Detection of Scratch Defects on Metal Surfaces Based on MSDD-UNet
Open Access
- 15 August 2024
- journal article
- research article
- Published by MDPI AG in Electronics
- Vol. 13 (16) , 3241
Abstract
In this work, we enhanced the U-shaped network and proposed a method for detecting scratches on metal surfaces based on the Metal Surface Defect Detection U-Net (MSDD-UNet). Initially, we integrated a downsampling approach using a Space-To-Depth module and a lightweight channel attention module to address the loss of contextual information in feature maps that results from multiple convolution and pooling operations. Building on this, we developed an improved attention module that utilizes image frequency decomposition and cross-channel self-attention mechanisms, as well as the strengths of convolutional encoders and self-attention blocks. Additionally, this attention module was integrated into the skip connections between the encoder and decoder. The purpose was to capture dense contextual information, highlight small and fine target areas, and assist in localizing micro and fine scratch defects. In response to the severe foreground–background class imbalance in scratch images, a hybrid loss function combining focal loss and loss was put forward to train the model for precise scratch segmentation. Finally, experiments were conducted on two surface defect datasets. The results reveal that our proposed method is more advantageous than other state-of-the-art scratch segmentation methods.
Keywords
This publication has 32 references indexed in Scilit:
- Segmentation of void defects in X-ray images of chip solder joints based on PCB-DeepLabV3 algorithmScientific Reports, 2024
- Enhancing automated inspection in metal industries: zero-shot segmentation of surface defects using bounding box promptsMeasurement Science and Technology, 2024
- Edge devices-oriented surface defect segmentation by GhostNet Fusion Block and Global Auxiliary LayerJournal of Real-Time Image Processing, 2023
- Semi-supervised transfer learning-based automatic weld defect detection and visual inspectionEngineering Structures, 2023
- Automatic segmentation of tunnel lining defects based on multiscale attention and context information enhancementConstruction and Building Materials, 2023
- Semantic Segmentation of Remote Sensing Image Based on Regional Self-Attention MechanismIEEE Geoscience and Remote Sensing Letters, 2021
- Surface defect detection of aluminum alloy welds with 3D depth image and 2D gray imageThe International Journal of Advanced Manufacturing Technology, 2020
- EGNet: Edge Guidance Network for Salient Object Detection2019
- An End‐to‐End Steel Strip Surface Defects Recognition System Based on Convolutional Neural NetworksSteel Research International, 2016
- A noise robust method based on completed local binary patterns for hot-rolled steel strip surface defectsApplied Surface Science, 2013