Affiliation:
1. School of Intelligent Science & Engineering, Shenyang University, Shenyang 110044, China
2. School of Information Engineering, Shenyang University, Shenyang 110044, China
Abstract
Defect classification is an important aspect of steel surface defect detection. Traditional approaches for steel surface defect classification employ convolutional neural networks (CNNs) to improve accuracy, typically by increasing network depth and parameter count. However, this approach overlooks the significant memory overhead of large models, and the incremental gains in accuracy diminish as the number of parameters increases. To address these issues, a multi-scale lightweight neural network model (MM) is proposed. The MM model, with a fusion encoding module as its core, constructs a multi-scale neural network by utilizing the Gaussian difference pyramid. This approach enhances the network’s ability to capture patterns at different resolutions while achieving superior model accuracy and efficiency. Experimental results on a dataset from a hot-rolled strip steel plant demonstrate that the MM network achieves a classification accuracy of 98.06% in defect classification tasks. Compared to networks such as ResNet-50, ResNet-101, VGG, AlexNet, MobileNetV2, and MobileNetV3, the MM model not only reduces the number of model parameters and compresses model size but also achieves better classification accuracy.
Subject
Materials Chemistry,Surfaces, Coatings and Films,Surfaces and Interfaces
Reference34 articles.
1. He, Y., Wen, X., and Xu, J. (2022). A Semi-Supervised Inspection Approach of Textured Surface Defects under Limited Labeled Samples. Coatings, 12.
2. An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features;He;IEEE Trans. Instrum. Meas.,2020
3. Liu, Y., Yuan, Y., Balta, C., and Liu, J. (2020). A Light-Weight Deep-Learning Model with Multi-Scale Features for Steel Surface Defect Classification. Materials, 13.
4. Classification of Surface Defects on Steel Strip Images using Convolution Neural Network and Support Vector Machine;Boudiaf;J. Fail. Anal. Prev.,2022
5. Nizan, O., and Tal, A. (2023). k-NNN: Nearest Neighbors of Neighbors for Anomaly Detection. arXiv.
Cited by
14 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献