Towards Unconstrained Face Recognition
Publication Date
2008
Journal or Book Title
2008 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, VOLS 1-3
Abstract
In this paper, we argue that the most difficult face recognition problems (unconstrained face recognition) will be solved by simultaneously leveraging the solutions to multiple vision problems including segmentation, alignment, pose estimation, and the estimation of other hidden variables such as gender and hair color. While in theory a single unified principle could solve all these problems simultaneously in a giant hidden variable model, we believe that such an approach will be computationally, and more importantly, statistically, intractable. Instead, we promote studying the interactions among mid-level vision features, such as segmentations and pose estimates, as a route toward solving very difficult recognition problems. In this paper, we discuss and provide results showing how pose and face segmentations mutually influence each other, and provide a surprisingly simple method for estimating pose from segmentations.
DOI
https://doi.org/10.1109/CVPRW.2008.4562973
Pages
166-173
Book Series Title
PROCEEDINGS - IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
Recommended Citation
Huang, GB; Narayana, M; and Learned-Miller, E, "Towards Unconstrained Face Recognition" (2008). 2008 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, VOLS 1-3. 733.
https://doi.org/10.1109/CVPRW.2008.4562973