文章基本信息

标题：Fast Noise Tolerant Vision-based Defect Detection on Flight Deck Surface from Non-destructive Testing Images
本地全文：下载
作者：Kwang Baek Kim ; Doo Heon Song
期刊名称：International Journal of Software Engineering and Its Applications
印刷版ISSN：1738-9984
出版年度：2015
卷号：9
期号：3
页码：117-122
DOI：10.14257/ijseia.2015.9.3.12
出版社：SERSC
摘要：Automatic defect detection of a product or a transportation structure is always an important topic of research due to the subjectivity of human visual inspection. Like concrete structure, flight deck surface has low brightness contrast in detecting defects. Unlike concrete structure or a bridge, the defect of a flight deck is not represented as crack lines but as the region of abnormality. Thus in this paper, we propose a method to locate such defective areas automatically by computer vision. The proposed method applies a series of image processing techniques and strong against noise as verified in the experiment.
关键词：Flight Deck Surface; Structure Health Monitoring; Defect Detection; ; Laplacian Filter; Noise Removal