Multi-task pose-invariant face recognition

Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:
Journal Article
Citation:
IEEE Transactions on Image Processing, 2015, 24 (3), pp. 980 - 993 (14)
Issue Date:
2015-03-01
Full metadata record
Files in This Item:
Filename Description Size
ThumbnailTIP 2015 - Multi-task Pose-Invariant Face Recognition.pdfPublished Version3.36 MB
Adobe PDF
Thumbnailproof.pdfPublished Version3.62 MB
Adobe PDF
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 multitask 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: