Surface Defect Recognition Research Articles

YOLO-LFPD: A Lightweight Method for Strip Surface Defect Detection.

Strip steel surface defect recognition research has important research significance in industrial production. Aiming at the problems of defect feature extraction, slow detection speed, and insufficient datasets, YOLOv5 is improved on the basis of YOLOv5, and the YOLO-LFPD (lightweight fine particle detection) model is proposed. By introducing the RepVGG (Re-param VGG) module, the robustness of the model is enhanced, and the expressive ability of the model is improved. FasterNet is used to replace the backbone network, which ensures accuracy and accelerates the inference speed, making the model more suitable for real-time monitoring. The use of pruning, a GA genetic algorithm with OTA loss function, further reduces the model size while better learning the strip steel defect feature information, thus improving the generalisation ability and accuracy of the model. The experimental results show that the introduction of the RepVGG module and the use of FasterNet can well improve the model performance, with a reduction of 48% in the number of parameters, a reduction of 13% in the number of GFLOPs, an inference time of 77% of the original, and an optimal accuracy compared with the network models in recent years. The experimental results on the NEU-DET dataset show that the accuracy of YOLO-LFPD is improved by 3% to 81.2%, which is better than other models, and provides new ideas and references for the lightweight strip steel surface defect detection scenarios and application deployment.

A standalone and portable imaging detection system with embedded computing for automated defect inspection of microfluidic devices

The existing methods for defect detection in PDMS microfluidic chips typically involve complex image recognition algorithms or manual inspection and still lack efficiency and reliability. Although some automatic defect detection methods have been proposed in recent years, most of them still rely on external computation systems to deploy. To address these challenges, we propose an independent portable defect detection system with embedded computing for microfluidic devices. This portable system is completely self-contained, integrating an image acquisition module, a control panel module, a power module, and an embedded computing control module to realize chip detection, processing, and result display functions. Experimental results show that the system can effectively detect most of the commonly seen defects in PDMS-based microfluidic chips, proving to be more efficient and reliable than manual inspection. With the control of the embedded system, two detection methods: template matching (based on comparison with standard samples) and automatic defect detection (based on surface defect recognition) were used to identify defects in PDMS-based microfluidic chips. The proposed system can automatically inspect and analyze chips without the need for external laboratory support and can provide a promising solution for future microfluidic chip manufacturing and operation.

DG2GAN: improving defect recognition performance with generated defect image sample

This article aims to improve the deep-learning-based surface defect recognition. In actual manufacturing processes, there are issues such as data imbalance, insufficient diversity, and poor quality of augmented data in the collected image data for product defect recognition. A novel defect generation method with multiple loss functions, DG2GAN is presented in this paper. This method employs cycle consistency loss to generate defect images from a large number of defect-free images, overcoming the issue of imbalanced original training data. DJS optimized discriminator loss is introduced in the added discriminator to encourage the generation of diverse defect images. Furthermore, to maintain diversity in generated images while improving image quality, a new DG2 adversarial loss is proposed with the aim of generating high-quality and diverse images. The experiments demonstrated that DG2GAN produces defect images of higher quality and greater diversity compared with other advanced generation methods. Using the DG2GAN method to augment defect data in the CrackForest and MVTec datasets, the defect recognition accuracy increased from 86.9 to 94.6%, and the precision improved from 59.8 to 80.2%. The experimental results show that using the proposed defect generation method can obtain sample images with high quality and diversity and employ this method for data augmentation significantly enhances surface defect recognition technology.

Steel surface defect recognition using classifier combination

Steel surface defect recognition using classifier combination

Metallic surface defect recognition network based on global feature aggregation and dual context decoupled head

Surface defect detection is a crucial inspection phase in ensuring industrial product quality and reliability, particularly in the context of metallic manufacturing components. While existing deep learning-based approaches have demonstrated some effectiveness, the design of certain network structures still lacks consideration for industrial scenarios. This paper proposed a complex metallic surface defect detection neural network which incorporates two innovatively designed modules along with other targeted enhancements. Firstly, the spatial pyramid pooling (SPP) structure is redesigned for richer global-local information fusion. A global feature fusion and redistribution module (GFAR) is designed to fully leverage feature information across different scales. With the combination of a novel global positional attention mechanism (GPAM), GFAR is capable of distinguishing defects from complex backgrounds. Moreover, the asymmetric convolution blocks (ACB) are employed to process the final features, enhancing the representational capacity for intricate defect shapes. Subsequently, the detection head is decoupled in both spatial and task domains to addresses the problems posed by inconsistent focus between classification and regression tasks. Finally, the reassignment of loss functions is undertaken for each respective task to enhance their alignment with the specific requirements of the defect detection task. Extensive ablation experiments are conducted on two steel surface defect datasets, NEU-DET and GC10-DET, to demonstrate the effectiveness of each module. The defects detection accuracy of our method respectively reaches 80.9 % and 84.8 % for the two datasets, which outperforms the majority of state-of-the-art detection neural networks.

