Steel Surface Defect Classification Research Articles

Hybrid-DC: A Hybrid Framework Using ResNet-50 and Vision Transformer for Steel Surface Defect Classification in the Rolling Process

This study introduces Hybrid-DC, a hybrid deep-learning model integrating ResNet-50 and Vision Transformer (ViT) for high-accuracy steel surface defect classification. Hybrid-DC leverages ResNet-50 for efficient feature extraction at both low and high levels and utilizes ViT’s global context learning to enhance classification precision. A unique hybrid attention layer and an attention fusion mechanism enable Hybrid-DC to adapt to the complex, variable patterns typical of steel surface defects. Experimental evaluations demonstrate that Hybrid-DC achieves substantial accuracy improvements and significantly reduced loss compared to traditional models like MobileNetV2 and ResNet, with a validation accuracy reaching 0.9944. The results suggest that this model, characterized by rapid convergence and stable learning, can be applied for real-time quality control in steel manufacturing and other high-precision industries, enhancing automated defect detection efficiency.

Maximizing Steel Slice Defect Detection: Integrating ResNet101 Deep Features with SVM via Bayesian Optimization

Accurate detection of defects on steel surfaces is crucial for maintaining quality standards in steel production. This paper addresses the challenge of classifying steel sheets into distinct defect categories by presenting a robust method that leverages deep learning and advanced optimization techniques. We propose a novel approach that utilizes the ResNet101 model to extract deep features, which are then classified using a support vector machine (SVM). To enhance the SVM's performance, Bayesian optimization is employed for hyperparameter tuning. Our method is validated using the "Severstal: Steel Defect Detection" dataset from Kaggle, achieving a validation accuracy of 89.1% and a test accuracy of 90.6%, with a classification error of 0.10934. Additionally, the area under the curve (AUC) for each class exceeds 0.95 in both the validation and test sets, demonstrating excellent discriminatory power. Further evaluation on the DAGM dataset achieved flawless results, with an accuracy of 100%, AUC of 1, sensitivity of 100%, specificity of 100%, precision of 100%, MCC of 100%, F1 score of 1, and kappa of 100%. On the NEU dataset, our method achieved an accuracy of 97.92%, sensitivity of 97.92%, specificity of 99.58%, precision of 98.06%, F1 score of 0.9791, MCC of 97.55%, and kappa of 92.50%. These results demonstrate the robustness and adaptability of the proposed method, offering an efficient and reliable solution for automating steel defect detection and surface defect classification in industrial applications.

ODNet: A High Real-Time Network Using Orthogonal Decomposition for Few-Shot Strip Steel Surface Defect Classification.

Strip steel plays a crucial role in modern industrial production, where enhancing the accuracy and real-time capabilities of surface defect classification is essential. However, acquiring and annotating defect samples for training deep learning models are challenging, further complicated by the presence of redundant information in these samples. These issues hinder the classification of strip steel surface defects. To address these challenges, this paper introduces a high real-time network, ODNet (Orthogonal Decomposition Network), designed for few-shot strip steel surface defect classification. ODNet utilizes ResNet as its backbone and incorporates orthogonal decomposition technology to reduce the feature redundancies. Furthermore, it integrates skip connection to preserve essential correlation information in the samples, preventing excessive elimination. The model optimizes the parameter efficiency by employing Euclidean distance as the classifier. The orthogonal decomposition not only helps reduce redundant image information but also ensures compatibility with the Euclidean distance requirement for orthogonal input. Extensive experiments conducted on the FSC-20 benchmark demonstrate that ODNet achieves superior real-time performance, accuracy, and generalization compared to alternative methods, effectively addressing the challenges of few-shot strip steel surface defect classification.

