Explore the vast range of titles available.

This paper addresses image enhancement and 3D reconstruction techniques for dim scenes inside the vacuum chamber of a nuclear fusion reactor. First, an improved multi-scale Retinex low-light image enhancement algorithm with adaptive weights is designed. It can recover image detail information that is not visible in low-light environments, maintaining image clarity and contrast for easy observation. Second, according to the actual needs of target plate defect detection and 3D reconstruction inside the vacuum chamber, a defect reconstruction algorithm based on photometric stereo vision is proposed. To optimize the position of the light source, a light source illumination profile simulation system is designed in this paper to provide an optimized light array for crack detection inside vacuum chambers without the need for extensive experimental testing. Finally, a robotic platform mounted with a binocular stereo-vision camera is constructed and image enhancement and defect reconstruction experiments are performed separately. The results show that the above method can broaden the gray level of low-illumination images and improve the brightness value and contrast. The maximum depth error is less than 24.0% and the maximum width error is less than 15.3%, which achieves the goal of detecting and reconstructing the defects inside the vacuum chamber.

The goal of the feature reconstruction network based on an autoencoder in the training phase is to force the network to reconstruct the input features well. The network tends to learn shortcuts of “identity mapping,” which leads to the network outputting abnormal features as they are in the inference phase. As such, the abnormal features based on reconstruction error cannot be distinguished from normal features, significantly limiting the detection performance of such methods. To address this issue, we propose a feature transformation reconstruction (FTR) network, which can avoid the identity mapping problem. Specifically, we use a normalizing flow model as a feature transformation (FT) network to transform input features into other forms. The training goal of the feature reconstruction (FR) network is no longer to reconstruct the input features but to reconstruct the transformed features, effectively avoiding the shortcut of learning the “identity map.” Furthermore, this paper proposes a masked convolutional attention (MCA) module, which randomly masks the input features in the training phase and reconstructs the input features in a self‐supervised manner. In the testing phase, the MCA can effectively suppress the excessive reconstruction of abnormal features and further improve anomaly detection performance. FTR achieves the scores of the area under the receiver operating characteristic curve (AUROC) at 99.5% and 97.8% on the MVTec AD and BTAD datasets, respectively, outperforming other state‐of‐the‐art methods. Moreover, FTR is faster than the existing methods, with a high speed of 137 frames per second (FPS) on a 3080ti GPU.

Industrial anomaly detection algorithms based on Convolutional Neural Networks (CNN) often struggle with identifying small anomaly regions and maintaining robust performance in noisy industrial environments. To address these limitations, this paper proposes the Swin Transformer-Based Hybrid Reconstruction Discriminative Network (SRDAD), which combines the global context modeling capabilities of Swin Transformer with complementary reconstruction and discrimination approaches. Our approach introduces three key contributions: a natural anomaly image generation module that produces diverse simulated anomalies resembling real-world defects; a Swin-Unet based reconstruction subnetwork with enhanced residual and pooling modules for accurate normal image reconstruction, utilizing hierarchical window attention mechanisms, and an anomaly contrast discrimination subnetwork based on convolutional Unet that enables end-to-end detection and localization through contrastive learning. This hybrid approach combines reconstruction and discrimination paradigms to improve anomaly detection performance. Experimental results on the industrial dataset MVTec AD demonstrate that SRDAD achieves competitive performance, with improvements of 0.6% in detection accuracy and 0.7% in localization precision. The method demonstrates improved performance in detecting small anomalies and maintaining performance in noisy environments, highlighting its potential for industrial applications.

The occurrence of anomalies on the surface of industrial products can lead to issues such as decreased product quality, reduced production efficiency, and safety hazards. Early detection and resolution of these problems are crucial for ensuring the quality and efficiency of production. The key challenge in applying deep learning to surface defect detection of industrial products is the scarcity of defect samples, which will make supervised learning methods unsuitable for surface defect detection problems. Therefore, it is a reasonable solution to use anomaly detection methods to deal with surface defect detection. Among image-based anomaly detection, reconstruction-based methods are the most commonly used. However, reconstruction-based approaches lack the involvement of defect samples in the training process, posing the risk of a perfect reconstruction of defects by the reconstruction network. In this paper, we propose a reconstruction-based defect detection algorithm that addresses these challenges by utilizing more realistic synthetic anomalies for training. Our model focuses on creating authentic synthetic defects and introduces an auto-encoder image reconstruction network with deep feature consistency constraints, as well as a defect separation network with a large receptive field. We conducted experiments on the challenging MVTec anomaly detection dataset and our trained model achieved an AUROC score of 99.70% and an average precision (AP) score of 99.87%. Our method surpasses recently proposed defect detection algorithms, thereby enhancing the accuracy of surface defect detection in industrial products.

The anomaly detection of products is a classical problem in the field of computer vision. Image reconstruction-based methods have shown promising results in the field of abnormality detection. Most of the existing methods use convolutional neural networks to build encoding–decoding structures to do image restoration. However, the limited receptive field of convolutional neural networks makes the information considered in the image restoration process limited, and the downsampling in the encoder causes information loss, which is not conducive to performing fine-grained restoration of images. To solve this problem, we propose a multi-layer feature restoration and projection model (MLFRP), which enables the restoration process to be carried out on multi-scale feature maps through a block-level feature restoration module that fully considers the detail information and semantic information required for the restoration process. We conducted in-depth experiments on the MvtecAD anomaly detection benchmark dataset, which showed that our model outperforms current state-of-the-art anomaly detection methods.

