Inspection Of Images Research Articles

Three-dimensional reconstruction method for layered structures based on a frequency modulated continuous wave terahertz radar

The feasibility of employing a continuous-wave terahertz detection system for non-contact and non-destructive testing (NDT) in multi-layered bonding structures is assessed in this study. The paper introduces the detection principle of terahertz frequency modulated continuous wave (FMCW) radar and outlines the two-dimensional (2D) scanning platform, which integrates optical lenses, three linear actuators, a control platform, and data acquisition units. Experimental results on two types of insulation with prefabricated defects demonstrate the capability of terahertz waves for transparent inspection imaging. These results confirm the viability of terahertz FMCW detection technology as an advanced NDT tool for multi-layered bonding structures. However, the inherent limitations of terahertz wavelength and hardware systems pose challenges in discriminating reflection peaks on upper and lower surfaces. To address this issue, a local adaptive empirical wavelet coefficient modal decomposition (LAEWCMD) method is proposed to enhance the longitudinal discrimination ability of terahertz detection. The proposed method involves segmenting the 2D terahertz detection image into regions to differentiate between defective and non-defective areas. Continuous wavelet transforms (CWT) are then applied to the range signals of each region to derive continuous wavelet coefficients (CWCs). Subsequently, empirical mode decomposition (EMD) is performed on the CWCs to decompose them into intrinsic mode functions (IMFs) and residual signals. The 1st IMF is utilized for three-dimensional (3D) reconstruction, and the regions are fused to generate the final output. The effectiveness of the proposed method is validated on aircraft thermal protection structures (TPS), achieving high-precision 3D reconstruction. This offers a novel approach for the application of terahertz computed tomography imaging and NDT.

A Complementary Fusion-Based Multimodal Non-Destructive Testing and Evaluation Using Phased-Array Ultrasonic and Pulsed Thermography on a Composite Structure.

Combinative methodologies have the potential to address the drawbacks of unimodal non-destructive testing and evaluation (NDT & E) when inspecting multilayer structures. The aim of this study is to investigate the integration of information gathered via phased-array ultrasonic testing (PAUT) and pulsed thermography (PT), addressing the challenges posed by surface-level anomalies in PAUT and the limited deep penetration in PT. A center-of-mass-based registration method was proposed to align shapeless inspection results in consecutive insertions. Subsequently, the aligned inspection images were merged using complementary techniques, including maximum, weighted-averaging, depth-driven combination (DDC), and wavelet decomposition. The results indicated that although individual inspections may have lower mean absolute error (MAE) ratings than fused images, the use of complementary fusion improved defect identification in the total number of detections across numerous layers of the structure. Detection errors are analyzed, and a tendency to overestimate defect sizes is revealed with individual inspection methods. This study concludes that complementary fusion provides a more comprehensive understanding of overall defect detection throughout the thickness, highlighting the importance of leveraging multiple modalities for improved inspection outcomes in structural analysis.

Guided Wave Phased Array Ultrasonic Imaging for Thin Plate Inspection

This study focuses on the application of phased array ultrasonic testing with guided waves for Structural Health Monitoring (SHM) in thin plates. Addressing the limitations of conventional ultrasonic testing efficiently by inspecting thin, long structures. This study employs phased array technology to thin isotropic plates at high frequency(2MHz), thereby elevating imaging and defect detection in structural components. Through the utilization of the full matrix capture (FMC) scanning approach in 3-D finite element (FE) simulations, A0 and S0 modes were generated on steel plates with through-hole geometries. The process involved capturing reflected signals to form an FMC matrix that includes all A-scan signals. Subsequently, the total focusing method (TFM) algorithm was applied to FMC data for the reconstruction of focused images of A0 and S0 modes separately. A key improvement in our approach is integrating a time-domain filtering method into the FMC data. This enhancement addresses the dispersive nature of guided waves, thus improving the accuracy in identifying defect locations and sizes within the images. Our finite element simulations on steel specimens, with varied through-hole locations, revealed the method's potential in accurately imaging defects located deeper within the structure. Additionally, the study expanded to evaluate the efficacy of phased array ultrasonic testing (PAUT) in SHM, particularly in conjunction with guided waves to study the flaw detection sensitivity of the defect through the TFM algorithm on isotropic steel plates up to wavelength(λ)/16. This whole analysis considered crucial factors such as ultrasonic wave mode, frequency, and group velocity for the structure under inspection. This study represents a significant contribution to the field of SHM, introducing a sophisticated, real-time monitoring methodology that promises to enhance structural integrity assessment. Keywords: SHM, PAUT, GW, FMC, TFM FE Simulations, Time Domain Filtering, Ultrasonic Testing.

