AAM (Active Appearance Model) Building module. AAM statistically builds a joint shape and texture appearance model, which has been widely applied in face tracking, lip reading, audio-visual HCI, etc.
Be the first to post a text review of AAMBuilding. Rate and review a project by clicking thumbs up or thumbs down in the right column.
wxWidget based GUI is afforded for AAM building, including both the Basic AAM building and Inverse Compositional Image Alignment (ICIA) AAM building. Since it's finished in Toronto, I call it a Toronto version.
Simplified aam building with only shape and texture model build. This version is an improved version with several bugs fixed. What's more, it's more C++/ISO style than the 1st version. Besides, it removes basic aam fitting and inverse compositional image alignment fitting pre-computation. AAM fitting demos could be found at http://www.visionopen.com .
The 1st version of aambuilding is a 2D AAM building open source. It produces all the parameters needed by using CMU Piecewise Affine Image Align algorithm, say, Hessian Matrix, steepest descent images, etc. In order to successfully build aambuilding, OpenCV and boost are required. Excluding the IO part in the code, only OpenCV is required.
Be the first person to add a text review.
Copyright © 2009 Geeknet, Inc. All rights reserved. Terms of Use
Thanks for your rating!
Would you also like to write a review?