ニューラルネットワークを用いた3次元顔画像の自動生成

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: 2013/01/01

タイトル(英語): Automatic Generation of 3D Facial Image Using Artificial Neural Networks

著者名: 山本　琢麿（名古屋工業大学大学院 産業戦略工学専攻），服部　公央亮（名古屋工業大学大学院 産業戦略工学専攻），田口　亮（名古屋工業大学大学院 産業戦略工学専攻），保黒　政大（中部大学 工学部 電子情報工学科），梅崎　太造（名古屋工業大学大学院 産業戦略工学専攻）

著者名(英語): Takuma Yamamoto (Nagoya Institute of Technology), Koosuke Hattori (Nagoya Institute of Technology), Ryo Taguchi (Nagoya Institute of Technology), Masahiro Hoguro (Chubu University), Taizo Umezaki (Nagoya Institute of Technology)

キーワード: ニューラルネットワーク，3次元復元，顔画像　　Neural networks，3D reconstruction，Facial image

要約(英語): Face is one of the most important factor to communicate with people. Therefore, many face recognition systems have been developed. These systems use images captured by a camera to recognize a person. However, facial images are various due to some external factors, such as the position of the body, luminous surroundings, facial expressions, and so on. These variations make recognition accuracy worse, therefore face recognition systems have been required to overcome this problem. Three-dimensional face data can solve this problem, but three-dimensional measuring systems are expensive. We propose a method that estimates three-dimensional face data from two-dimensional image which is captured by a camera. This method uses an artificial neural networks which learned the relations between two-dimensional facial images and three-dimensional facial data. We generate these data measured by a CCD camera and a laser range finder for teaching the artificial neural networks. The experimental results show that the proposed method is effective.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.133 No.1 （2013） 特集：2012 Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV2012)

本誌掲載ページ: 193-199 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/133/1/133_193/_article/-char/ja/