Defect Detection Research Articles

Toward robust and high-throughput detection of seed defects in X-ray images via deep learning

BackgroundThe detection of internal defects in seeds via non-destructive imaging techniques is a topic of high interest to optimize the quality of seed lots. In this context, X-ray imaging is especially suited. Recent studies have shown the feasibility of defect detection via deep learning models in 3D tomography images. We demonstrate the possibility of performing such deep learning-based analysis on 2D X-ray radiography for a faster yet robust method via the X-Robustifier pipeline proposed in this article.Results2D X-ray images of both defective and defect-free seeds were acquired. A deep learning model based on state-of-the-art object detection neural networks is proposed. Specific data augmentation techniques are introduced to compensate for the low ratio of defects and increase the robustness to variation of the physical parameters of the X-ray imaging systems. The seed defects were accurately detected (F1-score >90%), surpassing human performance in computation time and error rates. The robustness of these models against the principal distortions commonly found in actual agro-industrial conditions is demonstrated, in particular, the robustness to physical noise, dimensionality reduction and the presence of seed coating.ConclusionThis work provides a full pipeline to automatically detect common defects in seeds via 2D X-ray imaging. The method is illustrated on sugar beet and faba bean and could be efficiently extended to other species via the proposed generic X-ray data processing approach (X-Robustifier). Beyond a simple proof of feasibility, this constitutes important results toward the effective use in the routine of deep learning-based automatic detection of seed defects.

Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training

Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training

An Improved Lightweight Deep Learning Model and Implementation for Track Fastener Defect Detection with Unmanned Aerial Vehicles

An Improved Lightweight Deep Learning Model and Implementation for Track Fastener Defect Detection with Unmanned Aerial Vehicles

Application of a mild data-driven technique to Lippmann–Schwinger inverse scattering in variable-exponent Lebesgue spaces for microwave imaging

A mild data-driven approach for microwave imaging is considered in this paper. In particular, the developed technique relies upon the use of a Newton-type inversion scheme in variable-exponent Lebesgue spaces, which has been modified by including a data-driven operator to enforce the available a-priori information about the class of targets to be investigated. In this way, the performance of the method is improved, and the problems related to the possible convergence to local minima are mitigated. The effectiveness of the approach has been evaluated through numerical simulations involving the detection of defects inside (partially) known objects, showing good results.

A dynamic inference network (DI-Net) for online fabric defect detection in smart manufacturing

A dynamic inference network (DI-Net) for online fabric defect detection in smart manufacturing

Exploring and optimizing deep neural networks for precision defect detection system in injection molding process

Exploring and optimizing deep neural networks for precision defect detection system in injection molding process

SCFNet: Lightweight Steel Defect Detection Network Based on Spatial Channel Reorganization and Weighted Jump Fusion

The goal of steel defect detection is to enhance the recognition accuracy and accelerate the detection speed with fewer parameters. However, challenges arise in steel sample detection due to issues such as feature ambiguity, low contrast, and similarity among inter-class features. Moreover, limited computing capability makes it difficult for small and medium-sized enterprises to deploy and utilize networks effectively. Therefore, we propose a novel lightweight steel detection network (SCFNet), which is based on spatial channel reconstruction and deep feature fusion. The network adopts a lightweight and efficient feature extraction module (LEM) for multi-scale feature extraction, enhancing the capability to extract blurry features. Simultaneously, we adopt spatial and channel reconstruction convolution (ScConv) to reconstruct the spatial and channel features of the feature maps, enhancing the spatial localization and semantic representation of defects. Additionally, we adopt the Weighted Bidirectional Feature Pyramid Network (BiFPN) for defect feature fusion, thereby enhancing the capability of the model in detecting low-contrast defects. Finally, we discuss the impact of different data augmentation methods on the model accuracy. Extensive experiments are conducted on the NEU-DET dataset, resulting in a final model achieving an mAP of 81.2%. Remarkably, this model only required 2.01 M parameters and 5.9 GFLOPs of computation. Compared to state-of-the-art object detection algorithms, our approach achieves a higher detection accuracy while requiring fewer computational resources, effectively balancing the model size and detection accuracy.

Detection of Small Targets in Photovoltaic Cell Defect Polarization Imaging Based on Improved YOLOv7

A photovoltaic cell defect polarization imaging small target detection method based on improved YOLOv7 is proposed to address the problem of low detection accuracy caused by insufficient feature extraction ability in the process of small target defect detection. Firstly, polarization imaging technology is introduced, using polarization degree images as inputs to enhance the edge contour information of YOLOv7 for detecting small targets; then, the COT self-attention mechanism is added to reconstruct the SPPCSPC module to improve YOLOv7’s ability to capture and fuse small target features in complex backgrounds; next, the normalized Wasserstein distance (NWD) is used to replace the traditional loss function based on intersection over union (IoU) metric, reducing the boundary offset between the prior box and the closest real target box in the prediction process of the object detection model and reducing the sensitivity of the YOLOv7 network to small object position deviations; finally, by constructing a shortwave infrared polarization imaging system to obtain polarization images of photovoltaic cells and detect small targets with scratch defects in photovoltaic cells, the applicability and effectiveness of the proposed method are verified. The results show that the proposed method has good recognition ability for small target defects in photovoltaic cells. By applying the constructed dataset, the detection accuracy reaches 98.08%, the recall rate reaches 95.06% and the mAP reaches 98.83%.

