Graphics enhanced version of this site

Automatic Construction of Active Appearance Models
This project is no longer active.

Head: Simon Baker
Contact: Simon Baker

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213

Associated center: VASC
Associated lab/group: Face Group

Image coding is the task of representing a set of images as accurately as possible using a fixed number of parameters. One well known example is the linear coding problem that leads to Principal Components Analysis (PCA). Although optimal in a certain sense, PCA has limited coding power. A large number of parameters are often required to code a set of images accurately. In this project we have developed an algorithm for image coding using Active Appearance Models (AAMs). AAMs are a class of generative non-linear models (although linear in both shape and appearance) which have received a great deal of recent attention in the computer vision literature. Our algorithm can also be interpreted as an automatic algorithm for the (unsupervised) learning of Active Appearance Models.

Name - Title <Email Address>
• Simon Baker - Adjunct Faculty (Adjunct)
• [Home] Iain Matthews - Senior Systems Scientist <iainm@cs.cmu.edu (Currently On Leave)>
• [Home] Jeff Schneider - Assoc. Research Professor <schneide@cs.cmu.edu>

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• Automatic Construction of Active Appearance Models as an Image Coding Problem
  S. Baker, I. Matthews, and J. Schneider
  IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 10, October, 2004, pp. 1380 - 1384. [Abstract]
  Download: pdf [212 KB] copyrighted

• Image Coding with Active Appearance Models
  S. Baker, I. Matthews, and J. Schneider
  tech. report CMU-RI-TR-03-13, Robotics Institute, Carnegie Mellon University, April, 2003. [Abstract]
  Download: pdf [197 KB] copyrighted