The main results of the research consist in comparing the terms of construction work during the period of reconstruction or major overhaul in various normative documents and generalization to single result. Methods are proposed for resolving contentious issues, avoiding unnecessary costs and appealing to arbitration courts. It is established that in recent years, the methods of organization and construction management have undergone significant changes. It was revealed that normative documents of various institutions allow different interpretations of terms and concepts, which lead to controversial situations related to the classification of these works by tax authorities. The given problems arise at the stage of completion of construction work, when the adjustment in the design and contract documentation is practically impossible to execute. An example of construction and installation works implementation during the overhaul of an industrial building is considered and analyzed. Discrepancies in terms are revealed in terms of performance of construction work during the reconstruction or overhaul period.

The γ-ray detection efficiency of a detector decreases over time due to factors like radiation damage or an increase in the thickness of the inactive dead layer. For large γ-ray detector facilities, it is crucial to assess the health condition and performance of the inner regions of the detector crystals over time. In this study, we have introduced a method using GEANT4 simulation to detect defective regions within thick γ-ray detectors. In the experimental phase, a scanning setup was employed, comprising a single-crystal High Purity Germanium (HPGe) detector and a position-sensitive GAGG:Ce detector for coincidence measurements, using a 22 Na source. The 2D images were reconstructed from the front-face and side-face scans of the single-crystal coaxial HPGe detector, employing an energy gate set at 511 keV. A position gate applied to a specific section of those 2D images allowed for the mapping of γ-ray interactions along a conical path within the HPGe detector. The methodology involved the comparison and analysis of histograms generated from various sector gates, facilitating the identification of the defective region’s position. In the GEANT4 simulation, a defective region was defined within the crystal, and that was effectively represented in the corresponding scanned image, which exhibited reduced efficiency. It’s important to note that this method’s effectiveness is restricted by the absorption profile of the 511 keV γ-ray, limiting its applicability to a depth of approximately 4 cm from the surface of the HPGe crystal. However, this approach can offer a swift and convenient method for inspecting γ-ray detectors, making it a valuable tool for the detector industry.

Quality control and predictive maintenance are two essential pillars of Industry 4.0, aiming to optimize production, reduce operational costs, and enhance system reliability. Real-time visual inspection ensures early detection of manufacturing defects, assembly errors, or texture inconsistencies, preventing defective products from reaching customers. Predictive maintenance leverages sensor data by analyzing vibrations, temperature, and pressure signals to anticipate failures and avoid production downtime. Image-based quality control has become critical in industries such as automotive, electronics, aerospace, and food processing, where visual appearance is a key quality indicator. Although advances in deep learning and computer vision have significantly improved anomaly detection, industrial deployments remain challenged by the scarcity of labeled anomalies and the variability of defects. These issues increasingly lead to the adoption of unsupervised methods and generative approaches, which, despite their effectiveness, introduce substantial computational complexity. We conduct a unified comparison of ten anomaly detection methods, categorizing them according to their reliance on synthetic anomaly generation and their detection strategy, either reconstruction-based or feature-based. All models are trained exclusively on normal data to mirror realistic industrial conditions. Our evaluation framework combines performance metrics such as recall, precision, and their harmonic mean, emphasizing the need to minimize false negatives that could lead to critical production failures. In addition, we assess environmental impact and hardware complexity to better guide method selection. Practical recommendations are provided to balance robustness, operational feasibility, and sustainability in industrial applications.

In this paper, we present a new fabric defect detection algorithm based on learning an adaptive dictionary. Such a dictionary can efficiently represent columns of normal fabric images using a linear combination of its elements. Benefiting from the fact that defects on a fabric appear to be small in size, a dictionary can be learned directly from a testing image itself instead of a reference, allowing more flexibility to adapt to varying fabric textures. When modeling a test image using the learned dictionary, columns involving anomalies of the test image are likely to have larger reconstruction errors than normal ones. The anomalous regions (defects) can be easily enhanced in the residual image. Then, a simple threshold operation is able to segment the defective pixels from the residual image. To adapt more defects, especially some linear defects, we rotate the test image by a slight degree and re-analyze the rotated image. Compared to the Fourier method, experimental results on 47 real-world test images with defects reveal that our algorithm is able to adapt to varying fabric textures and exhibits more accurate defect detection.

Purpose The purpose of this study was to evaluate the effect of defective positron emission tomography (PET) detectors on clinical PET image quality in simultaneous PET/magnetic resonance imaging (MRI) for both time-of-flight (TOF) and non-TOF reconstructed images. Procedures A total of six patients with various malignant tumors were included and underwent a 2-deoxy-2-[ 18 F]fluoro- d -glucose PET scan in a fully functional simultaneous TOF PET/MRI. TOF and non-TOF PET images were reconstructed before and after simulating defective detector units. All images were clinically assessed and scored. In addition, a quantitative assessment was performed. Differences were ascertained and compared using the Wilcoxon matched pairs signed-rank test. Results Without TOF, the image artifacts introduced by one defective detector unit already started to degrade the overall image quality. It reduced the confidence and could lead to a change in diagnosis. Simulating three or five defective detector units resulted in more artifacts and further reduced overall image quality and confidence. By including TOF information, the effects were mitigated: Images reconstructed with one defective detector unit had similar scores as the ones without defective units. The average absolute percentage error for one, three, and five defective detector units were respectively 8, 20, and 37 % for the non-TOF cases and only 5, 11, and 19 % for the TOF cases. Conclusion Our study indicates that PET image artifacts due to (simulated) defective detectors are significantly mitigated with the integration of TOF information in simultaneous PET/MR. One defective detector unit introduces, on average, a 5 % absolute percentage error. However, in TOF imaging, even in cases with one or three defective units for head and neck imaging and one defective unit for chest and abdominal imaging, overall image quality, artifact scoring, and reader confidence are not significantly degraded.