Ultrasonic dynamic plane wave imaging for high-speed railway inspection

The detection of internal defects within railway tracks stands as a critical aspect of ensuring transport security, given its potential to precipitate severe accidents. Phased array ultrasonic testing methods have gained extensive usage in rail inspection owing to their remarkable precision and expansive coverage. Traditional ultrasonic inspection techniques typically require either a fixed relative position between the transducer and the specimens or a gentle movement of the transducer to beamform. However, the unavoidable vibration stemming from the vehicle–rail coupled interactions often results in time-variant media, significantly impacting the beamforming. This paper presents a refined wavenumber-domain plane wave imaging technique tailored to enable real-time dynamic imaging, specifically accommodating the vertical vibrational movement of the transducer. Real-time calculation of the transmission focal law is achieved by numerical fitting. The wavenumber-domain technique is utilized to realize real-time accurately reconstructed images. The efficacy of the proposed method is assessed through simulations and experiments performed on a convex cylindrical specimen and a rail head sample, respectively. It can be seen that this approach can achieve a frame rate of 83.3 fps with a pipeline architecture in this study, demonstrating the capability to reconstruct images in vibrating environments, such as during the high-speed inspection of railways.

Comparing jet-shaped point symmetry in cluster cooling flows and supernovae

I point out similarities between point-symmetric X-ray morphologies in cooling flow groups and clusters of galaxies, which are observed to be shaped by jets, and point-symmetric morphologies of eight core-collapse supernova (CCSN) remnants. I identify these similarities by qualitative eye inspection of multiwavelength images. I use these similarities to strengthen the jittering jet explosion mechanism (JJEM) of CCSNe, which predicts that the last pairs of jets to be launched by the newly born neutron star might shape some CCSN remnants to point-symmetric morphology. The point-symmetric morphologies in both types of objects are composed of two or more pairs of opposite bubbles (cavities), nozzles, some clumps, small protrusions (termed ears), and rims. The typically large volume of a CCSN remnant shaped by jets implies that the shaping jets carry an energy comparable to that of the ejecta, which in turn implies that jets exploded the remnant’s massive star progenitor. The morphological similarities studied here add to the similarity of CCSN remnants, not only point-symmetric ones, to planetary nebulae shaped by jets. Together, these similarities solidify the JJEM as the main explosion mechanism of CCSNe. I consider the identification of point-symmetry in CCSNe, as expected by jet-shaping in the JJEM, to be the most severe challenge to the competing neutrino-driven explosion mechanism. I reiterate my earlier claim, but in a more vocal voice, that the main explosion mechanism of CCSNe is the JJEM.

One-Dimensional Copper-Doped Rb2AgI3 with Efficient Sky-Blue Emission as a High-Performance X-ray Scintillator.

Scintillators have garnered heightened attention for their diverse applications in medical imaging and security inspection. Nonetheless, commercial scintillators encounter challenges with costly rare-earth metals and toxic elements like thallium (Tl), driving the need for sustainable, cost-effective, and eco-friendly alternatives to meet contemporary X-ray detection demands. This study focuses on exploring the potential of Cu+-doped Rb2AgI3 as an effective metal halide (MH) scintillator. One-dimensional (1D) Rb2AgI3 and Cu+-doped Rb2AgI3 single crystals (SCs) were synthesized by using the conventional temperature-lowering crystallization method. When excited by UV light, Cu+-doped SCs emitted a broad sky-blue light at 490 nm with a high photoluminescence (PL) quantum yield (PLQY) of 76.48%. Remarkably, under X-ray excitation, these Cu+-doped SCs demonstrated an outstanding light yield of 36,293 photons MeV-1, a relatively low detection threshold of 1.022 μGyair s-1, and a rapid scintillation decay time of 465 ns. The prepared translucent scintillation film has good uniformity and flexibility, with a high spatial resolution of 10.2 lp mm-1. These results position Cu+-doped Rb2AgI3 as a leading candidate among promising X-ray scintillators, offering superior scintillation light yield, excellent stability, and nontoxicity.