A method of particleboard surface defect detection and recognition based on deep learning

ABSTRACT Particleboard is a material for furniture and other wooden industrial products, directly impacting the service life of the final product. In this study, an innovative dual-attention mechanism, the Dense Connection Idea (DC-DACB), which combines Ganomaly and ResNet networks to detect and identify surface defects on particleboards was proposed. The model demonstrates superior performance in fine-grained direction. Evaluation metrics including precision, recall, average F1Score, and mAP are employed. Comparative analysis with Faster-RCNN and Yolo v5 baseline models reveals a 2.4% and 2.2% improvement in mAP for particleboard surface-defect detection. Moreover, the model exhibits excellent accuracy (93.1%) in recognizing five common defect types: shaving, scratches, chalk marks, soft spots, and adhesive spots. Comparative analysis with SE-Net, SA-Net, the original CBAM, and self-attention further supports its effectiveness in particleboard surface-defect detection. The integration of artificial-intelligence detection technology enables the timely detection of production process issues, reduces wood resource waste, and benefit the production of the enterprise.

Multi-scale surface defect detection method for bottled products based on variable receptive fields and Gather–Distribute feature fusion mechanism

The inspection of visual quality represents a crucial step in the production process of bottled products. Numerous machine vision methodologies have demonstrated proficient identification of significant defects on bottle surfaces in well-controlled imaging environments. However, the actual production scenario introduces a myriad of surface defect types on bottled products, exhibiting diverse shapes, with the majority of defect instances characterized by relatively small individual areas. Faced with such diverse and small-sized defects, traditional convolutional neural networks (CNNs) encounter limitations due to the utilization of fixed-size convolutional kernels. This choice results in a constrained receptive field, hindering the capture of sufficiently effective contextual information. Additionally, pooling operations within traditional CNNs lead to a substantial reduction in feature map dimensions, causing excessive blurring or outright neglect of small-sized defects. Consequently, this detrimentally impacts the accuracy of surface defect detection and recognition. This study proposes a novel multi-scale defect detection model incorporating a variable receptive field and Gather–Distribute feature fusion mechanism to overcome limitations of traditional CNNs. Nine different scale defect images of bottled products, including worn, wrinkles, joint markings and etc, were collected and enhanced to construct a surface defect detection dataset for the actual production of bottled products. Enhancements to convolutional layers and the C2f module improve feature extraction for different defect shapes and sizes. Integration of the Gather–Distribute feature fusion module (GDFFM) reduces feature information loss and enhances shallow-layer feature utilization. An efficient detection head (E-Detect) with ”parameter sharing” is proposed to reduce computational complexity and improve detection speed without experiencing significant accuracy loss. Experimental results demonstrate that the model’s superiority over advanced defect detection algorithms across various categories. Notably, it achieves accuracies of 89.9%, 55.6%, 89.4%, and 75% for challenging defects like small worn, subtle wrinkles, inclined external cover, and misaligned labels, with improvements of 3.2%, 7%, 2%, and 11.8% over the baseline model, respectively. The model’s mean Average Precision (mAP) also increases by 2.7%.

Unleashing the power of AI in detecting metal surface defects: an optimized YOLOv7-tiny model approach.

The detection of surface defects on metal products during the production process is crucial for ensuring high-quality products. These defects also lead to significant losses in the high-tech industry. To address the issues of slow detection speed and low accuracy in traditional metal surface defect detection, an improved algorithm based on the YOLOv7-tiny model is proposed. Firstly, to enhance the feature extraction and fusion capabilities of the model, the depth aware convolution module (DAC) is introduced to replace all ELAN-T modules in the network. Secondly, the AWFP-Add module is added after the Concat module in the network's Head section to strengthen the network's ability to adaptively distinguish the importance of different features. Finally, in order to expedite model convergence and alleviate the problem of imbalanced positive and negative samples in the study, a new loss function called Focal-SIoU is used to replace the original model's CIoU loss function. To validate the effectiveness of the proposed model, two industrial metal surface defect datasets, GC10-DET and NEU-DET, were employed in our experiments. Experimental results demonstrate that the improved algorithm achieved detection frame rates exceeding 100 fps on both datasets. Furthermore, the enhanced model achieved an mAP of 81% on the GC10-DET dataset and 80.1% on the NEU-DET dataset. Compared to the original YOLOv7-tiny algorithm, this represents an increase in mAP of nearly 11% and 9.2%, respectively. Moreover, when compared to other novel algorithms, our improved model demonstrated enhanced detection accuracy and significantly improved detection speed. These results collectively indicate that our proposed enhanced model effectively fulfills the industry's demand for rapid and efficient detection and recognition of metal surface defects.

