MeDERT: A Metal Surface Defect Detection Model

Metal surface quality control is significant in the production line of metal products. Detecting metal surface defects is challenging due to the various types and morphological patterns. Recent advances have witnessed deep learning-based automated optical inspection systems as a promising solution. This paper presents an enhanced YOLOv4 model for metal surface defect detection (MSDD). Specifically, we integrate three boosting components into the original YOLOv4, including 1) a self-dependent attentive fusion (SAF) block, placed within the model neck, to enhance inter-path and cross-layer feature fusion, 2) a component randomized Mosaic augmentation (CRMA) scheme to strategically discourage an over-transformed image to participate in training, and 3) a perturbation agnostic (PA) label smoothing method to keep the model from making over-confident predictions and thus act as a means of regularization. The proposed method has been validated on a self-developed MSDD dataset. It is shown that each boosting component can lead to an impressive mAP gain, and the final model outperforms the baselines, namely, Faster R-CNN, YOLOv4, YOLOv5, and YOLOX, by 7.85%, 6.51%, 3.76%, and 3.57%, respectively.

Accurate identification of defect morphology and size distribution on metallic surfaces is crucial for manufacturing, particularly in the steel industry where such materials are widely used. This study proposes a novel lightweight architecture based on YOLOv7-tiny to address the challenges of real-time metallic surface defect detection. The original anchor-based detection head is replaced with an anchor-free mechanism to reduce missed detections of defects with extreme aspect ratios, while a logarithmic transformation-based enhancement is introduced to strengthen defect features. The backbone is replaced by the lightweight MobileNetV3-large network to reduce the number of parameters, and an Efficient Multi-Scale Attention (EMA) module is embedded into the bottleneck structure to increase target importance and suppress background interference, especially for small defects. In addition, a bidirectional feature pyramid network with adaptively spatial feature fusion (BAFPN) is integrated as the Head architecture to provide richer semantic information. The improved model was evaluated on the DAGM 2007, NEU-DET, and GC10-DET datasets, which encompass metal surface defects with varying degrees of complexity. The results demonstrate an average increase of 6.24% in mean average precision (mAP) and an inference speed over 90 FPS, confirming both the efficacy and real-time capability of the proposed method.

Computer vision and deep learning techniques are the most emerging technologies in this era. Both of these can greatly raise the rate at which defects on metal surfaces are identified while performing industrial quality checks. The identification of faults over metal surfaces can be viewed as a significant challenge since they are easily impacted by ambient factors including illumination and light reflections. This paper proposes novel metal surface defect detection network called as YOLOv-5s-FRN in response to the problems of ineffective detection brought by the conventional manual inspection system. The proposed system is developed through the integration of a novel architectural module called as Feature Recalibration Network (FRN) to the You Only Look Once-version-5 small network )YOLOv-5s(. In order to extract the global feature information from the provided image, FRN is able to evaluate the interdependencies between the channels. This improves the feature discrimination capability and prediction accuracy of the defect detection system. The incorporation of FRN structure makes YOLOv-5s architecture to selectively enhance the necessary features and discard the unwanted ones. Therefore, the proposed novel method will efficiently detect and classify the metal surface defects such as crazing, patches, inclusions, scratches, pitted surfaces and rolled in scale. North Eastern University surface defect database (NEU-DET) has been used to train and test the proposed architectural model. The suggested system has been compared with alternative models based on several performance matrices such as precision, recall and Mean Average Precision (mAP). It is observed that the proposed YOLOv-5s-FRN architecture provides significant performance improvement than state-of-the-art methods. The proposed system has been provided satisfactory results by means of improvement in mAP and time consumption. The proposed model has delivered value of mAP_0.5 as 98.05% and that of mAP_0.5:0.95 as 89.03%.

Metallic surface defect detection is of great significance in quality control for production. However, this task is very challenging due to the noise disturbance, large appearance variation, and the ambiguous definition of the defect individual. Traditional image processing methods are unable to detect the damaged region effectively and efficiently. In this paper, we propose a new defect detection method, Attention Cascade R- CNN with Mix-NMS (ACRM), to classify and locate defects robustly. Three submodules are developed to achieve this goal: 1) a lightweight attention block is introduced, which can improve the ability in capture global and local feature both in the spatial and channel dimension; 2) we firstly apply the cascade R-CNN to our task, which exploits multiple detectors to sequentially refine the detection result robustly; 3) we introduce a new method named Mix Non-Maximum Suppression (Mix- NMS), which can significantly improve its ability in filtering the redundant detection result in our task. Extensive experiments on a real industrial dataset show that ACRM achieves state-of-the- art results compared to the existing methods, demonstrating the effectiveness and robustness of our detection method.

Aiming at the problems of inefficient detection caused by traditional manual inspection, unclear features and few defect sample in metal surface defect detection, an improved metal surface defect detection technology the siamese network is proposed. The proposed method constructs a deep siamese network with maximum interval, which consists of 4 convolutional layers, 4 max pooling layers and the top fully connected layer to improve the accuracy of the recognition of difficult small targets while ensuring the detection efficiency of the model. The performance of the improved metal surface defect detection technology is compared with other detection methods on the NEU surface defect database. The experimental result verify that the mean average precision of the proposed method is 96.1%, which is higher that of support vector machine, region convolutional neural network, faster region convolutional neural network, single shot multibox detector, you only look once neural network v3.

