Fabric defect detection based on low-rank decomposition with structural constraints

Fabric defect detection is an important part of the fabric production process. To realize the automatic detection of fabric defects, many algorithms based on machine vision technology have been proposed. However, the defect detection algorithms for patterned fabrics are still not mature enough. This paper proposes a fabric defect detection method based on low-rank decomposition with structural constraints. This method extracts the energy features and then constructs a fusion image of the original image and the energy image to highlight the defective regions. By considering the spatial connection of defective pixels, a new low-rank decomposition model is constructed by introducing the structured sparsity-inducing norm. After the low-rank decomposition, we can get the sparse part containing the defective pixels with high spatial continuity. Finally, we obtain the defect detection result by thresholding the sparse part. Experimental comparisons show that our method is superior to several state-of-the-art fabric defect detection methods.

Automated summary

This paper proposes a fabric defect detection method based on low-rank decomposition with structural constraints. The method extracts energy features and constructs a fusion image to highlight defective regions, then builds a new low-rank decomposition model with structured sparsity-inducing norm introduced, and obtain the defect detection result through thresholding the sparse part. Experimental comparisons show the superiority of the proposed method over several state-of-the-art fabric defect detection methods.