Recognition of Steel Surface Defects Based on Broad Learning System

Recognition of Steel Surface Defects Based on Broad Learning System

Steel Surface Defect Recognition in Smart Manufacturing Using Deep Ensemble Transfer Learning-Based Techniques

Steel Surface Defect Recognition in Smart Manufacturing Using Deep Ensemble Transfer Learning-Based Techniques

Generative and Contrastive Combined Support Sample Synthesis Model for Few-/Zero-Shot Surface Defect Recognition

Generative and Contrastive Combined Support Sample Synthesis Model for Few-/Zero-Shot Surface Defect Recognition

High-speed acquisition and intelligent tunnel surface defects recognition

We introduce a framework to efficiently capture and identify the defects on the subway tunnel surfaces. Specifically, we design a high-speed multi-camera-synchronous acquisition system for scanning the tunnel surfaces and capturing the cracks from images. We propose an Improved Cascade Region-Based Convolutional Neural Network (R-CNN) method to locate and classify defects, with the crack being refined by image processing algorithms. The methodology is tested by on-site experiments carried out in an operational subway. The mAP value reaches 0.827, with a specific AP value of 0.625 and a newly proposed measure identification rate of 0.942 for crack objects. Notably, by training on bounding box labels, our overall algorithm exhibits the lowest Error Rate (ER) and the highest Intersection over Union (IoU) across all test images, surpassing the performance of classical semantic segmentation networks trained on pixel-level labels.

Apple Surface Defect Detection Based on Gray Level Co-Occurrence Matrix and Retinex Image Enhancement

Aiming at the problems of uneven light reflectivity on the spherical surface and high similarity between the stems/calyxes and scars that exist in the detection of surface defects in apples, this paper proposed a defect detection method based on image segmentation and stem/calyx recognition to realize the detection and recognition of surface defects in apples. Preliminary defect segmentation results were obtained by eliminating the interference of light reflection inhomogeneity through adaptive bilateral filtering-based single-scale Retinex (SSR) luminance correction and using adaptive gamma correction to enhance the Retinex reflective layer, and later segmenting the Retinex reflective layer by using a region-growing algorithm. The texture features of apple surface defects under different image processing methods were analyzed based on the gray level co-occurrence matrix, and a support vector machine was introduced for binary classification to differentiate between stems/calyxes and scars. Deploying the proposed defect detection method into the embedded device OpenMV4H7Plus, the accuracy of stem/calyx recognition reached 93.7%, and the accuracy of scar detection reached 94.2%. It has conclusively been shown that the proposed defect detection method can effectively detect apple surface defects in the presence of uneven light reflectivity and stem/calyx interference.

Automatic recognition of surface defects of hot rolled strip steel based on deep parallel attention convolution neural network

In general, the existence of surface defects in hot rolled strip steel will seriously affect the quality and appearance of industrial products. In order to improve the classification efficiency and accuracy of surface defect recognition. Firstly, a lightweight and high-precision deep learning neural network, deep parallel attention convolutional neural network, is proposed in this paper. In this network, fusion attention module is combined with parallel multi-scale module to focus important feature information and capture context feature information without losing important feature information. Secondly, in order to verify the lightweight of the proposed model, the Parameters, FLOPs, Inference time and FPS of the deep parallel attention convolutional neural network are compared with the current popular classification networks. The experimental results show that the deep parallel attention convolutional neural network can be applied to the actual steel defect detection. The experimental results show that the recognition accuracy, precision and area under the curve of the deep parallel attention convolutional neural network model reach 99.57%, 99.6% and 99.8%, respectively. This method significantly improves the average accuracy of classification and is an effective tool for detecting steel defects.

Lightweight Reconstruction Network for Surface Defect Detection Based on Texture Complexity Analysis

Deep learning networks have shown excellent performance in surface defect recognition and classification of certain industrial products. However, most industrial product defect samples are scarce and have a wide variety of defect types, making methods that require a large number of defect samples for training unsuitable. In this paper, a lightweight surface defect detection network (LRN-L) based on texture complexity analysis is proposed. Only a large number of defect-free samples, which can be easily obtained, are needed to detect defects. LRN-L includes two stages: texture reconstruction stage and defect localization stage. In the texture reconstruction phase, a lightweight reconstruction network (LRN) based on convolutional autoencoder is designed, which can reconstruct defect-free texture images; a loss function combining structural loss and L1 loss is proposed to improve the detection effect; we built a calculation model for image complexity, calculated the texture complexity for texture samples, and divided textures into three levels based on complexity. In the defect localization stage, the residual between the reconstructed image and the original image is taken as the possible region of the defect, and the defect localization is realized via a segmentation algorithm. In this paper, the network structure, loss function, texture complexity and other factors of LRN-L are analyzed in detail and compared with other similar algorithms on multiple texture datasets. The results show that LRN-L has strong robustness, accuracy and generalization ability, and is more suitable for industrial online detection.