DiffDD: A surface defect detection framework with diffusion probabilistic model

Automated defect detection is critical to improve product quality, reduce costs, and enhance productivity in the manufacturing process. More recently, diffusion-based generative models have entered a new realm of vision tasks by offering high-quality and diverse images. However, the diffusion-based defect detection model fails to be researched, and generative models typically require postprocessing modules to achieve the segmentation of defective regions. Furthermore, generic diffusion models struggle to reconstruct defective regions while preserving the semantic information of the inspection images. To address these issues, we propose a Diffusion-based Defect Detection (DiffDD) framework, comprising a pre-trained backbone (PvTv2) and diffusion probabilistic model (DPM), for surface defect detection. The backbone is employed to extract multi-scale feature maps from input images supervised by pixel-wise labels. These pyramid maps interact with DPM to guide the diffusion process, refining the semantic information of the reconstructed image. Additionally, a semantic restoration (SR) module is used to restore the output of the backbone for loss computation with the pixel-wise label. A conditional image prior method is implemented to constrain the randomness of DPM, aiding the model in generating segmentation masks corresponding to the inspection images. Experimental results on NEU_SEG and MT demonstrate that our model outperforms state-of-the-art (SOTA) methods by a significant margin, indicating the generalization and effectiveness of the proposed DiffDD framework.

Fusion of infrared and terahertz imaging for non-invasive inspection of marqueteries coupled with finite element analyses

This study utilizes infrared thermography (IRT) and terahertz (THz) imaging techniques to conduct a non-invasive inspection of marqueteries. Specifically, two experimental investigations and image processing methods have been carried out, and their advantages and disadvantages have been highlighted. To cross-reference with the experimental results, a finite element simulation was performed for both IRT and THz, which validate the experimental outcomes and providing instructions to the experimental set-up and parameters. Then, an ad-hoc fusion imaging method has been applied to the experimental results to identify defects and features. Such a reverse engineering procedure integrating numerical and experimental images acquired at different wavelengths may be considered an interesting step forward for the optimization of cultural heritage nondestructive testing (NDT).

42‐4: Late‐News Paper: A Radiation‐Hardened Oxide TFT with a Multi‐Layered Gate Dielectric

We propose an IGZO thin‐film transistor (TFT) with a multi‐layered gate dielectric for X‐ray flat‐panel detectors (FPDs). By minimizing X‐ray effects on the gate insulator and threshold‐voltage shift in the IGZO layer, we achieve high radiation hardness. These TFTs in FPD are ideal for medical imaging and nondestructive inspection.