Steel Surface Defect Detection Algorithm Based on ESI-YOLOv8

Abstract To enhance the precision of detecting defects on steel plate surfaces and diminish the incidences of false detection and leakage, the ESI-YOLOv8 algorithm is introduced. The algorithm incorporates an EP module, which minimizes redundant computations and model parameters to optimize efficiency and simultaneously increases the multi-scale fusion mechanism to expand the sensory field. The SPPF-LSKA module is proposed by integrating the large separated convolutional attention module with the spatial pyramid pooling module. This integration reduces computational complexity, accelerates model operation speed, and improves detection accuracy. Additionally, the INNER-CIOU loss function is introduced to improve detection speed and model accuracy by controlling the scale size of the auxiliary border. The results of the experiment indicate that, following the improvements made, the algorithm's detection accuracy has increased to 78%, which is 3.7% higher than the original YOLOv8. Furthermore, the model parameters were reduced, and the verification was conducted using the CoCo dataset, resulting in an average accuracy of 77.8%. In conclusion, the algorithm has demonstrated its ability to perform steel plate surface defect detection with efficiency and accuracy.

YOLOv8-LMG: An Improved Bearing Defect Detection Algorithm Based on YOLOv8

In industrial manufacturing, bearings are crucial for machinery stability and safety. Undetected wear or cracks can lead to severe operational and financial setbacks. Thus, accurately identifying bearing defects is essential for maintaining production safety and equipment reliability. This research introduces an improved bearing defect detection model, YOLOv8-LMG, which is based on the YOLOv8n framework and incorporates four innovative technologies: the VanillaNet backbone network, the Lion optimizer, the CFP-EVC module, and the Shape-IoU loss function. These enhancements significantly increase detection efficiency and accuracy. YOLOv8-LMG achieves a mAP@0.5 of 86.5% and a mAP@0.5–0.95 of 57.0% on the test dataset, surpassing the original YOLOv8n model while maintaining low computational complexity. Experimental results reveal that the YOLOv8-LMG model boosts accuracy and efficiency in bearing defect detection, showcasing its significant potential and practical value in advancing industrial inspection technologies.

Surface Defect Detection of Aluminum Profiles Based on Multiscale and Self-Attention Mechanisms

To address the various challenges in aluminum surface defect detection, such as multiscale intricacies, sensitivity to lighting variations, occlusion, and noise, this study proposes the AluDef-ClassNet model. Firstly, a Gaussian difference pyramid is utilized to capture multiscale image features. Secondly, a self-attention mechanism is introduced to enhance feature representation. Additionally, an improved residual network structure incorporating dilated convolutions is adopted to increase the receptive field, thereby enhancing the network’s ability to learn from extensive information. A small-scale dataset of high-quality aluminum surface defect images is acquired using a CCD camera. To better tackle the challenges in surface defect detection, advanced deep learning techniques and data augmentation strategies are employed. To address the difficulty of data labeling, a transfer learning approach based on fine-tuning is utilized, leveraging prior knowledge to enhance the efficiency and accuracy of model training. In dataset testing, our model achieved a classification accuracy of 98.01%, demonstrating significant advantages over other classification models.

Advancing X-ray Inspection with Deep Learning De-noising Technology

X-ray inspection plays a pivotal role in the food and non-destructive testing industries, ensuring optimal products quality and safety. To improve contaminants and defects detection, it is crucial to reduce the amount of noise in the acquired images. Addressing this, Hamamatsu Photonics has developed a new de-noising technology based on deep learning algorithms and an innovative X-ray simulation method.

Enhancing Moisture-Induced Defect Detection in Insulated Steel Pipes through Infrared Thermography and Hybrid Dataset

It is crucial to accurately detect moisture-induced defects in steel pipe insulation in order to combat corrosion under insulation (CUI). This study enhances the capabilities of infrared thermography (IRT) by integrating it with top-performing machine learning models renowned for their effectiveness in image segmentation tasks. A novel methodology was developed to enrich machine learning training, incorporating synthetic datasets generated via finite element method (FEM) simulations with experimental data. The performance of four advanced models—UNet, UNet++, DeepLabV3+, and FPN—was evaluated. These models demonstrated significant enhancements in defect detection capabilities, with notable improvements observed in FPN, which exhibited a mean intersection over union (IoU) increase from 0.78 to 0.94, a reduction in loss from 0.19 to 0.06, and an F1 score increase from 0.92 to 0.96 when trained on hybrid datasets compared to those trained solely on real data. The results highlight the benefits of integrating synthetic and experimental data, effectively overcoming the challenges of limited dataset sizes, and significantly improving the models’ accuracy and generalization capabilities in identifying defects. This approach marks a significant advancement in industrial maintenance and inspection, offering a precise, reliable, and scalable solution to managing the risks associated with CUI.

