Boundary detection using mathematical morphology

被引：16

作者：

Yang, J ^{[1
]}

Li, XB ^{[1
]}

机构：

[1] UNIV ALBERTA,DEPT COMP SCI,EDMONTON,AB T6G 2H1,CANADA

来源：

PATTERN RECOGNITION LETTERS | 1995年 / 16卷 / 12期

关键词：

shape information; boundary detection; dynamic mathematical morphology; roll dilation;

D O I：

10.1016/0167-8655(95)00082-1

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Object boundaries contain important shape information in an image. Mathematical morphology is shape sensitive and can be used in boundary detection. In this paper, we propose dynamic mathematical morphology which only operates on the parts of interest in an image and reacts to certain characteristics of the region. The next position of the structuring element is dynamically selected at each step of the operation. The technique is used to detect object boundaries and has produced encouraging results.

引用

页码：1277 / 1286

页数：10

共 9 条

[1]

Ballard DH, 1982, COMPUTER VISION

[2]

COOPER J, 1993, IEEE T PATTERN ANAL, V8, P823

[3]

DAVE RN, 1992, 1992 P IEEE INT C FU, P127

[4]

DUBUISSON MP, 1993, 1993 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION : PROCEEDINGS, P471

[5] IMAGE-ANALYSIS USING MATHEMATICAL MORPHOLOGY [J].

HARALICK, RM ;

STERNBERG, SR ;

ZHUANG, XH .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1987, 9 (04) :532-550

[6]

HUANG DCD, 1991, 3RD P INT C TOOLS AR, P254

[7]

KASS M, 1987, 1ST P INT C COMP VIS, P259

[8]

MANJUNATH BS, 1991, 1991 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, P358

[9]

WILLIAMS DJ, 1992, CVGIP-IMAG UNDERSTAN, P14

← 1 →