International Journal of Computer Vision

, Volume 60, Issue 2, pp 135–164 | Cite as

Active Appearance Models Revisited

  • Iain Matthews
  • Simon Baker
Article

Abstract

Active Appearance Models (AAMs) and the closely related concepts of Morphable Models and Active Blobs are generative models of a certain visual phenomenon. Although linear in both shape and appearance, overall, AAMs are nonlinear parametric models in terms of the pixel intensities. Fitting an AAM to an image consists of minimising the error between the input image and the closest model instance; i.e. solving a nonlinear optimisation problem. We propose an efficient fitting algorithm for AAMs based on the inverse compositional image alignment algorithm. We show that the effects of appearance variation during fitting can be precomputed (“projected out”) using this algorithm and how it can be extended to include a global shape normalising warp, typically a 2D similarity transformation. We evaluate our algorithm to determine which of its novel aspects improve AAM fitting performance.

Active Appearance Models AAMs Active Blobs Morphable Models fitting efficiency Gauss-Newton gradient descent inverse compositional image alignment 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

APp.5273357_1.mpg
Supplementary material
APp.5273357_2.mpg
Supplementary material
APp.5273357_3.mpg
Supplementary material

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Iain Matthews
    • 1
  • Simon Baker
    • 1
  1. 1.The Robotics InstituteCarnegie Mellon UniversityUSA

Personalised recommendations