Search Results

This paper introduces an approach for the segmentation of surface defects, referred to as Efficient Surface Defect Network (ESD-Net). The proposed method uses novel components called the GhostNet Fusion Block (GFB) and the Global Auxiliary Layer (...$\mathrm{}$$\mathrm{}$$\mathrm{}$

Surface defect detection is an important task in the field of manufacturing, and dealing with imbalanced data is a challenge that has been addressed using methods such as anomaly detection and data augmentation. However, optical devices pose a ...

• A Generalized Well Neural Network via Template-Testing comparison is proposed.
• Dual-Attention and Recurrent Residual mechanisms proposed for noise elimination.
• Our approach generalizes to new batches via template collection in FMS.

In recent years, diverse detection methods have been proposed to achieve highly accurate image segmentation. However, low contrast and background noise interference still pose challenges to defect detection. Existing deep learning-based methods ...