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 languageEnglish
    Pages (from-to)1397-1405
    JournalPattern recognition letters
    Volume20
    Issue number11-13
    DOIs
    Publication statusPublished - 1999

    Keywords

    • Parameter estimation
    • Edge detection
    • Remote sensing
    • Likelihood
    • Least squares

    Fingerprint

    Dive into the research topics of 'A comparison of least-squares and Bayesian minimum risk edge parameter estimation'. Together they form a unique fingerprint.

    Cite this