A comparison of least-squares and Bayesian minimum risk edge parameter estimation

Mulder, Nanno J. and Abkar, Ali A. (1999) A comparison of least-squares and Bayesian minimum risk edge parameter estimation. Pattern Recognition Letters, 20 (11-13). pp. 1397-1405. ISSN 0167-8655

PDF
Restricted to UT campus only: Request a copy
215Kb

Abstract:	The problem considered here is to compare two methods for finding a common boundary between two objects with two unknown geometric parameters, such as edge position and edge orientation. We compare two model-based approaches: the least squares and the minimum Bayesian risk method. An expression is derived for the expected error as a function of radiometry. This shows that the least squares method emphasises outliers. The outliers increase the error in parameter estimation. In an experiment with edge parameter estimation, the negative aspects of least squares are detectable.
Item Type:	Article
Copyright:	© 1999 Elsevier
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Robotics and Mechatronics (CE)
Link to this item:	http://purl.utwente.nl/publications/73951
Official URL:	http://dx.doi.org/10.1016/S0167-8655(99)00111-7
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 112349