For fitting Active Appearance Models (AAMs) to low-resolution images, the authors built a multi-resolution AAM and show that the best fitting performance is obtained when the model resolution is slightly higher than the facial image resolution.
(AAMs) represent the shape and appearance of an object via two low-dimensional subspaces, one for shape and one for appearance. AAMs for facial images are currently receiving considerable attention from the vision community; however, most existing work focuses on fitting AAMs to high-quality facial images. For many applications, effectively fitting an AAM to low-resolution facial images is of critical importance. This paper addresses this challenge from two aspects. On the modeling side, the authors propose an iterative AAM enhancement scheme, which not only results in increased fitting speed, but also improves the fitting robustness. Experimental results using both indoor video and outdoor surveillance video are presented. (Publisher abstract provided)
Downloads
Similar Publications
- Media Contact and Posttraumatic Stress in Employees of New York City Area Businesses after the September 11 Attacks
- Targeting youth at risk for gang involvement: Validation of a gang risk assessment to support individualized secondary prevention
- Robust Methods and Statistical Thinking for “Big Data” Science and Surveys