Robust active appearance models with iteratively rescaled Kernels

M. G. Roberts, T. F. Cootes, J. E. Adams

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

    Abstract

    Active appearance models (AAMs) are widely used to fit statistical models of shape and appearance to images, and have applications in segmentation, tracking, and classification of structures. A limitation of AAMs is that they are not robust to a large set of gross outliers. Using a robust kernel can help, but there are potential problems in determining the correct kernel scaling parameters. We describe a method of learning two sets of scaling parameters during AAM training: a coarse and a fine scale set. Our algorithm initially applies the coarse scale and then uses a form of deterministic annealing to reduce to the fine outlier rejection scaling as the AAM converges. The algorithm was assessed on two large datasets consisting of a set of faces, and a medical dataset of images of the spine. A significant improvement in accuracy and robustness was observed in cases which were difficult for a standard AAM.
    Original languageEnglish
    Title of host publicationBMVC 2007 - Proceedings of the British Machine Vision Conference 2007|BMVC - Proc. Br. Mach. Vis. Conf.
    PublisherBMVA Press
    DOIs
    Publication statusPublished - 2007
    Event2007 18th British Machine Vision Conference, BMVC 2007 - Warwick
    Duration: 1 Jul 2007 → …

    Conference

    Conference2007 18th British Machine Vision Conference, BMVC 2007
    CityWarwick
    Period1/07/07 → …

    Fingerprint

    Dive into the research topics of 'Robust active appearance models with iteratively rescaled Kernels'. Together they form a unique fingerprint.

    Cite this