Application of Artificial Intelligence in Solar System Exploration and Beyond

Carl Sagan’s reflections emphasize the boundless potential awaiting humanity in space, regardless of our past achievements or failures. This optimistic view resonates with current space agencies, private space startups, and enthusiasts, all driven by the ambition to make humans a multiplanetary species. Key examples include Elon Musk’s goal to terraform Mars, despite skepticism from some scientists. Space exploration faces numerous challenges, such as dealing with space debris, unpredictable climates on other planets, and the complexities of missions like NASA’s attempts to land on Mars. Space missions confront obstacles in navigation, life detection, and sample testing. Astronauts also encounter physical and mental limitations due to the harsh conditions of space. Artificial Intelligence (AI) has emerged as a crucial tool in addressing these challenges. AI is categorized into supervised learning, unsupervised learning, and semi-supervised learning, with reinforcement learning being a distinct method used for autonomous applications. Neural networks, including convolutional and recurrent neural networks, mimic human behavior for tasks like image inspection and sequential data handling. Deep learning aids in complex pattern recognition, and natural language processing facilitates speech recognition and development. Expert systems enhance decision-making processes. This review explores various AI applications in space missions. AI technologies have been integral to recent missions such as the James Webb Space Telescope, which uses AI for object and galaxy inspection, and the ARTEMIS mission, which employs AI in designing new spacesuits. SpaceX leverages AI for reusable launch vehicles, while the European Space Agency (ESA) uses AI for autonomous spacecraft to cut mission costs. India plans to launch the AI-based Vyommitra robot in space and has utilized AI in the Chandrayaan mission for landing and navigation. Mars exploration benefits significantly from AI, given the planet’s unpredictable weather and cratered surface. AI technologies, like the OASIS system, aid in mission planning and rover navigation. AI also supports space agriculture research, as demonstrated by the UAE’s habitat design efforts. Beyond Mars, AI influences the exploration of asteroids and deep space. AI techniques, such as convolutional neural networks, assist in space dynamics calculations to predict asteroid trajectories and potential Earth impacts. AI has been employed in Voyager missions to seek extraterrestrial life and in the Hubble telescope for imaging exoplanets. AI enhances satellite communication and automates tasks on space stations, saving time and costs. Weather satellites, powered by AI, provide crucial alerts for natural disasters. Despite the challenges, AI offers promising solutions for advancing space exploration. The historical tendency to deem certain challenges insurmountable is gradually shifting, as past impossibilities, like human flight and space travel, have become historical milestones. This reinforces the importance of maintaining hope and persistence in the quest to explore space, as today's dreams may become tomorrow's history.

Enhancing Accuracy in Breast Density Assessment Using Deep Learning: A Multicentric, Multi-Reader Study.

The evaluation of mammographic breast density, a critical indicator of breast cancer risk, is traditionally performed by radiologists via visual inspection of mammography images, utilizing the Breast Imaging-Reporting and Data System (BI-RADS) breast density categories. However, this method is subject to substantial interobserver variability, leading to inconsistencies and potential inaccuracies in density assessment and subsequent risk estimations. To address this, we present a deep learning-based automatic detection algorithm (DLAD) designed for the automated evaluation of breast density. Our multicentric, multi-reader study leverages a diverse dataset of 122 full-field digital mammography studies (488 images in CC and MLO projections) sourced from three institutions. We invited two experienced radiologists to conduct a retrospective analysis, establishing a ground truth for 72 mammography studies (BI-RADS class A: 18, BI-RADS class B: 43, BI-RADS class C: 7, BI-RADS class D: 4). The efficacy of the DLAD was then compared to the performance of five independent radiologists with varying levels of experience. The DLAD showed robust performance, achieving an accuracy of 0.819 (95% CI: 0.736-0.903), along with an F1 score of 0.798 (0.594-0.905), precision of 0.806 (0.596-0.896), recall of 0.830 (0.650-0.946), and a Cohen's Kappa (κ) of 0.708 (0.562-0.841). The algorithm achieved robust performance that matches and in four cases exceeds that of individual radiologists. The statistical analysis did not reveal a significant difference in accuracy between DLAD and the radiologists, underscoring the model's competitive diagnostic alignment with professional radiologist assessments. These results demonstrate that the deep learning-based automatic detection algorithm can enhance the accuracy and consistency of breast density assessments, offering a reliable tool for improving breast cancer screening outcomes.

Improved Positron Emission Tomography Quantification: Evaluation of a Maximum-Likelihood Scatter Scaling Algorithm.

Incorrect scatter scaling of positron emission tomography (PET) images can lead to halo artifacts, quantitative bias, or reconstruction failure. Tail-fitted scatter scaling (TFSS) possesses performance limitations in multiple cases. This study aims to investigate a novel method for scatter scaling: maximum-likelihood scatter scaling (MLSS) in scenarios where TFSS tends to induce artifacts or are observed to cause reconstruction abortion. [68Ga]Ga-RGD PET scans of nine patients were included in cohort 1 in the scope of investigating the reduction of halo artifacts relative to the scatter estimation method. PET scans of 30 patients administrated with [68Ga]Ga-uPAR were included in cohort 2, used for an evaluation of the robustness of MLSS in cases where TFSS-integrated reconstructions are observed to fail. A visual inspection of MLSS-corrected images scored higher than TFSS-corrected reconstructions of cohort 1. The quantitative investigation near the bladder showed a relative difference in tracer uptake of up to 94.7%. A reconstruction of scans included in cohort 2 resulted in failure in 23 cases when TFSS was used. The lesion uptake values of cohort 2 showed no significant difference. MLSS is suggested as an alternative scatter-scaling method relative to TFSS with the aim of reducing halo artifacts and a robust reconstruction process.

