Fabric Defect Image Segmentation Method Based on The Combination of Canny and Morphology

In order to filter out the background noise while retaining the characteristics of the defects, this paper combines Canny and morphological processing to segment the fabric defects. After image preprocessing, our improved algorithm is used to detect the defects, and considering the characteristics of the fabric image, when using the morphology closed operation, the cross-shaped kernel and the rectangular kernel are combined to separate the defect and the background. The defect area obtained by the improved algorithm is compared with the defect area obtained by the expert manual marking method. The defect area obtained by the improved algorithm has a proportion of more than 85%, which proves that our proposed algorithm is effective in the field of image segmentation.