Combining local and global shape models for deformable object matching

Philip A. Tresadern, Harish Bhaskar, Steve A. Adeshina, Chris J. Taylor, Tim F. Cootes

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We describe a method for modelling and locating deformable objects using a combination of global and local shape models. An object is represented as a set of patches together with a geometric model of their relative positions. The geometry is modelled with a global pose and linear shape model, together with a Markov Random Field (MRF) model of local displacements from the global model. Matching to a new image involves an alternating scheme in which an MRF inference technique selects the best candidates for each point, which are then used to update the parameters of the global pose and shape model. A cascade of increasingly complex models is used to achieve robust matching to new images. We explore the effect of model parameters on system performance and show that the proposed method achieves better accuracy than other widely used methods on standard datasets. © 2009. The copyright of this document resides with its authors.
    Original languageEnglish
    Title of host publicationBritish Machine Vision Conference, BMVC 2009 - Proceedings|Br. Mach. Vis. Conf., BMVC - Proc.
    PublisherBMVA Press
    DOIs
    Publication statusPublished - 2009
    Event2009 20th British Machine Vision Conference, BMVC 2009 - London
    Duration: 1 Jul 2009 → …

    Conference

    Conference2009 20th British Machine Vision Conference, BMVC 2009
    CityLondon
    Period1/07/09 → …

    Keywords

    • Faces
    • Model Matching

    Fingerprint

    Dive into the research topics of 'Combining local and global shape models for deformable object matching'. Together they form a unique fingerprint.

    Cite this