中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 重庆绿色智能技术研究院
  3. 中国科学院重庆绿色智能技术研究院
Multi-View Face Recognition Via Well-Advised Pose Normalization Network

文献类型：期刊论文

作者Shao, Xiaohu1,2; Zhou, Xiangdong2; Li, Zhenghao2; Shi, Yu2
刊名IEEE ACCESS
出版日期2020
卷号8页码:66400-66410
关键词Multi-view face recognition GAN face frontalization quality assessment
ISSN号2169-3536
DOI10.1109/ACCESS.2020.2983459
通讯作者Zhou, Xiangdong(xiangdongzhou@foxmail.com)
英文摘要Numerous face frontalization methods based on 3D Morphable Model (3DMM) and Generative Adversarial Networks (GAN) have made great progress in multi-view face recognition. However, facial feature analysis and identity discrimination often suffer from failure frontalization results because of monotonous single-domain training and unpredictable input profile faces. To overcome the drawback, we present a novel approach named Well-advised Pose Normalization Network (WAPNN), which leverages multiple domains and extracts features considering their frontalization qualities wisely, to achieve a high accuracy on multi-view face recognition. Through multi-domain datasets, we design an end-to-end facial pose normalization network with adaptive weights on different objectives to exploit potentialities of various profile-front relationships. Meanwhile, the proposed method encourages intra-class compactness and inter-class separability between facial features by introducing quality-aware feature fusion. Experimental analyses show that our method effectively recovers frontal faces with good-quality textures and high identity-preserving, and significantly reduces the impact of various poses on face recognition under both constrained and wild environments.
资助项目National Key Research and Development Program of China[2018YFC0808303] ; National Natural Science Foundation of China[61806185] ; National Natural Science Foundation of China[61802361] ; Technology Innovation and Application Development Projects in Chongqing[cstc2019jscx-msxmX0299] ; Technology Innovation and Application Development Projects in Chongqing[cstc2019jscx-gksbX0073]
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
WOS记录号WOS:000527415800002
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.138/handle/2HOD01W0/10905]  
专题中国科学院重庆绿色智能技术研究院
通讯作者Zhou, Xiangdong
作者单位1.Univ Chinese Acad Sci, Beijing 100864, Peoples R China
2.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing 400714, Peoples R China
推荐引用方式
GB/T 7714		 Shao, Xiaohu,Zhou, Xiangdong,Li, Zhenghao,et al. Multi-View Face Recognition Via Well-Advised Pose Normalization Network[J]. IEEE ACCESS,2020,8:66400-66410.
APA Shao, Xiaohu,Zhou, Xiangdong,Li, Zhenghao,&Shi, Yu.(2020).Multi-View Face Recognition Via Well-Advised Pose Normalization Network.IEEE ACCESS,8,66400-66410.
MLA Shao, Xiaohu,et al."Multi-View Face Recognition Via Well-Advised Pose Normalization Network".IEEE ACCESS 8(2020):66400-66410.

入库方式： OAI收割

来源：重庆绿色智能技术研究院

浏览0
下载0
收藏0
其他版本

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。