マット型圧力センサを用いた生体認証システムの開発

カテゴリ: 部門大会

論文No: GS15-4

グループ名: 【C】平成20年電気学会電子・情報・システム部門大会講演論文集

発行日: 2008/08/20

タイトル(英語): Biometric Personal Identification System by Load Distribution Sensor

著者名: 叶紅 (兵庫県立大学),谷口 和彦(きんでん),小橋昌司 (兵庫県立大学),畑 豊(兵庫県立大学),浅利 一成(関西電力)

著者名(英語): Hong Ye(University of Hyogo),Kazuhiko Taniguchi(Kinden Corporation),Syoji Kobashi(University of Hyogo),Yutaka Hata(University of Hyogo),kazunari Asari(The Kansai Electric Power Co.,Inc.)

キーワード: 生体認証|足底圧力|重心|マット型圧力センサ|ニューラルネットワーク|Biometrics|Sole pressure|Center of Pressure|Load Distribution Sensor|Neural Network

要約(日本語): Biometrics technology, as a method of personal Identification, plays an important role in our daily lives. In this paper, we propose a biometrics personal identification system using Center of Pressure (COP) tested by a load distribution sensor. Refer to sole-data-based biometrics approach, gait or footprint is exclusively employed. However, to suit for the service environment, it is necessary to develop a biometrics system with less information, costs less time and take less space. We propose a biometric personal identification system. First, we have a user stand on load distribution sensor with shoes, and acquire pressure data during a simple motion, as touching a bell nearby by one hand but without movements of feet. Second, we calculate the site of COP from obtained pressure data. Features for identification are extracted from the COP position or the movement of COP. We built a Neural Network (NN) model with the feature value. Third, we input test data to the NN model to identify them. We employ 10 volunteers, and experimental result reveals that the proposed identification method can achieve almost 92.0% accuracy.

PDFファイルサイズ: 3,806 Kバイト