An improved seeded region growing algorithm

被引：251

作者：

Mehnert, A ^{[1
]}

Jackway, P ^{[1
]}

机构：

[1] Univ Queensland, Dept Elect & Comp Engn, Cooperat Res Ctr Sensor Signal & Informat Proc, Brisbane, Qld 4072, Australia

来源：

PATTERN RECOGNITION LETTERS | 1997年 / 18卷 / 10期

关键词：

priority queue; seeded region growing; segmentation; watershed segmentation;

D O I：

10.1016/S0167-8655(97)00131-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recently Adams and Bischof (1994) proposed a novel region growing algorithm for segmenting intensity images. The inputs to the algorithm are the intensity image and a set of seeds - individual points or connected components - that identify the individual regions to be segmented. The algorithm grows these seed regions until all of the image pixels have been assimilated. Unfortunately the algorithm is inherently dependent on the order of pixel processing. This means, for example, that raster order processing and anti-raster order processing do not, in general, lead to the same tessellation. In this paper we propose an improved seeded region growing algorithm that retains the advantages of the Adams and Bischof algorithm fast execution, robust segmentation, and no tuning parameters - but is pixel order independent. (C) 1997 Elsevier Science B.V.

引用

页码：1065 / 1071

页数：7