Multi-Task Pose-Invariant Face Recognition

Publication Type:
Journal Article
IEEE Transactions on Image Processing, 2015, 24 (3), pp. 980 - 993
Issue Date:
Filename Description Size
ThumbnailTIP 2015 - Multi-task Pose-Invariant Face Recognition.pdfPublished Version3.36 MB
Adobe PDF
Thumbnailproof.pdfPublished Version3.62 MB
Adobe PDF
Full metadata record
© 2015 IEEE. 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.
Please use this identifier to cite or link to this item: