Accurate regression procedures for active appearance models

Patrick Sauer, Tim Cootes, Chris Taylor

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


    Active Appearance Models (AAMs) are widely used to fit shape models to new images. Recently it has been demonstrated that non-linear regression methods and sequences of AAMs can significantly improve performance over the original linear formulation. In this paper we focus on the ability of a model trained on one dataset to generalise to other sets with different conditions. In particular we compare two non-linear, discriminative regression strategies for predicting shape updates, a boosting approach and variants of Random Forest regression. We investigate the use of these regression methods within a sequential model fitting framework, where each stage in the sequence consists of a shape model and a corresponding regression model. The performance of the framework is assessed by both testing on unseen data taken from within the training databases, as well as by investigating the more difficult task of generalising to unrelated datasets. We present results that show that (a) the generalisation performance of the Random Forest is superior to that of the linear or boosted regression procedure and that (b) using a simple feature selection procedure, the Random Forest can be made to be as efficient as the boosting procedure without significant reduction in accuracy. © 2011. The copyright of this document resides with its authors.
    Original languageEnglish
    Title of host publicationBMVC 2011 - Proceedings of the British Machine Vision Conference 2011|BMVC - Proc. Br. Mach. Vis. Conf.
    PublisherBMVA Press
    Publication statusPublished - 2011
    Event2011 22nd British Machine Vision Conference, BMVC 2011 - Dundee
    Duration: 1 Jul 2011 → …


    Conference2011 22nd British Machine Vision Conference, BMVC 2011
    Period1/07/11 → …


    • Active Appearance Model


    Dive into the research topics of 'Accurate regression procedures for active appearance models'. Together they form a unique fingerprint.

    Cite this