Arc-based evaluation and detection of ellipses

被引：30

作者：

Qiao, Yu

Ong, S. H.

机构：

[1] Agcy Sci Technol & Res, Biomed Imaging Lab, Singapore 138671, Singapore

[2] Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 119260, Singapore

[3] Natl Univ Singapore, Div Bioengn, Singapore 119260, Singapore

来源：

PATTERN RECOGNITION | 2007年 / 40卷 / 07期

关键词：

ellipse verification; ellipse detection; elliptic arc; model-based distance; connectivity; angular connectivity;

D O I：

10.1016/j.patcog.2006.10.009

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose the use of elliptic arcs as a reliable criterion for ellipse evaluation and reconstruction. A technique based on pixel connectivity is developed for detecting the endpoints and subtended angles of elliptic arcs. Model-based distance and angular connectivity are introduced for quick and meaningful estimation of elliptic arcs. An iterative algorithm for multiple-ellipse fitting based on arc detection is presented. Experimental results confirm the robustness and accuracy of the algorithm for the fitting of multiple overlapping ellipses. (c) 2006 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：1990 / 2003

页数：14

共 21 条

[1]

BENTZVI D, 1989, P 5 INT C IM AN PROC, P152

[2] A DATA-DRIVEN INTERMEDIATE LEVEL FEATURE-EXTRACTION ALGORITHM [J].