Deformable Patterned Fabric Defect Detection With Fisher Criterion-Based Deep Learning

In this paper, we propose a discriminative representation for patterned fabric defect detection when only limited negative samples are available. Fabric patches are efficiently classified into defectless and defective categories by Fisher criterion-based stacked denoising autoencoders (FCSDA). First, fabric images are divided into patches of the same size, and both defective and defectless samples are utilized to train FCSDA. Second, test patches are classified through FCSDA into defective and defectless categories. Finally, the residual between the reconstructed image and defective patch is calculated, and the defect is located by thresholding. Experimental results demonstrate the effectiveness of the proposed scheme in the defect detection for periodic patterned fabric and more complex jacquard warp-knitted fabric. Note to Practitioners-Fabric defect detection is an important measure for quality control in a textile factory. The author has conducted a research on defect detection for plain warp-knitted fabric and developed an automatic defect inspection system for textile factories. Based on this previous research, this paper focuses on defect detection for more complex fabric. Deep learning is introduced into this field for the first time. The proposed method provides a new idea for practitioners working on defect detection. In the future, we would like to explore how to integrate this method into an automatic defect inspection system.