Jump to content

Active appearance model

From Wikipedia, the free encyclopedia
This is an old revision of this page, as edited by Mogism (talk | contribs) at 22:43, 2 November 2012 (External links: Typo fixing and cleanup, typos fixed: commerical → commercial using AWB (8414)). The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

An active appearance model (AAM) is a computer vision algorithm for matching a statistical model of object shape and appearance to a new image. They are built during a training phase. A set of images, together with coordinates of landmarks that appear in all of the images, is provided to the training supervisor.

The model was introduced by Cootes, Edwards and Taylor in 1998.[1][2] The approach is widely used for matching and tracking faces and for medical image interpretation.

The algorithm uses the difference between the current estimate of appearance and the target image to drive an optimization process. By taking advantage of the least squares techniques, it can match to new images very swiftly.

It is related to the active shape model (ASM). One disadvantage of ASM is that it only uses shape constraints (together with some information about the image structure near the landmarks), and does not take advantage of all the available information – the texture across the target object. This can be modelled using an AAM.

  • Free Tools for experimenting with AAMs from Manchester University (for research use only).
  • Description of AAMs from Manchester University.
  • Tim Cootes' home page (one of the original co-inventors of AAMs).
  • Mikkel B. Stegmann's home page of AAM-API, C++ AAM implementation (non-commercial use only).
  • Original Active Appearance Model Open-source Matlab implementation
  • [1] AAMtools: An Active Appearance Modeling Toolbox
  • [2] FaceTracker, free for research purposes only.
  • [3] Open Tracking Library.

Some reading

  • T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graham. Training models of shape from sets of examples. In Proceedings of BMVC’92, pages 266–275, 1992
  • S. C. Mitchell, J. G. Bosch, B. P. F. Lelieveldt, R. J. van der Geest, J. H. C. Reiber, and M. Sonka. 3-d active appearance models: Segmentation of cardiac MR and ultrasound images. IEEE Trans. Med. Imaging, 21(9):1167–1178, 2002
  • T.F. Cootes, G. J. Edwards, and C. J. Taylor. Active appearance models. ECCV, 2:484–498, 1998[pdf]

References

  1. ^ Attention: This template ({{cite doi}}) is deprecated. To cite the publication identified by doi:10.1007/BFb0054760, please use {{cite journal}} (if it was published in a bona fide academic journal, otherwise {{cite report}} with |doi=10.1007/BFb0054760 instead.
  2. ^ Attention: This template ({{cite doi}}) is deprecated. To cite the publication identified by doi:10.1109/34.927467, please use {{cite journal}} (if it was published in a bona fide academic journal, otherwise {{cite report}} with |doi=10.1109/34.927467 instead.