This tool comprises a basic Matlab implementation of active appearance models, as well as an extension of active appearance models that has a more powerful texture models (it models texture using a mixture of PCA model). The implementation uses the inverse compositional algorithm for fitting. The implementation was developed as part of the following paper:
• L.J.P. van der Maaten and E.A. Hendriks. Capturing Appearance Variation in Active Appearance Models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 34-41, 2010.
I used this implementation in hands-on sessions during one of my courses. The code comes with a set of assignment that shows how to install and use the active appearance model implementation. The assignments also demonstrate how active appearance models may be used to build a simple facial expression classifier.
- year: 2011
- month: Mar
- url: http://homepage.tudelft.nl/19j49/Active_appearance_models.html
- main_author: Laurens van der Maaten
- license: For non-commercial use only
- platform: Matlab (all platforms)
Categories: face-analysis; face-synthesis