edoc

On Compositional Image Alignment, with an Application to Active Appearance Models

Amberg, Brian and Blake, Andrew and Vetter, Thomas. (2009) On Compositional Image Alignment, with an Application to Active Appearance Models. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009 : CVPR 2009 ; 20 - 25 June 2009, Miami [Beach], FL, USA. Piscataway, NJ, 1714 - 1721.

Full text not available from this repository.

Official URL: http://edoc.unibas.ch/dok/A5253835

Downloads: Statistics Overview

Abstract

Efficient and accurate fitting of Active AppearanceModels (AAM) is a key requirement for many applications.The most efficient fitting algorithm today is Inverse CompositionalImage Alignment (ICIA). While ICIA is extremelyfast, it is also known to have a small convergence radius.Convergence is especially bad when training and testingimages differ strongly, as in multi-person AAMs. We describe“forward” compositional image alignment in a consistentframework which also incorporates methods previouslytermed “inverse” compositional, and use it to developtwo novel fitting methods. The first method, CompositionalGradient Descent (CoDe), is approximately fourtimes slower than ICIA, while having a convergence radiuswhich is even larger than that achievable by direct Quasi-Newton descent. An intermediate convergence range withthe same speed as ICIA is achieved by LinCoDe, the secondnew method. The success rate of the novel methods is 10 to20 times higher than that of the original ICIA method.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Computergraphik Bilderkennung (Vetter)
UniBasel Contributors:Vetter, Thomas and Amberg, Brian
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Bibsysno:Link to catalogue
Publisher:IEEE
Note:Publication type according to Uni Basel Research Database: Conference paper
Related URLs:
Identification Number:
Last Modified:24 May 2013 09:09
Deposited On:22 Mar 2012 13:57

Repository Staff Only: item control page