期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2019
卷号：252
期号：2
页码：1-8
DOI：10.1088/1755-1315/252/2/022077
出版社：IOP Publishing
摘要：In order to improve the results of fabric defect detection with less obvious features such as dense road and sparse road, a Gaussian hybrid clustering algorithm is proposed. Firstly, the image is preprocessed by means of mean filter, and then a Gabor filter and Gaussian mixture clustering algorithm are used to identify the defects of the image to be detected. The experimental results show that compared with other defect detection methods, the method is effective in detecting the defects of fabrics such as dense road and sparse fabric, and has some practical value in defect detection.
