A steel surface defect detection model based on graph neural networks
Authors:
- 17 January 2024
- journal article
- research article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 35 (4) , 046201
Abstract
Steel is an indispensable raw material in the construction industry. To avert catastrophic events such as building collapse, it is essential to detect minute defects on steel surfaces during production. However, this has been a persistent challenge due to the minuscule and dense nature of these defects. To this end, we propose an efficient defect detector called Vision Grapher with Hadamard, which employs a novel attention mechanism (HDmA) to establish local-to-local relationships within an image and integrates global relationships by graph convolution. With the HDmA module, we can not only fuse information under the same field of view, but also under different fields of view, which significantly enhances the richness of the acquired features. In addition, compared to convolutional neural networks, graph neural networks can utilize the contextual information in the image more effectively and resulting in better performance. We evaluate our model on the NEU-DET and GC-10 benchmark datasets, which encompass six and ten types of defects on the surfaces of hot-rolled and cold-rolled steel, and our model achieves a mean average precision of 79.04% and 66.93% on the two datasets, respectively. The results demonstrate that our model significantly improves the accuracy of defect detection compared to existing methods.Keywords
This publication has 27 references indexed in Scilit:
- A multiple feature-maps interaction pyramid network for defect detection of steel surfaceMeasurement Science and Technology, 2023
- Low-pass U-Net: a segmentation method to improve strip steel defect detectionMeasurement Science and Technology, 2022
- Bolt loosening angle detection based on binocular visionMeasurement Science and Technology, 2022
- Rail surface defect detection based on improved Mask R-CNNComputers and Electrical Engineering, 2022
- Surface defect detection of steel strips based on improved YOLOv4Computers and Electrical Engineering, 2022
- Visual inspection of steel surface defects based on domain adaptation and adaptive convolutional neural networkMechanical Systems and Signal Processing, 2021
- An accurate fuzzy measure-based detection method for various types of defects on strip steel surfacesComputers in Industry, 2020
- A simulation-based few samples learning method for surface defect segmentationNeurocomputing, 2020
- SSD: Single Shot MultiBox Detector2016
- Speeded-Up Robust Features (SURF)Computer Vision and Image Understanding, 2008