Defect Data Augmentation Method for Robust Image-based Product Inspection

In this paper, we develop a model for detecting defects in fabric products based on an object segmentation algorithm, including a novel image data augmentation method to enhance the robustness. First, a vision-based inspection system is established to collect image data of the fabric products. The three types of fabric defects, such as a hole, a stain, and a dyeing defect, are considered. To enhance defect detection accuracy and robustness, a novel image data augmentation method, referred to as the defect-area cut-mix, is proposed. In this method, the shapes that are the same as each defect are extracted using the masks, and then they are added to non-defective fabric images. Second, an ensemble process is implemented by combining the results of two models, one with high sensitivity in defect diagnosis and the other with lower sensitivity. The results demonstrated that the model trained on the augmented dataset exhibits improved metrics such as intersection over union and classification accuracy in defect detection on the test dataset.