[1]王培珍,陈维南.一种基于融合技术的图像边缘检测方案[J].东南大学学报(自然科学版),2001,31(6):78-80.[doi:10.3969/j.issn.1001-0505.2001.06.019]
　Wang Peizhen,Chen Weinan.A New Edge Detection Technique Based on Data Fusion[J].Journal of Southeast University (Natural Science Edition),2001,31(6):78-80.[doi:10.3969/j.issn.1001-0505.2001.06.019]
点击复制

一种基于融合技术的图像边缘检测方案()
分享到：

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
31
期数:
2001年第6期
页码:
78-80
栏目:
计算机科学与工程
出版日期:
2001-11-20

文章信息/Info

Title:
A New Edge Detection Technique Based on Data Fusion
作者:
王培珍1;  陈维南2
1 安徽工业大学工业自动化系,马鞍山 243002; 2 东南大学自动化研究所,南京 210096
Author(s):
Wang Peizhen1;  Chen Weinan2
1 Department of Industrial Automation, Anhui Industrial University, Ma’anshan 243002, China; 2 Automatic Research Institute, Southeast University, Nanjing 210096, China)
关键词:
信息融合;  梯度算子;  边缘检测
Keywords:
data fusion;  derivative operator;  edge detection
分类号:
TP391.41
DOI:
10.3969/j.issn.1001-0505.2001.06.019
摘要:
从信息融合的角度出发,直接运用运算量较小的梯度算子,在分析各种简单梯度算子的互补特性的基础上,将它们有机地融合,其中融合的权重自适应地调整.针对梯度算子在检测边缘时对像素点具有扩散作用及边缘定位不准确等问题,本文采用了松弛标记的技术将融合后的边缘进行了细化,在计算量不显著增加的前提下,提高了边缘检测的质量.
Abstract:
From the view of data fusion, the compensation characters of simple operators are discussed, and the data from the simple operators are properly fused, the weights of fusion can adaptively be gained. In order to determine whether a putative edge point is a true edge point and to find its exact position, a relaxation labeling technique is also implemented to thin the edge. Thus, the quality of the edge can be improved and the time of calculation is limited.

参考文献/References:

[1] Chan Minghua,Lee D.Residual analysis for feature detection.IEEE Trans on Pattern Analysis and Machine Intelligence,1991,13(1):30～40
[2] 王润生.图像理解.长沙:国防科技大学出版社,1995.47～57
[3] 罗希平,田捷,诸葛婴,等.图像分割方法综述.模式识别与人工智能,1999,12(3):300～312
[4] Bhandarkar S M,Zhang Y Q,Potter W D.An edge detection technique using genetic algorithm-based optimization.Pattern Recognition,1994,27(9):1159～1180
[5] Hancock E R.Resolving edge-line ambiguities using probabilistic relaxation.Computer Vision & Pattern Recognition,1993,93:300～306

备注/Memo

备注/Memo:
作者简介:王培珍,女,1966年生,硕士,副教授.
基金项目:安徽省教育厅科研计划资助项目(2000jl176).
更新日期/Last Update: 2001-11-20