Novel Tb3+ doped borophosphate glass scintillator for X-ray imaging

In this study, we introduce an efficient green-emitting material made from Tb3+ doped borophosphate scintillating glass for X-ray imaging. An influence of Tb2O3 concentration on the physical, optical, luminescent, and scintillation properties of glasses were investigated. The glass density and refractive index increase, while the molar volume and Tb3+ inter-ionic distance decreases with Tb2O3 addition. These glasses absorb the photons in range of UV, Vis, and NIR. The excitations by UV and X-ray on glasses causes the strong green emission centered around 545 nm by the 5D4 → 7F5 transition of Tb3+. The energy transfer from Gd3+ to Tb3+ was occurred in this emission. The glass doped with 4 mol% of Tb2O3 demonstrates the highest emission intensity at 545 nm due to the concentration quenching. The decay time of glasses are in few milliseconds. The integral X-ray scintillation efficiency of 4 mol% doped glass is 52% compared to that of BGO crystal. Additionally, this glass was proceeded in the X-ray imaging and yielded the image with satisfied resolution, characteristics and MTF values, compared to that obtained from YAG:Ce crystal. The developed glass has a potential for X-ray imaging applications, especially in the medical imaging, flaw detection, and security inspection.

Stower-13: A Multi-View Inspection Image Dataset for the Automatic Classification and Naming of Tension Towers

In high-voltage transmission lines, the tension tower needs to withstand the tension load of the overhead power line for a long time, which is prone to damage, and it is an important part of the inspection in the circuit inspection. In the modern circuit inspection process, operation and maintenance personnel mostly use unmanned aerial vehicles (UAVs) to photograph various parts of the tension tower, obtain inspection images, and manually classify and name the massive inspection images, which is low in accuracy and efficiency. Based on the above problems, this paper collects a large number of real-life UAV inspection images of various parts of a tension tower, and proposes the Stower-13 inspection image dataset, which is used to train the classification model to achieve automatic classification and naming of inspection images. Based on this dataset, this paper also proposes an improved MobileViT model, in which the Scale-Correlated Pyramid Convolution Block Attention Block (SCPCbam) module is introduced, which adds the Convolution Block Attention Module (CBAM) to the four branches of the original Scale-Correlated Pyramid Convolution (SCPC) module, so as to strengthen the ability of image multi-scale information extraction and improve the classification accuracy. This paper discusses a number of experiments on the model, and the experimental results show that the dataset proposed in this paper helps the model to understand the feature information. At the same time, the improved MobileViT model has a strong ability to extract image spatial feature information, the classification accuracy is higher than that of other models of the same type, so it is able to cope with a wide range of problems that arise in the course of practice, and it meets the practical needs of automatically naming transmission line inspection images.

Prohibited Item Detection Within X-Ray Security Inspection Images Based on an Improved Cascade Network

Prohibited Item Detection Within X-Ray Security Inspection Images Based on an Improved Cascade Network

An Adaptive Steganography Insertion Technique Based on Cosine Transform

In the last couple decades, several successful steganography approaches have been proposed. Least Significant Bit (LSB) Insertion technique has been deployed due to its simplicity in implementation and reasonable payload capacity. The most important design parameter in LSB techniques is the embedding location selection criterion. In this work, LSB insertion technique is proposed which is based on selecting the embedding locations depending on the weights of coefficients in Cosine domain (2D DCT). The cover image is transformed to the Cosine domain (by 2D DCT) and predefined number of coefficients are selected to embed the secret message (which is in the binary form). Those weights are the outputs of an adaptive algorithm that analyses the cover image in two domains (Haar and Cosine). Coefficients, in the Cosine transform domain, with small weights are selected. The proposed approach is tested with samples from the BOSSbase, and a custom-built databases. Two metrics are utilized to show the effectiveness of the technique, namely, Root Mean Squared Error (RMSE), and Peak Signal-to-Noise Ratio (PSNR). In addition, human visual inspection of the result image is also considered. As shown in the results, the proposed approach performs better, in terms of (RMSE, and PSNR) than commonly employed truncation and energy based methods.

