liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Flexible Template and Model Matching Using Intensity
University College London.
University College London.
2005 (English)In: Proceedings of Digital Image Computing: Techniques and Applications, / [ed] Brian C. Lovell, Anthony J. Maeder, Terry Caelli, and Sebastien Ourselin, IEEE , 2005, 438--447 p.Conference paper (Refereed)
Abstract [en]

Intensity-based image and template matching is briefly reviewed with particular emphasis on the problems that arise when flexible templates or models are used. Use of such models and templates may often lead to a very small basin of attraction in the error landscape surrounding the desired solution and also to spurious, trivial solutions. Simple examples are studied in order to illustrate these problems which may arise from photometric transformations of the template, from geometric transforms of it or from internal parameters of the template that allow similar types of variation. It is pointed out that these problems are, from a probabilistic point of view, exacerbated by a failure to model the whole image, i.e. both the foreground object or template and the image background, which a Bayesian approach strictly requires. Some general remarks are made about the form of the error landscape to be expected in object recognition applications and suggestions made as to optimisation techniques that may prove effective in locating a correct match. These suggestions are illustrated by a preliminary example.

Place, publisher, year, edition, pages
IEEE , 2005. 438--447 p.
National Category
Engineering and Technology
URN: urn:nbn:se:liu:diva-52179DOI: 10.1109/DICTA.2005.1578162ISBN: 0-7695-2774-4OAI: diva2:280086
DICTA 2005, Digital Image Computing: Techniques and Applications, December 6-8, 2005 Cairns Convention Centre, Brisbane, Australia
Available from: 2010-09-21 Created: 2009-12-08 Last updated: 2010-09-21Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Zografos, Vasileios
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 69 hits
ReferencesLink to record
Permanent link

Direct link