Fabric Defect Detection Algorithm for Dense Road and Sparse Road

2018 4th International Conference on Environmental Science and Material Application

生态环境科学;材料科学

Li, Dejun^1 ; Fang, Han^1 ; Zheng, Liwen^1 ; Ji, Changjun^1 ; Yuan, Haoran^1

Wuhan Textile University Electronics and Electrical Engineering, Hubei, Wuhan

430200, China^1

关键词: Defect detection;    Defect detection method;    Fabric defect detection;    Gaussian mixture clustering;    Gaussians;    Hybrid clustering algorithm;    Mean filter;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/252/2/022077/pdf
DOI  :  10.1088/1755-1315/252/2/022077

来源: IOP

【 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.