A coarse-to-fine method for glass fiber fabric surface defect detection. Issue 3 (4th March 2021)

• Record Type: Journal Article
• Authors: Jing, Junfeng; Zheng, Min; Zhang, Huanhuan; Zhuo, Dong
• Is Part Of: Journal of the Textile Institute. Volume 112:Issue 3(2021)
• Page Start: 388
• Page End: 397
• Publication Date: 2021-03-04
• Subjects: Fiber glass fabrics -- defect detection -- sorting operation -- convolution operation; Textile industry -- Periodicals; Textile fabrics -- Periodicals; Periodicals; 677.005
• DOI: 10.1080/00405000.2020.1758454
• Languages: English
• ISSNs: 0040-5000

Abstract

Abstract: Surface defect detection of glass fiber fabrics has always been one of the research hotspots in the field of textile industry. The main reasons are the complexity of defect types, the interference of false defects and the random arrangement of gray values. In this paper, a surface defect detection method for glass fiber fabric based on coarse-to-fine strategy is presented. Firstly, the grayscale values of the images to be detected are arranged in the ascending order by row and column respectively, and the corresponding grayscale value curves are drawn. According to the coordinate defect position obtained by the curve, the defect candidate area of glass fiber fabric image is roughly segmented. Then, the convolution kernel is constructed to convolute the coarse segmented image. Finally, the OTSU algorithm is used to locate defects. Qualitative and quantitative experiments show that the detection results of the proposed method are better than Gabor method, FT method and Zhang's method. The average detection accuracy of the proposed method can reach 98.8%, which can meet the actual needs of enterprises.