Iterative Error Bound Minimisation for AAM Alignment

Jason Sarigih, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

22 Citations (Scopus)
1 Downloads (Pure)

Abstract

The active appearance model (AAM) is a powerful generative method used for modelling and segmenting de-formable visual objects. Linear iterative methods have proven to be an efficient alignment method for the AAM when initialisation is close to the optimum. However, current methods are plagued with the requirement to adapt these linear update models to the problem at hand when the class of visual object being modelled exhibits large variations in shape and texture. In this paper, we present a new precomputed parameter update scheme which is designed to reduce the error bound over the model parameters at every iteration. Compared to traditional update methods, our method boasts significant improvements in both convergence frequency and accuracy for complex visual objects whilst maintaining efficiency
Original languageEnglish
Title of host publicationProceedings of the 18th international conference on pattern recognition
EditorsYuan Yan Tang, Patrick Wang
Place of PublicationAustralia
PublisherIEEE
Pages1192-1195
Number of pages4
ISBN (Print)0-7695-2521-0
DOIs
Publication statusPublished - 2006
Externally publishedYes
EventICPR2006 - , Hong Kong
Duration: 20 Aug 200624 Aug 2006

Conference

ConferenceICPR2006
CountryHong Kong
Period20/08/0624/08/06

Fingerprint Dive into the research topics of 'Iterative Error Bound Minimisation for AAM Alignment'. Together they form a unique fingerprint.

  • Cite this

    Sarigih, J., & Goecke, R. (2006). Iterative Error Bound Minimisation for AAM Alignment. In Y. Y. Tang, & P. Wang (Eds.), Proceedings of the 18th international conference on pattern recognition (pp. 1192-1195). IEEE. https://doi.org/10.1109/ICPR.2006.730