A rule-based approach for robust clump splitting

被引：88

作者：

Kumar, S

Ong, SH

Ranganath, S

Ong, TC

Chew, FT

机构：

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

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

[3] Natl Univ Singapore, Dept Biol Sci, Singapore 119260, Singapore

来源：

PATTERN RECOGNITION | 2006年 / 39卷 / 06期

关键词：

concavity analysis; overlapping objects; segmentation; clump splitting;

D O I：

10.1016/j.patcog.2005.11.014

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents a robust rule-based approach for the splitting of binary clumps that are formed by objects of diverse shapes and sizes. First, the deepest boundary pixels, i.e., the concavity pixels in a clump, are detected using a fast and accurate scheme. Next, concavity-based rules are applied to generate the candidate split lines that join pairs of concavity pixels. A figure of merit is used to determine the best split line from the set of candidate lines. Experimental results show that the proposed approach is robust and accurate. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：1088 / 1098

页数：11

共 23 条

[11] Recursive splitting of active contours in multiple clump segmentation [J].