3D-2D face recognition with pose and illumination normalization

详细信息    查看全文

• 作者：Ioannis A. Kakadiaris ; ¹ ; ^a ; ^{ikakadia@central.uh.edu} ; ^{ioannisk@uh.edu} ; George Toderici² ; ^a ; ^{george.toderici@gmail.com} ; Georgios Evangelopoulos³ ; ^a ; ^{gevang@mit.edu} ; Georgios Passalis⁴ ; ^a ; ^b ; ^{passalis@di.uoa.gr} ; Dat Chu⁵ ; ^a ; ^{dattanchu@gmail.com} ; Xi Zhao⁶ ; ^a ; ^{zhaoxi1@gmail.com} ; Shishir K. Shah¹ ; ^a ; ^{shah@cs.uh.edu} ; Theoharis Theoharis⁷ ; ^a ; ^b ; ^{theotheo@idi.ntnu.no}
• 关键词：Face and gesture recognition ; Biometrics ; Physically-based modeling ; 3D-2D face recognition ; Illumination normalization ; Model-based face recognition ; 3D-2D model fitting ; Object recognition ; Computer vision
• 刊名：Computer Vision and Image Understanding
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：154
• 期：Complete
• 页码：137-151
• 全文大小：5423 K
• 卷排序：154

文摘

Describes a conceptual framework for 3D-2D (or 2D-3D) face recognition. Proposes a novel 3D-2D system for 2D image face recognition from 3D datasets. Proposes a method to build subject-specific 3D gallery models, using 3D+2D data, and a method for model-based, texture representation and relighting. 3D-2D recognition surpasses 2D-2D on challenging 2D+3D data with pose and illumination variations, and can approximate 3D-3D, shape-based similarity methods. Representation and normalization using 3D models can compensate for non-frontal poses or different lighting conditions.