Learning Active Appearance Models from Image Sequences

Authors: Jason Saragih and Roland Göcke

Presented by Jason Saragih at the HCSNet Workshop on the Use of Vision in HCI VisHCI2006, Canberra, Australia, 1-3 November 2006


One of the major drawbacks of the Active Appearance Model (AAM) is that it requires a training set of pseudo-dense correspondences. Most methods for automatic correspondence finding involve a groupwise model building process which optimises over all images in the training sequence simultaneously. In this work, we pose the problem of correspondence finding as an adaptive template tracking process. We investigate the utility of this approach on an audio-visual (AV) speech database and show that it can give reasonable results.

Download (860kB, PDF)

Bibtex Entry

AUTHOR = {J. Saragih and R. Goecke},
TITLE = {{Learning Active Appearance Models from Image Sequences}},
BOOKTITLE = {{Proceedings of the HCSNet Workshop on the Use of Vision in HCI VisHCI2006}},
ADDRESS = {Canberra, Australia},
SERIES = {Conferences in Research and Practice in Information Technology},
VOLUME = 56,
PAGES = {51--60},
MONTH = nov,
YEAR = 2006}

[Homepage] [Research] [Publications]

(c) Roland Göcke
Last modified: Wed May 09 14:05:14 AUS Eastern Standard Time 2007