This paper proposes a novel template-based correction (TC) method for the defect detection on images with periodic structures. In this method, a fabric image is segmented into lattices according to variation regularity, and correction is applied to reduce the effect of misalignment among lattices. Also, defect-free lattices are chosen for establishing an average template as a uniform reference. Furthermore, the defect detection procedure is composed of two steps, namely, defective lattices locating and defect shape outlining. Defective lattices locating is based on classification for defect-free and defective patterns, which involves an improved E-V method with template-based correction and centralized processing, while defect shape outlining provides pixel-level results by threshold segmentation. In this paper we also present some experiments on fabric defect detection. Experimental results show that the proposed method is effective.

No abstract

To accurately detect defects in patterned fabrics, a novel detection algorithm combining template correction with primitive decomposition (TCPD) method is proposed in this study. First of all, the fabric image is segmented into lattices according to variation regularity. Then, the authors propose an effective anisotropy correction method to reduce the interference of stretching and distortion between lattices. On the basis of the proposed PD method, the corrected lattice is further divided into graphic elements with smaller particle size. The smaller primitives make the boundary of the detection results more accurate. Moreover, a self‐supervised threshold selection strategy is presented, which utilises the defect‐free regions to obtain threshold. Furthermore, this strategy makes each primitive has corresponding criteria for judging defects. Extensive experiments demonstrate that TCPD method achieves 0.8127 true positive rate, 0.3889 positive predictive value and 0.5261 f value in star‐patterned fabrics.

No abstract

Existing block-level defect detection method in patterned fabric causes a large number of false detections due to the lack of edge information. To solve this problem, in this paper, we propose a bilayer Markov random field (BMRF) method for inspecting defects in patterned fabric. First, the proposed method reduces samples of the original fabric image to obtain the constraint layer, which can locate the defective block roughly. Second, we interpolate samples into the image to supplement the local information to improve and optimize the imperfect boundary, to obtain a more detailed data layer. Moreover, this paper proposes a new potential function, which considers the differential characteristics of the image blocks in the same layer and the transition probability between different layers. Finally, this paper utilizes a parameter estimation method based on the expectation maximization to solve the parameters of the BMRF method. The proposed BMRF method is evaluated on databases of star-, box- and dot-patterned fabrics. By comparing the resultant and ground-truth images, the recall rate of the proposed method in the three patterned fabrics is 95.32%, 89.29% and 93.28%, respectively, which is comparable to the existing methods.