Research on adaptive shooting algorithm for unmanned aerial vehicles under typical operating conditions of overhead transmission lines

We consider typical environmental conditions, such as different shooting backgrounds, lighting, and shooting distances, and study adaptive shooting algorithms for unmanned aerial vehicle (UAV) on-site environments under typical working conditions to achieve high-quality acquisition of UAV inspection images and reduce the technical difficulty of artificial intelligence recognition of inspection images. Based on the collected high-quality images and the characteristics of unmanned aerial vehicle inspection images, a deep learning technology framework is adopted to study the intelligent identification method of hidden dangers in transmission line equipment and channel environment, achieving the intelligent recognition of pin level fine particle defects.

Automatic Detection of Pavement Marking Defects in Road Inspection Images Using Deep Learning

Automatic Detection of Pavement Marking Defects in Road Inspection Images Using Deep Learning

Implementation of quality control systems based on machine vision and web technologies

The development of Computer Vision technologies has seen widespread adoption in various fields over the last time, including medicine, manufacturing, transportation, logistics, agriculture, and chemical industry. Research analysis indicates that Computer Vision and its practical implementation, known as Machine Vision, are widely used for defect detection in production and equipment. Despite significant research progress in this field in recent years, many unresolved issues remain concerning the quality and dimensions of input data, selection of image recognition models and their training, and the accuracy of results. Integration of machine vision system elements for information exchange and decision-making poses a significant challenge. This paper presents one approach to addressing this issue. The aim of the paper is to explore the implementation approach of quality control systems using web technologies. The task of detecting defects in printed circuit boards (PCBs) is common in many manufacturing processes. PCB inspection involves comparing the current PCB sample with a defect-free reference. Essentially, this task involves comparing two images and identifying differences between them. Defect recognition is based on the Structural Similarity Index (SSIM), which computes the degradation component reflecting the difference between images and the similarity component. The SSIM metric is already implemented in image processing libraries. This work utilizes calculations using OpenCV and scikit-image image libraries. To automate the PCB comparison process and address deployment and integration challenges at the SCADA level, a web application has been developed. This web application allows users to select a reference PCB image and upload the current PCB image for inspection. For the client-side implementation, Vue.js was chosen due to its popularity and efficiency in developing web interfaces, particularly Single Page Applications (SPAs). Vue.js's reactive system ensures automatic updates to reflect changes in data state. For the server-side implementation, Flask – a Python framework, was used, facilitating integration with the PCB comparison algorithm as both utilize Python. According to the available features, operators can upload two images – a reference PCB image and the PCB image to be compared with the reference. After uploading, the images are displayed in the system interface. On the server side, the received data is decoded and compared using the appropriate algorithms. After comparison, the results are encoded in base64 format and sent back to the client-side for display, allowing the operator to assess the similarity or differences between the PCBs. The application can operate in both automatic and manual modes. Therefore, an analysis of the challenges encountered in implementing and deploying quality control systems based on computer vision methods has been developed. The use of web technologies, particularly Python frameworks, for integrating developed models is proposed. This approach is demonstrated using the example of PCB defect recognition tasks.

Vision AI System Development for Improved Productivity in Challenging Industrial Environments: A Sustainable and Efficient Approach

This study presents a development plan for a vision AI system to enhance productivity in industrial environments, where environmental control is challenging, by using AI technology. An image pre-processing algorithm was developed using a mobile robot that can operate in complex environments alongside workers to obtain high-quality learning and inspection images. Additionally, the proposed architecture for sustainable AI system development included cropping the inspection part images to minimize the technology development time, investment costs, and the reuse of images. The algorithm was retrained using mixed learning data to maintain and improve its performance in industrial fields. This AI system development architecture effectively addresses the challenges faced in applying AI technology at industrial sites and was demonstrated through experimentation and application.