Small defects on the surface of copper strips have a significant impact on key properties such as electrical conductivity and corrosion resistance, and existing inspection techniques struggle to meet the demand in terms of accuracy and generalisability. Although there have been some studies on metal surface defect detection, there is a relative lack of research on highly reflective copper strips. In this paper, a lightweight and efficient copper strip defect detection algorithm, SC-AttentiveNet, is proposed, aiming to solve the problems of the large model size, slow speed, insufficient accuracy and poor generalisability of existing models. The algorithm is based on ConvNeXt V2, and combines the SCDown module and group normalisation to design the SCGNNet feature extraction network, which significantly reduces the computational overhead while maintaining excellent feature extraction capability. In addition, the algorithm introduces the SPPF-PSA module to enhance the multi-scale feature extraction capability, and constructs a new neck feature fusion network via the HD-CF Fusion Block module, which further enhances the feature diversity and fine granularity. The experimental results show that SC-AttentiveNet has a mAP of 90.11% and 64.14% on the KUST-DET and VOC datasets, respectively, with a parameter count of only 6.365 MB and a computational complexity of 14.442 GFLOPs. Tests on the NEU-DET dataset show that the algorithm has an excellent generalisation performance, with a mAP of 76.41% and a detection speed of 78 FPS, demonstrating a wide range of practical application potential.

A cascaded twin dense network based metallic surface defect detection algorithm SCSEG-Net is proposed to address the problems of low accuracy and difficulty in locating defects in real-time metal surface defect detection. The method incorporates atrous spatial pyramid pooling structure to obtain feature maps with different sampling rates to capture multi-scale information. Meanwhile, in order to enhance the classification accuracy, the low-level texture and boundary features obtained by shallow convolution and the complex high-level feature information obtained by deep convolution are fused during training to better optimize the training parameters through the cascade network. SCSEG-Net can convert defect images into pixel-level prediction masks and quickly acquire real defect classes. The SCSEG-Net algorithm is trained, evaluated and verified on the industry standard steel surface defect data set. The results show that compared with similar algorithms, proposed method can segment the contour of steel surface defects more accurately and complete the classification with an <italic>F</italic>₁-score of 97.8% and a recall rate of 98.81%.

CV Gemilang Kencana is a company engaged in the manufacturing and processing industry of carica sweets which was established on October 10, 2013. The carica fruit itself is a fruit that grows in the highlands of Wonosobo. From the production of carica sweets, there are several problems during the production process, including defects in packaging products such as slanted labels, inappropriate product weight, damaged/leaky packaging cups, with a total product defect of 474 cups with the most defects on February 29, 2023. from product defects that have been described, therefore quality control is needed to reduce product defects, namely by using the seven tools method in quality control. The control chart table shows the most defects, namely on the 29th with a total of 43 cups of defects while the highest level of disability is on the 7th with a middle limit value of 0.0079, an upper limit of 0.012692, and a lower limit of 0.003108. The histogram graph shows the highest defect, namely the damaged / leaky packaging cup, after that the product weight defect does not match and the lowest is the slanted label. In the pareto diagram through processing, a pareto diagram is made with the most dominant result of defects, namely damaged/leaking cup packaging with a value of 47.68%. Based on the scatter diagram, which involves two variables, namely the variable number of production and total product defects. Based on the scatter diagram, it can be seen that the shape of the distribution has a positive correlation or relationship between the amount of production and product defects. Based on fishbone analysis, the causes of product defects are from several factors, namely machine, human, environmental, and methods factors so that companies take preventive or corrective actions to minimize defects during the production process.

Surface defects in industrial production are complex and diverse. Therefore, deep learning-based defect detection models must consistently adapt to newly emerging defect categories. The trained models generally suffer from catastrophic forgetting as they learn new defect categories. To address this issue, we propose a selective distillation for incremental defect detection (SD-IDD) model based on GFLv1. Specifically, three selective distillation strategies are proposed, including high-confidence classification distillation, dual-stage cascaded regression distillation, and Intersection over Union (IoU)-driven difficulty-aware feature distillation. The high-confidence classification distillation aims to preserve critical discriminative knowledge of old categories within semantic confusion regions of the classification head, reducing interference from low-value regions. Dual-stage cascaded regression distillation focuses on high-quality anchors through geometric prior coarse filtering and statistical fine filtering, utilizing IoU-weighted KL divergence distillation loss to accurately transfer localization knowledge. IoU-driven difficulty-aware feature distillation adaptively allocates distillation resources, prioritizing features of high-difficulty targets. These selective distillation strategies significantly mitigate catastrophic forgetting while enhancing the detection accuracy of new classes, without requiring access to old training samples. Experimental results demonstrate that SD-IDD achieves superior performance, with mAP_old of 58.2% and 99.3%, mAP_new of 69.0% and 97.3%, and mAP_all of 63.6% and 98.3% on the NEU-DET and DeepPCB datasets, respectively, surpassing existing incremental detection methods.

