PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Object recognition using geometric properties and a variant of boosting
Martin Antenreiter and Peter Auer
In: 1st Austrian Cognitive Vision Workshop OCG-Schriftenreihe , 186 . (2005) Oesterreichische Computer Gesellschaft , Wien, Austria , pp. 43-50. ISBN 3-85403-186-6

Abstract

This paper describes an approach for learning object descriptions as combinations of simple features using labeled still images. The contribution of this paper is a new method for constructing geometric relations of simple features with the LPBoost algorithm. A full search for relevant geometric relations between simple features is rather impossible because of the computation time required. We therefore use a greedy search strategy. In comparison, our recognition results are better than results using related approaches.

EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:1610
Deposited By:Martin Antenreiter
Deposited On:28 November 2005