|
|
【答案】应助回帖
★ ★ ★
sina1300841: 金币+3, ★★★很有帮助 2014-08-28 19:10:18
sunshan4379: LS-EPI+1, 感谢应助！ 2014-08-28 19:33:38
Fabric defect image segmentation based on the visual attention mechanism of the wavelet domain
作者:Guan, SQ (Guan, Shengqi)[ 1 ] ; Gao, ZY (Gao, Zhaoyuan)[ 1 ]
TEXTILE RESEARCH JOURNAL
卷: 84
期: 10
页: 1018-1033
DOI: 10.1177/0040517513517964
出版年: JUN 2014
查看期刊信息
摘要
In order to explore the accurate image segmentation of fabric defects, we will introduce the visual attention mechanism of the wavelet domain to the dynamic detection of fabric defects. First of all, feature maps are formed by extracting simple features from a collection image. Secondly, feature maps by multi-layer wavelet decomposition are decomposed into a lot of feature sub-maps of the wavelet domain. On this basis, the center-surround operator among feature sub-maps of the wavelet domain is adopted to build the feature difference sub-maps, which are fused into feature saliency maps through fuse strategy. Finally, the defect interest areas are segmented based on the maximum between-cluster variance method in saliency maps, and the fabric defects through the region growing method are detected in the defect interest areas. Comparing with the wavelet transform algorithm, experimental results show that the proposed method is able to segment the defect information completely, and it has a strong ability to resist noise interference, which can improve the accuracy of defect detection.
关键词
作者关键词:wavelet domain; visual attention mechanism; feature saliency map; image segmentation
KeyWords Plus:INSPECTION
作者信息
通讯作者地址: Guan, SQ (通讯作者)
Xian Polytech Univ, Coll Mech & Elect Engn, 19 South Rd, Xian, Peoples R China.
地址:
[ 1 ] Xian Polytech Univ, Coll Mech & Elect Engn, Xian, Peoples R China
电子邮件地址:sina1300841@163.com
基金资助致谢
基金资助机构
授权号
Scientific Research Program - Shan xi Provincial Education Department
2013JK1083
Doctoral scientific Research - Xi'an Polytechnic University
BS1005
查看基金资助信息
出版商
SAGE PUBLICATIONS LTD, 1 OLIVERS YARD, 55 CITY ROAD, LONDON EC1Y 1SP, ENGLAND
类别 / 分类
研究方向:Materials Science
Web of Science 类别:Materials Science, Textiles
文献信息
文献类型:Article
语种:English
入藏号: WOS:000338014400002
ISSN: 0040-5175
电子 ISSN: 1746-7748
期刊信息
Impact Factor (影响因子): Journal Citation Reports®
其他信息
IDS 号: AJ9FZ
Web of Science 核心合集中的 "引用的参考文献": 22
Web of Science 核心合集中的 "被引频次": 0
引文网络
0 被引频次
22 引用的参考文献
查看 Related Records
查看引证关系图
创建引文跟踪
(数据来自 Web of ScienceTM 核心合集)
全部被引频次计数
0 / 所有数据库
0 / Web of Science 核心合集
0 / BIOSIS Citation Index
0 / 中国科学引文数据库
0 / Data Citation Index
0 / SciELO Citation Index
此记录来自:
Web of ScienceTM 核心合集
建议修正
如果希望提高此记录中数据的质量，请提供修正建议。 |
|
回复此楼