Multi-Task Pose-Invariant Face Recognition | |
Ding, Changxing ; Xu, Chang ; Tao, Dacheng | |
刊名 | IEEE Transactions on Image Processing
![]() |
2015 | |
DOI | 10.1109/TIP.2015.2390959 |
英文摘要 | Face images captured in unconstrained environments usually contain significant pose variation, which dramatically degrades the performance of algorithms designed to recognize frontal faces. This paper proposes a novel face identification framework capable of handling the full range of pose variations within ±90° of yaw. The proposed framework first transforms the original pose-invariant face recognition problem into a partial frontal face recognition problem. A robust patch-based face representation scheme is then developed to represent the synthesized partial frontal faces. For each patch, a transformation dictionary is learnt under the proposed multi-task learning scheme. The transformation dictionary transforms the features of different poses into a discriminative subspace. Finally, face matching is performed at patch level rather than at the holistic level. Extensive and systematic experimentation on FERET, CMU-PIE, and Multi-PIE databases shows that the proposed method consistently outperforms single-task-based baselines as well as state-of-the-art methods for the pose problem. We further extend the proposed algorithm for the unconstrained face verification problem and achieve top-level performance on the challenging LFW data set. ? 2015 IEEE.; EI; 3; 980-993; 24 |
语种 | 英语 |
内容类型 | 期刊论文 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/436049] ![]() |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Ding, Changxing,Xu, Chang,Tao, Dacheng. Multi-Task Pose-Invariant Face Recognition[J]. IEEE Transactions on Image Processing,2015. |
APA | Ding, Changxing,Xu, Chang,&Tao, Dacheng.(2015).Multi-Task Pose-Invariant Face Recognition.IEEE Transactions on Image Processing. |
MLA | Ding, Changxing,et al."Multi-Task Pose-Invariant Face Recognition".IEEE Transactions on Image Processing (2015). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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