Anchor selection based deep learning two stage fabric defect localization

Abstract

Localizing and classifying fabric defects is a crucial step in the quality control process used in the production of textiles. Recently, fabric defect classification and detection have made use of deep learning approaches based on anchor selection. But due to in effectiveness in anchor selection, the computational overhead and localization error are higher in these solutions. As a solution to this problem, this work proposes a two-stage improvised anchor selection deep learning technique. In first stage, quaternion fourier transform frequency domain analysis along with super pixel segmentation is done over the fabric image to select probable defect regions. In the second stage deep learning based regression along with super pixel segment comparison is done over the probable defect regions localize and categorize the defect. Due to effectiveness in selection of probable defect regions and categorization of regions, the defect localization accuracy is increased at a comparative low computational overhead in the proposed two stage improvise anchor selection deep learning technique. Testing against the irish longitudinal study on ageing (TILDA) fabric defect detection dataset, the proposed solution is found to provide 1.2% higher fabric defect localization accuracy at a 3% lower computation overhead compared to most recent existing works.