A Fourier-Space Palmprint Feature Extraction Method for Personal Identification

カテゴリ: 部門大会

論文No: OS1-5

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): A Fourier-Space Palmprint Feature Extraction Method for Personal Identification

著者名: Hillary Choge(徳島大学),Stephen Karungaru(徳島大学),柘植 覚(徳島大学),福見 稔(徳島大学)

著者名(英語): Hillary Choge(The University of Tokushima),Stephen Karungaru(The University of Tokushima),Satoru Tsuge(The University of Tokushima),Minoru Fukumi(The University of Tokushima)

キーワード: Palmprint|Feature Extraction|DFT|Neural Network

要約(日本語): Over the last quarter century, research in biometric systems has developed at a breathtaking pace and what started with the focus on the fingerprint has now expanded to include face, voice, iris, and behavioral characteristics such as gait. Palmprint is one of the most recent additions, and is currently the subject of great research interest due to its inherent uniqueness, stability, user-friendliness and ease of acquisition. This paper describes an effective and procedurally simple method of palmprint feature extraction for identification and verification, which takes advantage of the correspondence that exists between prominent palmprint features in the spatial domain with those in the frequency or Fourier domain, together with the more compact and precise nature of interesting points as opposed to the traditional methods based on edge points. Palmprint images from the ‘PolyU Palmprint Database’ are preprocessed before extracting features in the frequency domain based on interesting points, and these features are then selected using the KLT transform before classification via a multilayer perceptron. Preliminary tests indicate that this is an effective method for identification and/or verification.

PDFファイルサイズ: 9,966 Kバイト