Region growing: A new approach

被引：354

作者：

Hojjatoleslami, SA ^{[1
]}

Kittler, J ^{[1
]}

机构：

[1] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford GU2 5XH, Surrey, England

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 1998年 / 7卷 / 07期

关键词：

D O I：

10.1109/83.701170

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 region growing method for finding the boundaries of blobs is presented. A unique feature of the method is that at each step, at most one pixel exhibits the required properties to join the region. The method uses two novel discontinuity measures, average contrast and peripheral contrast, to control the growing process.

引用

页码：1079 / 1084

页数：6

共 13 条

[1] Class of constrained clustering algorithms for object boundary extraction
Abrantes, AJ
Marques, JS
[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1996, 5 (11) : 1507 - 1521
[2] SEEDED REGION GROWING
ADAMS, R
BISCHOF, L
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1994, 16 (06) : 641 - 647
[3] Ballard D.H., 1982, Computer Vision
[4] IMAGE SEGMENTATION TECHNIQUES
HARALICK, RM
SHAPIRO, LG
[J]. COMPUTER VISION GRAPHICS AND IMAGE PROCESSING, 1985, 29 (01): : 100 - 132
[5] HOJJATOLESLAMI SA, 1995, IEE 5 INT C IM PROC, P139
[6] Jiang H., 1993, Systems and Computers in Japan, V24, P28
[7] LOCALLY SENSITIVE METHOD FOR CLUSTER-ANALYSIS
KITTLER, J
[J]. PATTERN RECOGNITION, 1976, 8 (01) : 23 - 33
[8] NAJIMAN L, 1996, IEEE T PATTERN MACHI, V18, P1163
[9] A REVIEW ON IMAGE SEGMENTATION TECHNIQUES
PAL, NR
PAL, SK
[J]. PATTERN RECOGNITION, 1993, 26 (09) : 1277 - 1294
[10] INTEGRATING REGION GROWING AND EDGE-DETECTION
PAVLIDIS, T
LIOW, YT
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (03) : 225 - 233

← 1 2 →