確率モデルに基づく画像間差分特徴を組み合わせた入退室管理システム向け顔認証

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2011/12/01

タイトル(英語): Face Recognition for Access Control Systems Combining Image-Difference Features Based on a Probabilistic Model

著者名: 三輪　祥太郎（三菱電機（株） 先端技術総合研究所），鹿毛　裕史（三菱電機（株） 先端技術総合研究所），平位　隆史（三菱電機（株） 先端技術総合研究所），鷲見　和彦（三菱電機（株） 先端技術総合研究所）

著者名(英語): Shotaro Miwa (Advanced Technology R&D Center, Mitsubishi Electric Corp.), Hiroshi Kage (Advanced Technology R&D Center, Mitsubishi Electric Corp.), Takashi Hirai (Advanced Technology R&D Center, Mitsubishi Electric Corp.), Kazuhiko Sumi (Advanced Technology R&D Center, Mitsubishi Electric Corp.)

キーワード: 顔認証，事前確率，AdaBoost，確率モデル　　Face Recognition，Prior Probability，AdaBoost，Probabilistic Model

要約(英語): We propose a probabilistic face recognition algorithm for Access Control System(ACS)s. Comparing with existing ACSs using low cost IC-cards, face recognition has advantages in usability and security that it doesn't require people to hold cards over scanners and doesn't accept imposters with authorized cards. Therefore face recognition attracts more interests in security markets than IC-cards. But in security markets where low cost ACSs exist, price competition is important, and there is a limitation on the quality of available cameras and image control. Therefore ACSs using face recognition are required to handle much lower quality images, such as defocused and poor gain-controlled images than high security systems, such as immigration control.To tackle with such image quality problems we developed a face recognition algorithm based on a probabilistic model which combines a variety of image-difference features trained by Real AdaBoost with their prior probability distributions. It enables to evaluate and utilize only reliable features among trained ones during each authentication, and achieve high recognition performance rates.The field evaluation using a pseudo Access Control System installed in our office shows that the proposed system achieves a constant high recognition performance rate independent on face image qualities, that is about four times lower EER (Equal Error Rate) under a variety of image conditions than one without any prior probability distributions. On the other hand using image difference features without any prior probabilities are sensitive to image qualities. We also evaluated PCA, and it has worse, but constant performance rates because of its general optimization on overall data. Comparing with PCA, Real AdaBoost without any prior distribution performs twice better under good image conditions, but degrades to a performance as good as PCA under poor image conditions.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.131 No.12 （2011） 特集：電気関係学会東海支部連合大会

本誌掲載ページ: 2165-2171 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/131/12/131_12_2165/_article/-char/ja/