Learning robust objective functions for model fitting in image understanding applications

Matthias Wimmer, Freek Stulp, Stephan Tschechne, Bernd Radig

Research output: Contribution to conferencePaperpeer-review

21 Scopus citations

Abstract

Model-based methods in computer vision have proven to be a good approach for compressing the large amount of information in images. Fitting algorithms search for those parameters of the model that optimise the objective function given a certain image. Although fitting algorithms have been the subject of intensive research and evaluation, the objective function is usually designed ad hoc and heuristically with much implicit domain-dependent knowledge. This paper formulates a set of requirements that robust objective functions should satisfy. Furthermore, we propose a novel approach that learns the objective function from training images that have been annotated with the preferred model parameters. The requirements are automatically enforced during the learning phase, which yields generally applicable objective functions. We compare the performance of our approach to other approaches. For this purpose, we propose a set of indicators that evaluate how well an objective function meets the stated requirements.

Original languageEnglish
Pages1159-1168
Number of pages10
StatePublished - 2006
Event2006 17th British Machine Vision Conference, BMVC 2006 - Edinburgh, United Kingdom
Duration: 4 Sep 20067 Sep 2006

Conference

Conference2006 17th British Machine Vision Conference, BMVC 2006
Country/TerritoryUnited Kingdom
CityEdinburgh
Period4/09/067/09/06

Fingerprint

Dive into the research topics of 'Learning robust objective functions for model fitting in image understanding applications'. Together they form a unique fingerprint.

Cite this