A lightweight convolutional neural network for recognition and classification for Si3N4 chip substrate surface defects

For the low accuracy and poor efficiency for surface defects detection, identifying and locating defects becomes a key process. However, traditional inspection methods cannot solve these problems. A lightweight improved YOLOX network with attention mechanism (GhostC-YOLOX) for Si3N4 ceramic chip substrate surface defect recognition and classification is proposed. For liner regression, detection and classification tasks, SimOTA label assignment strategy is combined with Moscia and MixUp data augmentation. Dynamic allocation of positive samples is achieved and the dataset is expanded. To the training process, the loss function is optimized. L2 regularization term is introduced to improve the generalization ability. Aiming to generate more feature maps with fewer parameters, the GhostNet structure is embed into the Neck of YOLOX, which reduces the computational cost while maintaining performance. To improve the defect detection accuracy, the lightweight Attention mechanism CBAM(Convolutional Block Attention Module) is integrated into the Backbone tail of YOLOX. The attention is allocated to the two dimensions simultaneously. The detection accuracy of Si3N4 ceramic chip substrate is 96.47%. Compared with YOLOX and Faster RCNN models, the detection accuracy is improved by 2.648% and 18.08% respectively. Moreover, the parameter size of the method is only 5.034 MB. Its detection performance is obviously ahead of other detection methods.

A hierarchical training-convolutional neural network with feature alignment for steel surface defect recognition

A hierarchical training-convolutional neural network with feature alignment for steel surface defect recognition

Product Defect Identification System

Abstract: Some uncontrollable defects will occur on the surface of metal work pieces during processing. The existence of surface defects not only affects the appearance of the finished product, but also affects the quality to a certain extent. Surface defect detection of metal work pieces can effectively improve product quality and production efficiency, and is an important link in the process of product quality control. This proposed system uses the convolutional neural network algorithm in deep learning to classify and detect metal surface defects. The surface defect recognition accuracy and defect detection rate of metal work is computed.

Apple Grading Based on Multi-Dimensional View Processing and Deep Learning.

This research proposes an apple quality grading approach based on multi-dimensional view information processing using YOLOv5s network as the framework to rapidly and accurately perform the apple quality grading task. The Retinex algorithm is employed initially to finish picture improvement. Then, the YOLOv5s model, which is improved by adding ODConv dynamic convolution and GSConv convolution and VoVGSCSP lightweight backbone, is used to simultaneously complete the detection of apple surface defects and the identification and screening of fruit stem information, retaining only the side information of the apple multi-view. After that, the YOLOv5s network model-based approach for assessing apple quality is then developed. The introduction of the Swin Transformer module to the Resnet18 backbone increases the grading accuracy and brings the judgment closer to the global optimal solution. In this study, datasets were made using a total of 1244 apple images, each containing 8 to 10 apples. Training sets and test sets were randomly created and divided into 3:1. The experimental results demonstrated that in the multi-dimensional view information processing, the recognition accuracy of the designed fruit stem and surface defect recognition model reached 96.56% after 150 iteration training, the loss function value decreased to 0.03, the model parameter was only 6.78 M, and the detection rate was 32 frames/s. After 150 iteration training, the average grading accuracy of the quality grading model reached 94.46%, the loss function value decreased to 0.05, and the model parameter was only 3.78 M. The test findings indicate that the proposed strategy has a good application prospect in the apple grading task.

Multi-classification recognition and quantitative characterization of surface defects in belt grinding based on YOLOv7

Due to the complex and varied surface defects of the belt grinding, the automatic recognition and quantitative characterization of the surface defects is still an issue that needs to be resolved. To characterize surface defects in belt grinding, this study proposed a multi-classification recognition and quantification method. The YOLOv7 algorithm was utilized to detect defects, which would obtain classification and location information of defects. Aiming at the defects with continuous geometric boundaries, an object detection strategy based on Hough straight-line image correction was designed to quantitatively describe the characteristics of the defects in the grinding direction. In order to capture the quantitative information of burn defects without continuous geometric boundaries, an adaptive threshold segmentation approach with correction factors was developed. The results demonstrated that the YOLOv7 performance on our dataset reaches the mAP of 0.907. The suggested quantitative characterization method can effectively quantitatively characterize and analyze the defects.