2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (2008)
Anchorage, AK, USA
June 23, 2008 to June 28, 2008
Manjunath Narayana , University of Massachusetts, Amherst, USA
Erik Learned-Miller , University of Massachusetts, Amherst, USA
Gary B. Huang , University of Massachusetts, Amherst, USA
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.
Manjunath Narayana, Erik Learned-Miller, Gary B. Huang, "Towards unconstrained face recognition", 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 00, no. , pp. 1-8, 2008, doi:10.1109/CVPRW.2008.4562973