Hot rolled steel surface defect detection and classification using an automatic ensemble approach

This study introduces an ensemble-based Deep Neural Network (DNN) model for detecting defects on steel surfaces. The method suggested in this study classifies steel surface conditions into six possible fault categories, namely, crazing, inclusion, rolled in, pitted surface, scratches, and patches. The images undergo preprocessing and extraction of features in spatial and frequency domains using image segmentation techniques such as grey level difference method (GLDM), fast Fourier Transform (FFT), grey level co-occurrence matrix (GLCM), texture analysis and discrete wavelet transform (DWT). The ensembling of image features into a fused feature pool is carried out after the preprocessing of input images that are provided as input to a light-weight neural network model for training and testing. The performance of the model is comprehensively evaluated via an ablation study both before and after ensembling. In addition, the model capability is effectively analyzed using receiver operating characteristics (ROC) curve, confusion matrix from which classification accuracy of the model could be obtained and other parameters including precision and f1-score. It was observed that the proposed deep learning network presents phenomenally high accuracy of 99.72% for detection and classification of steel surface faults. This result was found to be superior when compared with the performance of the same neural network over each feature type individually. This study also compares the classification results of the model built based on the ensembled feature set with the results of various other classification approaches available in literature. The ensemble-based model could potentially be integrated into existing inspection systems for real-time, efficient and robust condition monitoring of steel surfaces.

Development of Hybrid Models Based on AlexNet and Machine Learning Approaches for Strip Steel Surface Defect Classification

Development of Hybrid Models Based on AlexNet and Machine Learning Approaches for Strip Steel Surface Defect Classification

Spiking ViT: spiking neural networks with transformer—attention for steel surface defect classification

Spiking ViT: spiking neural networks with transformer—attention for steel surface defect classification

Research on steel surface defect classification method based on deep learning

Surface defects on steel, arising from factors like steel composition and manufacturing techniques, pose significant challenges to industrial production. Efficient and precise detection of these defects is crucial for enhancing production efficiency and product quality. In accordance with these requisites, this paper elects to undertake the detection task predicated on the you only look once (YOLO) algorithm. In this study, we propose a novel approach for surface flaw identification based on the YOLOv5 algorithm, called YOLOv5-KBS. This method integrates attention mechanism and weighted Bidirectional Feature Pyramid Network (BiFPN) into YOLOv5 architecture. Our method addresses issues of background interference and defect size variability in images. Experimental results show that the YOLOv5-KBS model achieves a notable 4.2% increase in mean Average Precision (mAP) and reaches a detection speed of 70 Frames Per Second (FPS), outperforming the baseline model. These findings underscore the effectiveness and potential applications of our proposed method in industrial settings.

A Novel Feature Extraction Method Based on Legendre Multi-Wavelet Transform and Auto-Encoder for Steel Surface Defect Classification

A Novel Feature Extraction Method Based on Legendre Multi-Wavelet Transform and Auto-Encoder for Steel Surface Defect Classification

Low-Resolution Steel Surface Defects Classification Network Based on Autocorrelation Semantic Enhancement

Aiming at the problems of low-resolution steel surface defects imaging, such as defect type confusion, feature blurring, and low classification accuracy, this paper proposes an autocorrelation semantic enhancement network (ASENet) for the classification of steel surface defects. It mainly consists of a backbone network and an autocorrelation semantic enhancement module (ASE), in which the autocorrelation semantic enhancement module consists of three main learnable modules: the CS attention module, the autocorrelation computation module, and the contextual feature awareness module. Specifically, we first use the backbone network to extract the basic features of the image and then use the designed CS attention module to enhance the basic features. In addition, to capture different aspects of semantic objects, we use the autocorrelation module to compute the correlation between neighborhoods and contextualize the basic and augmented features to enhance the recognizability of the features. Experimental results show that our method produces significant results, and the classification accuracy reaches 96.24% on the NEU-CLS-64 dataset. Compared with ViT-B/16, Swin_t, ResNet50, Mobilenet_v3_small, Densenet121, Efficientnet_b2, and baseline, the accuracy is 9.43%, 5.15%, 4.87%, 3.34%, 3.28%, 3.01%, and 2.72% higher, respectively.