Perinatal management of pregnancies with Fetal Congenital Anomalies: A guide to Obstetricians and Pediatricians.

Background Congenital anomalies are responsible for approximately 20% of all neonatal deaths worldwide. Improvements in antenatal screening and diagnosis have significantly improved the prenatal detection of birth defects; however, these improvements have not translated into the improved neonatal prognosis of babies born with congenital anomalies. Objectives An attempt has been made to summarise the prenatal interventions, if available, the optimal route, mode and time of delivery and discuss the minimum delivery room preparations that should be made if expecting to deliver a fetus with a congenital anomaly. Methods The recent literature related to the perinatal management of the fetus with prenatally detected common congenital anomalies were searched in English peer-reviewed journals from the PubMed database, to work out an evidence-based approach for their management. Results Fetuses with prenatally detected congenital anomalies should be delivered at a tertiary care centre with facilities for neonatal surgery and paediatric intensive care if needed. There is no indication for preterm delivery in the majority of cases. Only a few congenital malformations, like high-risk sacrococcygeal teratoma, congenital lung masses with significant fetal compromise, fetal cerebral lesions or neural tube defects with Head circumference >40 cm or the biparietal diameter is ≥12 cm, gastroschisis with extracorporeal liver, or giant omphaloceles in the fetus warrant caesarean section as the primary mode of delivery. Conclusion The prognosis of a fetus with congenital anomalies can be significantly improved if planning for delivery, including the Place and Time of delivery, is done optimally. A multi-disciplinary team should be available for the fetus to optimize conditions right from when it is born.

Shaping down syndrome brain cognitive and molecular changes due to aging using adult animals from the Ts66Yah murine model.

Down syndrome (DS) is the most common condition with intellectual disability and is caused by trisomy of Homo sapiens chromosome 21 (HSA21). The increased dosage of genes on HSA21 is associated with early neurodevelopmental changes and subsequently at adult age with the development of Alzheimer-like cognitive decline. However, the molecular mechanisms promoting brain pathology along aging are still missing. The novel Ts66Yah model represents an evolution of the Ts65Dn, used in characterizing the progression of brain degeneration, and it manifest phenotypes closer to human DS condition. In this study we performed a longitudinal analysis (3-9 months) of adult Ts66Yah mice. Our data support the behavioural alterations occurring in Ts66Yah mice at older age with improvement in the detection of spatial memory defects and also a new anxiety-related phenotype. The evaluation of hippocampal molecular pathways in Ts66Yah mice, as effect of age, demonstrate the aberrant regulation of redox balance, proteostasis, stress response, metabolic pathways, programmed cell death and synaptic plasticity. Intriguingly, the genotype-driven changes observed in those pathways occur early promoting altered brain development and the onset of a condition of premature aging. In turn, aging may account for the subsequent hippocampal deterioration that fall in characteristic neuropathological features. Besides, the analysis of sex influence in the alteration of hippocampal mechanisms demonstrate only a mild effect. Overall, data collected in Ts66Yah provide novel and consolidated insights, concerning trisomy-driven processes that contribute to brain pathology in conjunction with aging. This, in turn, aids in bridging the existing gap in comprehending the intricate nature of DS phenotypes.

Identification of surface defects on solar PV panels and wind turbine blades using attention based deep learning model

The global generation of renewable energy has rapidly increased, primarily due to the installation of large-scale renewable energy power plants. However, monitoring renewable energy assets in these large plants remains challenging due to environmental factors that could result in reduced power generation, malfunctioning, and degradation of asset life. Therefore, the detection of surface defects on renewable energy assets is crucial for maintaining the performance and efficiency of these plants. This paper proposes an innovative detection framework to achieve an economical surface monitoring system for renewable energy assets. High-resolution images of the assets are captured regularly and inspected to identify surface or structural damages on solar panels and wind turbine blades. Vision transformer (ViT), one of the latest attention-based deep learning (DL) models in computer vision, is proposed in this work to classify surface defects. The ViT model outperforms other DL models, including MobileNet, VGG16, Xception, EfficientNetB7, and ResNet50, achieving high accuracy scores above 97% for both wind and solar plant assets. From the results, our proposed model demonstrates its potential for monitoring and detecting damages in renewable energy assets for efficient and reliable operation of renewable power plants.

