Detection and characterization of junctions in a 2D image

被引：12

作者：

Bergevin, R ^{[1
]}

Bubel, A ^{[1
]}

机构：

[1] Univ Laval, Dept Elect & Comp Engn, Comp Vis & Syst Lab, Quebec City, PQ G1K 7P4, Canada

来源：

COMPUTER VISION AND IMAGE UNDERSTANDING | 2004年 / 93卷 / 03期

基金：

加拿大自然科学与工程研究理事会;

关键词：

junction detection; branch characterization; interest points; vector quantization; topological criteria; edge grouping;

D O I：

10.1016/j.cviu.2003.10.003

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A new junction characterization and validation method is proposed. Junction branches of volumetric objects are extracted at interest points in a 2D image, using a topologically constrained grouping process. This is followed by structural validation and position refinement of extracted junctions. An interesting feature of the proposed method is that all types of junctions are described uniformly and extracted using the same generic process. For instance, the size of the interest regions is kept constant despite local variations in contour density and curvature. Validation rate of real junctions is high and most false hypotheses are properly rejected. An experimental evaluation illustrates the capabilities of the proposed method in demanding situations. (C) 2003 Elsevier Inc. All rights reserved.

引用

页码：288 / 309

页数：22