Research on a Classification Method for Strip Steel Surface Defects Based on Knowledge Distillation and a Self-Adaptive Residual Shrinkage Network

Different types of surface defects will occur during the production of strip steel. To ensure production quality, it is essential to classify these defects. Our research indicates that two main problems exist in the existing strip steel surface defect classification methods: (1) they cannot solve the problem of unbalanced data using few-shot in reality, (2) they cannot meet the requirement of online real-time classification. To solve the aforementioned problems, a relational knowledge distillation self-adaptive residual shrinkage network (RKD-SARSN) is presented in this work. First, the data enhancement strategy of Cycle GAN defective sample migration is designed. Second, the self-adaptive residual shrinkage network (SARSN) is intended as the backbone network for feature extraction. An adaptive loss function based on accuracy and geometric mean (Gmean) is proposed to solve the problem of unbalanced samples. Finally, a relational knowledge distillation model (RKD) is proposed, and the functions of GUI operation interface encapsulation are designed by combining image processing technology. SARSN is used as a teacher model, its generalization performance is transferred to the lightweight network ResNet34, and it is conveniently deployed as a student model. The results show that the proposed method can improve the deployment efficiency of the model and ensure the real-time performance of the classification algorithms. It is superior to other mainstream algorithms for fine-grained images with unbalanced data classification.

Multi-Scale Lightweight Neural Network for Steel Surface Defect Detection

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.

Steel surface defect classification approach using an All-optical Neuron-based SNN with attention mechanism

PurposeThe purpose of this study is to propose a new method for the end-to-end classification of steel surface defects.Design/methodology/approachThis study proposes an AM-AoN-SNN algorithm, which combines an attention mechanism (AM) with an All-optical Neuron-based spiking neural network (AoN-SNN). The AM enhances network learning and extracts defective features, while the AoN-SNN predicts both the labels of the defects and the final labels of the images. Compared to the conventional Leaky-Integrated and Fire SNN, the AoN-SNN has improved the activation of neurons.FindingsThe experimental findings on Northeast University (NEU)-CLS demonstrate that the proposed neural network detection approach outperforms other methods. Furthermore, the network’s effectiveness was tested, and the results indicate that the proposed method can achieve high detection accuracy and strong anti-interference capabilities while maintaining a basic structure.Originality/valueThis study introduces a novel approach to classifying steel surface defects using a combination of a shallow AoN-SNN and a hybrid AM with different network architectures. The proposed method is the first study of SNN networks applied to this task.

Multi-level semantic information guided image generation for few-shot steel surface defect classification

Surface defect classification is one of key points in the field of steel manufacturing. It remains challenging primarily due to the rare occurrence of defect samples and the similarity between different defects. In this paper, a multi-level semantic method based on residual adversarial learning with Wasserstein divergence is proposed to realize sample augmentation and automatic classification of various defects simultaneously. Firstly, the residual module is introduced into model structure of adversarial learning to optimize the network structure and effectively improve the quality of samples generated by model. By substituting original classification layer with multiple convolution layers in the network framework, the feature extraction capability of model is further strengthened, enhancing the classification performance of model. Secondly, in order to better capture different semantic information, we design a multi-level semantic extractor to extract rich and diverse semantic features from real-world images to efficiently guide sample generation. In addition, the Wasserstein divergence is introduced into the loss function to effectively solve the problem of unstable network training. Finally, high-quality defect samples can be generated through adversarial learning, effectively expanding the limited training samples for defect classification. The experimental results substantiate that our proposed method can not only generate high-quality defect samples, but also accurately achieve the classification of defect detection samples.

Steel surface defect detection based on global context block

Steel is the most basic raw material in China’s industrial production, which plays a great role in promoting China’s industrialization process. Therefore, it is of great significance to detect defective steel and the surface quality of steel. In order to further improve the detection accuracy of steel surface defects, this paper proposes a steel surface defect detection algorithm based on global context block. In this paper, a global context module is introduced based on the UNet++ network model to achieve accurate segmentation and classification of complex steel surface defects. The results show that the improved UNet++ network model achieves a dice coefficient of 94.67% on the steel surface defect dataset provided by the Kaggle competition platform. Compared with semantic segmentation models such as UNet, LinkNet, and UNet++, the segmentation effect is more accurate. Therefore, the deep learning model based on the improved UNet++ can learn more semantic features from industrial steel images, so as to obtain more accurate steel defect information. This method can be a big help for real-world applications like defect detection in industrial images.

