Multi-Task Pose-Invariant Face Recognition
Multi-Task Pose-Invariant Face Recognition
复制标题
DOI：
10.1109/tip.2015.2390959
复制
发表时间：
2015-01
影响因子：
10.6
通讯作者：
Changxing Ding;Chang Xu;D. Tao
中科院分区：
文献类型：
--
作者：
Changxing Ding;Chang Xu;D. Tao
在无约束环境中拍摄的人脸图像通常包含显著的姿态变化，这大大降低了设计用于识别正面人脸的算法的性能。本文提出了一种新的人脸识别框架，能够处理±90°偏航范围内的姿态变化。该框架首先将原始的姿态不变人脸识别问题转化为部分正面人脸识别问题。一个强大的基于块的人脸表示方案，然后开发来表示合成的部分正面脸。对于每个补丁，一个变换字典学习下提出的多任务学习计划。变换字典将不同姿态的特征变换到一个判别子空间中。最后，人脸匹配是在补丁级别，而不是在整体水平。在FERET、CMU-PIE和Multi-PIE数据库上进行的广泛而系统的实验表明，所提出的方法始终优于基于单任务的基线以及最先进的方法。我们进一步扩展了所提出的算法的无约束人脸验证问题，并在具有挑战性的LFW数据集上实现顶级性能。
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.