Porosity Prediction in Laser-based Powder Bed Fusion of Polyamide 12 Using Infrared Thermography and Machine Learning

Achieving precise control in laser-based powder bed fusion of polymers is crucial for ensuring the structural integrity of aerospace and automotive components. Closed-loop feedback control systems using process monitoring techniques, such as infrared thermography, have the potential to provide reliable production by controlling the temperature of the melt. However, challenges arise from complex interactions among variables, such as part geometry, scan strategy, and laser parameters, affecting the melted polymer's temperatures and subsequent particle fusion. Thus, the correlation between thermal signals and resulting part density still needs to be clarified. In this work, a machine learning algorithm is trained to predict local porosity or, rather, solidity based on thermal and temporal features extracted from the melt's temperature-time profile. This enables statistical techniques to assess the contribution of the melt's thermal and temporal features in the decision-making process for evaluating porosity, along with the influence of voxel size and configuration. The in-situ process signature is measured using infrared thermography, and the porosity is analyzed by X-ray micro-computed tomography. The 2D thermal data is first converted into voxel information and then stitched with the 3D mircoCT data in a second step. The resulting 3D thermal features and porosity matrices are downsampled and utilized to train a machine learning algorithm (lightGBM). Models with high prediction accuracy are achieved using a small voxel size to avoid over-homogenizing features and by utilizing thermal signals from adjacent voxels to determine porosity in a volume element. The highest predictor for resulting porosity is the peak temperature of the melt during laser exposure. Interlayer effects, such as sufficient reheating of subsurface layers, are the second-highest indicator for dense parts. Furthermore, the model's performance is also affected by intra-layer effects, including the peak temperature of adjacent voxels and the cooling behavior after laser exposure. This research has several implications for industry, as it enables the detection of process defects based on in-situ process monitoring data without post-process material testing. Moreover, identifying thermal signal ranges that lead to the highest porosity can reduce the number of experiments needed for material qualification processes.

Yolo-sd: simulated feature fusion for few-shot industrial defect detection based on YOLOv8 and stable diffusion

Yolo-sd: simulated feature fusion for few-shot industrial defect detection based on YOLOv8 and stable diffusion

Quantifying the effect of X-ray scattering for data generation in real-time defect detection.

X-ray imaging is widely used for the non-destructive detection of defects in industrial products on a conveyor belt. In-line detection requires highly accurate, robust, and fast algorithms. Deep Convolutional Neural Networks (DCNNs) satisfy these requirements when a large amount of labeled data is available. To overcome the challenge of collecting these data, different methods of X-ray image generation are considered. Depending on the desired degree of similarity to real data, different physical effects should either be simulated or can be ignored. X-ray scattering is known to be computationally expensive to simulate, and this effect can greatly affect the accuracy of a generated X-ray image. We aim to quantitatively evaluate the effect of scattering on defect detection. Monte-Carlo simulation is used to generate X-ray scattering distribution. DCNNs are trained on the data with and without scattering and applied to the same test datasets. Probability of Detection (POD) curves are computed to compare their performance, characterized by the size of the smallest detectable defect. We apply the methodology to a model problem of defect detection in cylinders. When trained on data without scattering, DCNNs reliably detect defects larger than 1.3mm, and using data with scattering improves performance by less than 5%. If the analysis is performed on the cases with large scattering-to-primary ratio (1<SPR<5), the difference in performance could reach 15% (approx. 0.4mm). Excluding the scattering signal from the training data has the largest effect on the smallest detectable defects, and the difference decreases for larger defects. The scattering-to-primary ratio has a significant effect on detection performance and the required accuracy of data generation.

Performance Analysis of ResNet50 and Inception-V3 Image Classification for Defect Detection in 3D Food Printing

In the future, 3D food printing may be a fruitful area for the food industry. The presence of this technology opens the public's eyes to a revolution in the food sector, where food processing is limited to the conventional. The existence of this technology will also make food production much more effective and efficient. However, there is a problem when the 3D Food Printing process is carried out; when object defects occur, there will be material waste. This research proposes deep learning-based defect detection for defect and non-defect objects. This model mainly uses CNN as a deep learning method. The dataset is taken from the image of the print process performed at the time of object creation to be trained and validated to check the effectiveness of the proposed model. The architecture used uses pre-trained CNN models namely Inception-V3 and ResNet50 with the hope of classifying images that have a higher viscosity of the material. Where the model has been tested with previous datasets and applied with 3D Food Printing datasets with a dataset division ratio of 85% which is training data and 15% is validation data. After testing the two proposed scenarios, the accuracy result obtained in the test model scenario 1, Inception-V3, is 84.62% and for the test model scenario 2, ResNet50, the accuracy is 93.83%. The outcomes also demonstrate that improved accuracy, loss, and classification time may be obtained by applying CNN in conjunction with data augmentation.