Research on the Detection of Steel Plate Defects Based on SimAM and Twin-NMF Transfer
Open Access
- 8 September 2024
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 12 (17) , 2782
Abstract
Pulsed eddy current thermography can detect surface or subsurface defects in steel, but in the process of combining deep learning, it is expensive and inefficient to build a complete sample of defects due to the complexity of the actual industrial environment. Consequently, this study proposes a transfer learning method based on Twin-NMF and combines it with the SimAM attention mechanism to enhance the detection accuracy of the target domain task. First, to address the domain differences between the target domain task and the source domain samples, this study introduces a Twin-NMF transfer method. This approach reconstructs the feature space of both the source and target domains using twin non-negative matrix factorization and employs cosine similarity to measure the correlation between the features of these two domains. Secondly, this study integrates a parameter-free SimAM into the neck of the YOLOv8 model to enhance its capabilities in extracting and classifying steel surface defects, as well as to alleviate the precision collapse phenomenon associated with multi-scale defect recognition. The experimental results show that the proposed Twin-NMF model with SimAM improves the detection accuracy of steel surface defects. Taking NEU-DET and GC10-DET as source domains, respectively, in the ECTI dataset, mAP@0.5 reaches 99.3% and 99.2%, and the detection accuracy reaches 98% and 98.5%.Keywords
Funding Information
- Yunnan Provincial Major Science and Technology Project (202102AD080002)
This publication has 23 references indexed in Scilit:
- EFS-YOLO: a lightweight network based on steel strip surface defect detectionMeasurement Science and Technology, 2024
- Steel surface defect detection algorithm in complex background scenariosMeasurement, 2024
- A domain adaptation YOLOv5 model for industrial defect inspectionMeasurement, 2023
- New cosine similarity and distance measures for Fermatean fuzzy sets and TOPSIS approachKnowledge and Information Systems, 2022
- A Review of Yolo Algorithm DevelopmentsProcedia Computer Science, 2022
- Infrared machine vision and infrared thermography with deep learning: A reviewInfrared Physics & Technology, 2021
- Infrared Thermal Imaging-Based Crack Detection Using Deep LearningIEEE Access, 2019
- An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical FeaturesIEEE Transactions on Instrumentation and Measurement, 2019
- Improving visibility of rear surface cracks during inductive thermography of metal plates using AutoencoderInfrared Physics & Technology, 2018
- Learning the parts of objects by non-negative matrix factorizationNature, 1999