KMS Chongqing Institute of Green and Intelligent Technology, CAS
Multi-View Face Recognition Via Well-Advised Pose Normalization Network | |
Shao, Xiaohu1,2; Zhou, Xiangdong1; Li, Zhenghao1; Shi, Yu1 | |
2020 | |
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. |
关键词 | Multi-view face recognition GAN face frontalization quality assessment |
DOI | 10.1109/ACCESS.2020.2983459 |
发表期刊 | IEEE ACCESS |
ISSN | 2169-3536 |
卷号 | 8页码:66400-66410 |
通讯作者 | Zhou, Xiangdong(xiangdongzhou@foxmail.com) |
收录类别 | SCI |
WOS记录号 | WOS:000527415800002 |
语种 | 英语 |