An Improved Multi-View Face Synthesis Method Based on Point Distribution Models

摘要：

A multi-view face synthesis method has been proposed based on point distribution models (PDMs) for face recognition across pose, which strongly relies on the “ pose parameters in the PDM to control the up-down and/or leftright rotations of faces. However, the pose parameters would not appear in the fi xed positions, and that may result in undesired virtual faces with some defi nite training data. Thus, a simple yet effective automatic inspection strategy is introduced in this paper to fi nd the corresponding pose parameters for the desired face pose transformation, which could be used to improve the performance of the existing face synthesis methods. Meanwhile, a counterexample is given to illustrate show the latent defect of the existing methods. Experimental results are provided to validate the effectiveness of the proposed solution.

关键词： face synthesis point distribution models PCA

作者: Fei Yang Dan Xia Fanbao Meng

作者单位: Department of Automation, School of Power andMechanical Engineering, Wuhan University, Wuhan, China. Department of Information Technology, Central China Normal University, Wuhan, China. Unit 75719 of the Peoples Liberation Army, Wuhan, China.

会议类型: 国际会议

会议名称: The 24th Chinese Control and Decision Conference (第24届中国控制与决策学术年会 2012 CCDC)

会议地点: 太原

会议语种:英文

页码: 208-211

在线出版日期: 2012-05-23（万方平台首次上网日期，不代表论文的发表时间）