
Keyword(3) Biometrics
Keyword(4) Behavioral Characteristics
Keyword(5) Pattern Matching
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
Date 2012-05-21
Paper # MoMuC2012-4
Volume (vol) vol.112
Number (no) 44
Page pp.pp.-
#Pages 6
Date of Issue