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

Nanno Mulder, Ali-Akbar Abkar

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)

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.
Original languageUndefined
Pages (from-to)1397-1405
JournalPattern recognition letters
Volume1999
Issue number20
DOIs
Publication statusPublished - 1999

Keywords

  • METIS-112349
  • IR-73951
  • Parameter estimation
  • Edge detection
  • Remote sensing
  • Likelihood
  • Least squares

Cite this

Mulder, Nanno ; Abkar, Ali-Akbar. / A comparison of least-squares and Bayesian minimum risk edge parameter estimation. In: Pattern recognition letters. 1999 ; Vol. 1999, No. 20. pp. 1397-1405.
@article{ced138c439e448c1ae9590e61a3f5259,
title = "A comparison of least-squares and Bayesian minimum risk edge parameter estimation",
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.",
keywords = "METIS-112349, IR-73951, Parameter estimation, Edge detection, Remote sensing, Likelihood, Least squares",
author = "Nanno Mulder and Ali-Akbar Abkar",
year = "1999",
doi = "10.1016/S0167-8655(99)00111-7",
language = "Undefined",
volume = "1999",
pages = "1397--1405",
journal = "Pattern recognition letters",
issn = "0167-8655",
publisher = "Elsevier",
number = "20",

}

A comparison of least-squares and Bayesian minimum risk edge parameter estimation. / Mulder, Nanno; Abkar, Ali-Akbar.

In: Pattern recognition letters, Vol. 1999, No. 20, 1999, p. 1397-1405.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A comparison of least-squares and Bayesian minimum risk edge parameter estimation

AU - Mulder, Nanno

AU - Abkar, Ali-Akbar

PY - 1999

Y1 - 1999

N2 - 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.

AB - 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.

KW - METIS-112349

KW - IR-73951

KW - Parameter estimation

KW - Edge detection

KW - Remote sensing

KW - Likelihood

KW - Least squares

U2 - 10.1016/S0167-8655(99)00111-7

DO - 10.1016/S0167-8655(99)00111-7

M3 - Article

VL - 1999

SP - 1397

EP - 1405

JO - Pattern recognition letters

JF - Pattern recognition letters

SN - 0167-8655

IS - 20

ER -