Active appearance models

I developed a basic Matlab implementation of active appearance models. The implementation uses the inverse compositional algorithm for fitting. The implementation was developed as part of the following paper:

  1. 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. [ PDF ]

I used this implementation in hands-on sessions during one of my courses. The second part of this assignment shows how to install and use the active appearance model implementation. Together with the first part of the assignment (which uses PRTools), it also provides a demonstration of how active appearance models may be used to build a very simple facial expression classifier.

All required Matlab files and some example data are in the following ZIP-file (7.5MB). Parts of the code are written in C++; precompiled binaries are available for 32-bit Windows and Mac.


You are free to use, modify, or redistribute the software above in any way you want, but only for non-commercial purposes. The use of the software is at your own risk; the author is not responsible for any damage as a result from errors in the software.