Analysing error of fit functions for ellipses

被引：45

作者：

Rosin, PL

机构：

[1] Dept. of Comp. Sci. and Info. Syst., Brunel University, Uxbridge, Middlesex UB8 3PH, Kingston Lane

来源：

PATTERN RECOGNITION LETTERS | 1996年 / 17卷 / 14期

关键词：

D O I：

10.1016/S0167-8655(96)00102-X

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We describe several established error of fit (EOF) functions for use in the least square fitting of ellipses, and introduce a further four new EOFs. Four measures are used for assessing the suitability of such EOFs, quantifying their linearity, curvature bias, asymmetry, and overall goodness. These measures enable a better understanding to be gained of the individual merits of the EOF functions.

引用

页码：1461 / 1470

页数：10

共 18 条

[1]

AGIN G, 1981, CMURITR815 CARN U RO

[2]

Albano A., 1974, COMP GRAPH INFO PROC, V3, P23, DOI [10.1016/0146-664X(74)90008-2, DOI 10.1016/0146-664X(74)90008-2CGIPBG0146-664X]

[3] Estimation of ellipse parameters using optimal minimum variance estimator [J].