A Shallow Neural Network for Recognition of Strip Steel Surface Defects Based on Attention Mechanism

This research proposes an efficient strip steel surface defect classification model (ASNet) based on convolutional neural network (CNN), which can run in real time on commonly used serial computing platforms. We only used a very shallow CNN structure to extract features of the defect images, and an attention layer which makes the model ignore some irrelevant noise and obtain an effective description of the defects is designed. In addition, a nonlinear perceptron is added to the top of the model to recognize defects based on the extracted features. On the strip steel surface defect image dataset NEU-CLS, our model achieves an average classification accuracy of 99.9%, while the number of parameters of the model is only 0.041 M and the computational complexity of the model is 98.1 M FLOPs. It can meet the requirements of real-time operation and large-scale deployment on a common serial computing platform with high recognition accuracy.

A multi-scale pooling convolutional neural network for accurate steel surface defects classification.

Surface defect detection is an important technique to realize product quality inspection. In this study, we develop an innovative multi-scale pooling convolutional neural network to accomplish high-accuracy steel surface defect classification. The model was built based on SqueezeNet, and experiments were carried out on the NEU noise-free and noisy testing set. Class activation map visualization proves that the multi-scale pooling model can accurately capture the defect location at multiple scales, and the defect feature information at different scales can complement and reinforce each other to obtain more robust results. Through T-SNE visualization analysis, it is found that the classification results of this model have large inter-class distance and small intra-class distance, indicating that this model has high reliability and strong generalization ability. In addition, the model is small in size (3MB) and runs at up to 130FPS on an NVIDIA 1080Ti GPU, making it suitable for applications with high real-time requirements.

FaNet: Feature-aware network for few shot classification of strip steel surface defects

Accurate classification of surface defects is one of the most important factors in achieving quality inspection for strip steel. Most existing methods are based on fully-supervised learning, which requires a large number of labeled training data samples. In the manufacturing process, collecting defective samples is time-consuming and laborious. So it is very difficult to train a fully supervised model based on few labeled samples. In this paper, we propose a feature-aware network (FaNet) for a few shot defect classification, which can effectively distinguish new classes with a small number of labeled samples. In our proposed FaNet, we use ResNet12 as our baseline. The feature-attention convolution module (FAC) is applied to extract the comprehensive feature information from the base classes, as well as to fuse semantic information by capturing the long-range feature relationships between the upper and lower layers. Meanwhile, during the test phase, an online feature-enhance integration module (FEI) is adopted to average the noise from the support set and query set defect images, further enhancing image features among the different tasks. In addition, we construct a large-scale strip steel surface defects few shot classification dataset (FSC-20) with 20 different types. Experimental results show that the proposed method achieves the best performance compared to state-of-the-art methods for the 5-way 1-shot and 5-way 5-shot tasks. The dataset and code are available at: https://github.com/VDT-2048/FSC-20.

Research on Steel Surface Defect Detection Algorithm Based on Improved Deep Learning

With the development of industrial economy, more and more enterprises use machine vision and artificial intelligence to replace manual detection. Therefore, the research of steel surface defect detection based on artificial intelligence is of great significance to promote the rapid development of intelligent factory and intelligent manufacturing system. In this paper, Yolov5 deep learning algorithm is used to build a classification model of steel surface defects to realize the classification and detection of steel surface defects. At the same time, on the basis of Yolov5, combined with the attention mechanism, the backbone network is improved to further improve the classification model of steel surface defects. The experiment shows that the Recall and mAP of improved Yolov5 perform better on the steel surface defect data set. Compared with Yolov5, the number of C3CA-Yolov5 parameters decreased by 13.02%, and the size of pt files decreased by 12.72%; the number of C3ECA-Yolov5 parameters decreased by 13.36%, and the size of pt files decreased by 13.22%.

Automated steel surface defect detection and classification using a new deep learning-based approach

Automated steel surface defect detection and classification using a new deep learning-based approach

NSLNet: An improved deep learning model for steel surface defect classification utilizing small training datasets

Manufacturing industries contemplate integrating computer vision and artificial intelligence into shop floor operations, such as steel surface defect identification, to realize smart manufacturing goals. However, inadequate annotated training datasets and reduced prediction abilities with image perturbations restrict the practical implementation. This paper introduces NSLNet framework utilizing ImageNet as a feature-extractor combined with adversarial training in the extracted feature space through Neural Structure Learning to address these barriers. The experiments on public (NEU) and synthetically generated datasets (ENEU) showed that the NSLNet could learn with few training samples maintaining resilience against image perturbations outperforming conventional models significantly and nearest deep learning competitors marginally.