Optimization Problems for Fast AAM Fitting in-the-Wild
Authors:
- Georgios TzimiropoulosGTGeorgios Tzimiropoulos
- Maja PanticMPMaja Pantic
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 593-600
Abstract
We describe a very simple framework for deriving the most-well known optimization problems in Active Appearance Models (AAMs), and most importantly for providing efficient solutions. Our formulation results in two optimization problems for fast and exact AAM fitting, and one new algorithm which has the important advantage of being applicable to 3D. We show that the dominant cost for both forward and inverse algorithms is a few times mN which is the cost of projecting an image onto the appearance subspace. This makes both algorithms not only computationally realizable but also very attractive speed-wise for most current systems. Because exact AAM fitting is no longer computationally prohibitive, we trained AAMs in-the-wild with the goal of investigating whether AAMs benefit from such a training process. Our results show that although we did not use sophisticated shape priors, robust features or robust norms for improving performance, AAMs perform notably well and in some cases comparably with current state-of-the-art methods. We provide Matlab source code for training, fitting and reproducing the results presented in this paper at http://ibug.doc.ic.ac.uk/resources.Keywords
This publication has 17 references indexed in Scilit:
- A Semi-automatic Methodology for Facial Landmark Annotation2013
- Fourier Lucas-Kanade AlgorithmIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Localizing parts of faces using a consensus of exemplars2011
- Learning AAM fitting through simulationPattern Recognition, 2009
- Efficient image inner products applied to active appearance models2008 19th International Conference on Pattern Recognition, 2008
- Adaptive and constrained algorithms for inverse compositional Active Appearance Model fitting2008
- Generic Face Alignment using Boosted Appearance Model2007
- A Nonlinear Discriminative Approach to AAM Fitting2007
- Active Appearance Models RevisitedInternational Journal of Computer Vision, 2004
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004