Knowledge Commons of Institute of Automation,CAS
High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild | |
Zhu XY(朱翔昱); Lei Z(雷震); Yan JJ(闫俊杰); Yi D(易东); Li ZQ(李子青) | |
2015 | |
会议名称 | IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
会议日期 | 7-12 June, 2015 |
会议地点 | Boston, MA, USA |
摘要 |
Pose and expression normalization is a crucial step to recover the canonical view of faces under arbitrary conditions, so as to improve the face recognition performance. An ideal normalization method is desired to be automatic, database independent and should preserve the face appearance with little artifact and information loss, which we call high-fidelity. However, most normalization methods fail to satisfy one or more of the goals.In this paper, we propose a High-fidelity Pose and Expression Normalization (HPEN) method with 3D Morphable Model (3DMM) which can automatically generate a natural face image in frontal pose and neutral expression.Specifically, we firstly make a landmark marching assumption to describe the non-correspondence between 2D and 3D landmarks caused by pose variations and propose a pose adaptive 3DMM fitting algorithm. Secondly, we mesh the whole image into a 3D object and eliminate the pose and expression variations using an identity preserving 3D transformation. Finally, we propose an inpainting method based on Possion Editing to fill the invisible region caused by self occlusion. Extensive experiments on Multi-PIE and LFW demonstrate that the proposed method significantly improves face recognition performance and outperforms state-of-the-art methods in both constrained and unconstrained environments. |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/14784 |
专题 | 多模态人工智能系统全国重点实验室_生物识别与安全技术 |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhu XY,Lei Z,Yan JJ,et al. High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild[C],2015. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
07298679.pdf(2596KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论