The detection of metal surface defects is crucial in the field of industrial production. However, in practical applications, challenges such as ambiguous defect directions, large scale differences, and strong background interference are often encountered. This paper proposes an improved multi-scale fine-grained object detection framework based on YOLOv11, referred to as “DA-YOLO.” Firstly, the 3D attention module (3DAM) was used to enhance the model’s ability to model spatial direction features and improve the model’s ability to perceive fine-grained structures. Secondly, a feature enhancement module (AMFEM) employing multi-scale convolution and a spatial-channel attention mechanism was constructed, significantly boosting the model’s recognition accuracy for multi-scale targets and blurry boundary defects. Furthermore, an intersection and union ratio Aware Joint Loss function (IoU-Aware joint loss, IAJ-Loss) was proposed and designed, which further enhanced the quality perception ability and stability of the model in complex detection scenarios. The experimental results show that the DA-YOLO model improved mAP@0.5 by 5.42% and 4.05% respectively on the GC10-DET and NEU-DET datasets compared to the baseline YOLOv11 model, demonstrating superior defect detection performance.

To address the challenges of low localization accuracy, weak feature discrimination, and real-time constraints in small-scale metallic surface defect detection, this study proposes a novel detection framework named FF-MDE (fine-grained multi-branch diversified encoder). The proposed model enhances detection capability through three key modules: a direction-aware multi-branch convolutional block (BBDES) that strengthens orientation-sensitive feature extraction via re-parameterization; a multi-scale fusion network (MFFN) incorporating a location-offset heterogeneous kernel selection strategy and a channel cross-embedding mechanism to align cross-resolution features and expand receptive fields adaptively; and a lightweight attention-guided up-sampling that improves fine-detail recovery while suppressing irrelevant responses. A large number of experiments on the NEU-DET and GC10-DET datasets show that FF-MDE has achieved excellent performance. The indicators of mAP50 are 70.3 and 57.9% respectively, which are 4.1 and 3.3% higher than the benchmark model and 7.6 and 6.5% higher on average than the existing methods. Moreover, the real-time inference speed of this network exceeds 60 FPS, providing a powerful and deployable solution for high-precision defect detection in industrial vision inspection systems.

Enhanced Detection of Glass Insulator Defects Using Improved Generative Modeling and Faster RCNN

Adverse weather conditions such as haze, rain, and snow degrade images captured by unmanned aerial vehicles (UAVs) during transmission line inspections and severely affect the detection of corrosion defects in transmission line fittings. To address this challenge, we propose LARNet-SAP-YOLOv11, a unified end-to-end model that integrates lightweight image restoration and defect detection. The proposed model comprises LARNet, a lightweight all-in-one image restoration network, and SAP-YOLOv11, an enhanced object detector based on YOLOv11.LARNet is built upon the DehazeFormer architecture and introduces a Triplet Attention Block (TAB) to improve adaptability to various weather degradations. SAP-YOLOv11 enhances the baseline YOLOv11n by incorporating a Shallow Robust Feature Downsampling (SRFD) module, an Adaptive Fine-Grained Channel Attention (AFGCAttention) mechanism, and a Pixel-level Cross-Attention Feature Fusion (PCAFFusion) module, significantly improving corrosion area perception. Experimental results show that LARNet achieves an average PSNR of 30.43 dB and SSIM of 0.951 across different conditions. For defect detection, SAP-YOLOv11 improves the mAP@50 by 2.1% compared to the original YOLOv11n. When jointly applied, LARNet-SAP-YOLOv11 achieves an mAP@50 of 88.6%, outperforming the baseline YOLOv11n by 12.1% in challenging weather conditions. This unified model offers an efficient and reliable solution for UAV-based intelligent inspection of transmission lines under diverse environmental conditions.

Solenoid connectors play important role in electronic stability system design, with the features of small size, low cost, fast response time and high reliability. The main production process challenge for solenoid connectors is the accurate detection of defects, which is closely related to safe driving. Both faultless and defective products have similar color and shape at the defect location, making proper inspection challenging. To address these issues, we proposed a defect detection model called PO-YOLOv5 to achieve accurate defect detection for solenoid connectors. First, an additional prediction head was added to enable the model to acquire more semantic information to detect larger-scale defective features. Second, we introduced dynamic convolution to learn complementary connections between the four dimensions of the convolution kernel by utilizing its multidimensional attention mechanism. Replacing conventional convolution with dynamic convolution enhances the detection accuracy of the model and reduces the inference time. Finally, we validated PO-YOLOv5 versus the state-of-the-art object detection methods on the same solenoid connectors dataset. Experiments revealed that our proposed approach exhibited higher accuracy. The mAP (mean Average Precision) result of PO-YOLOv5 was found to be about 90.1%. Compared with the original YOLOv5, PO-YOLOv5 exhibited improved precision by about 3%.

Uncertain network data envelopment analysis with undesirable outputs to evaluate the efficiency of electricity power production and distribution processes