For fitting an ellipse to a point sequence, ML (maximum likelihood) has been regarded as having the highest accuracy. In this paper, we demonstrate the existence of a "hyperaccurate" method which outperforms ML. This is made possible by error analysis of ML followed by subtraction of high-order bias terms. Since ML nearly achieves the theoretical accuracy bound (the KCR lower bound), the resulting improvement is very small. Nevertheless, our analysis has theoretical significance, illuminating the relationship between ML and the KCR lower bound.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Kenichi KANATANI, "Ellipse Fitting with Hyperaccuracy" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 10, pp. 2653-2660, October 2006, doi: 10.1093/ietisy/e89-d.10.2653.
Abstract: For fitting an ellipse to a point sequence, ML (maximum likelihood) has been regarded as having the highest accuracy. In this paper, we demonstrate the existence of a "hyperaccurate" method which outperforms ML. This is made possible by error analysis of ML followed by subtraction of high-order bias terms. Since ML nearly achieves the theoretical accuracy bound (the KCR lower bound), the resulting improvement is very small. Nevertheless, our analysis has theoretical significance, illuminating the relationship between ML and the KCR lower bound.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.10.2653/_p
Copy
@ARTICLE{e89-d_10_2653,
author={Kenichi KANATANI, },
journal={IEICE TRANSACTIONS on Information},
title={Ellipse Fitting with Hyperaccuracy},
year={2006},
volume={E89-D},
number={10},
pages={2653-2660},
abstract={For fitting an ellipse to a point sequence, ML (maximum likelihood) has been regarded as having the highest accuracy. In this paper, we demonstrate the existence of a "hyperaccurate" method which outperforms ML. This is made possible by error analysis of ML followed by subtraction of high-order bias terms. Since ML nearly achieves the theoretical accuracy bound (the KCR lower bound), the resulting improvement is very small. Nevertheless, our analysis has theoretical significance, illuminating the relationship between ML and the KCR lower bound.},
keywords={},
doi={10.1093/ietisy/e89-d.10.2653},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Ellipse Fitting with Hyperaccuracy
T2 - IEICE TRANSACTIONS on Information
SP - 2653
EP - 2660
AU - Kenichi KANATANI
PY - 2006
DO - 10.1093/ietisy/e89-d.10.2653
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2006
AB - For fitting an ellipse to a point sequence, ML (maximum likelihood) has been regarded as having the highest accuracy. In this paper, we demonstrate the existence of a "hyperaccurate" method which outperforms ML. This is made possible by error analysis of ML followed by subtraction of high-order bias terms. Since ML nearly achieves the theoretical accuracy bound (the KCR lower bound), the resulting improvement is very small. Nevertheless, our analysis has theoretical significance, illuminating the relationship between ML and the KCR lower bound.
ER -